{"id":"b4e79ef0-d966-4bae-b0e5-e3a490cdd934","entityType":"agent","slug":"clawhub-xiaoba-dev-rotifer-guide","name":"rotifer-guide","canonicalUrl":"https://www.xpersona.co/agent/clawhub-xiaoba-dev-rotifer-guide","canonicalPath":"/agent/clawhub-xiaoba-dev-rotifer-guide","generatedAt":"2026-10-11T07:39:56.256Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:48:48.305Z","emptyReason":null},"description":"Entry point for Rotifer Protocol — onboarding to Rotifer Genes, scaffolding a Gene from a description, diagnosing a Gene's F(g) or compile failure, searching the Rotifer Gene registry, and upgrading a Gene's fidelity from Wrapped to Native. Invoke explicitly when starting with Rotifer, or when unsure which Rotifer capability to use. Do NOT use for general onboarding, tutorials, troubleshooting, or search — every capability here operates on Rotifer Genes and the Rotifer CLI, and nothing else.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s174dvd7sg66gw86h4t3c8575d83g51m:rotifer-guide","sourceUrl":"https://clawhub.ai/xiaoba-dev/rotifer-guide","homepage":"https://clawhub.ai/xiaoba-dev/skills/rotifer-guide","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/xiaoba-dev/rotifer-guide","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/xiaoba-dev/skills/rotifer-guide","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"rotifer-guide technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:48:48.305Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:48:48.305Z","emptyReason":null},"stars":null,"forks":null,"downloads":1155,"packageName":null,"latestVersion":"1.2.2","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:48:48.291Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T04:48:48.305Z","lastCrawledAt":"2026-10-11T04:48:48.291Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T04:48:48.291Z","lastVerifiedAt":null,"highlights":[{"version":"1.2.2","createdAt":"2026-09-20T13:21:12.734Z","changelog":"rotifer-guide v1.2.2 - Pins Rotifer CLI to version 0.26.0 and MCP server to 0.17.0 for all commands and instructions, updating all user guidance and prerequisite checks accordingly. - Updates related skill references to use new consistent prefixes (e.g., `rotifer-gene`, `rotifer-genome`). - Improves CLI usage recommendations for reproducibility and reviewability, including lockfile and integrity guidance. - Removes deprecated file: skill-card.md. - Documentation and manifest updates to clarify exact versioning, installation, and routing behaviors.","fileCount":5,"zipByteSize":10365},{"version":"1.2.1","createdAt":"2026-08-17T14:55:02.061Z","changelog":"rotifer-guide v1.2.1 - Improved intent routing: clearer guidance for when and how this skill should be invoked. - Updated onboarding and scaffold documentation for accuracy and concise user signals. - Clarified that this skill only operates in Rotifer contexts, preventing accidental invocation for non-Rotifer scenarios. - Minor edits for precision and directness in workflow descriptions.","fileCount":5,"zipByteSize":9848},{"version":"1.2.0","createdAt":"2026-08-17T14:39:38.022Z","changelog":"rotifer-guide v1.2.0 - Clarified intended use: not for general onboarding, tutorials, troubleshooting, or search — Rotifer Genes/CLI only. - Updated SKILL.md description and instructions for clearer scope boundaries. - Removed deprecated skill-card.md file. - No changes to core workflow or sub-capabilities (onboarding, scaffold, doctor, explorer, upgrade). - Minor refinements to explanations, user prompts, and fallback logic.","fileCount":5,"zipByteSize":9073},{"version":"1.1.1","createdAt":"2026-08-17T09:21:10.858Z","changelog":"rotifer-guide 1.1.1 - Added an explicit section detailing exactly what this Skill does on your machine, including which commands it runs, what it reads/writes, and when it sends data to the cloud. - Clarified in the scaffold (natural-language scaffolding) section that Path A transmits user content to rotifer.ai, and that local CLI fallback does not; users are prompted to confirm when content is sent online. - Enhanced transparency and user control by stating that commands which install, publish, or overwrite are only run with user approval. - No core workflow or command changes; all flows remain as before. - Documentation improvements for clarity and user privacy awareness.","fileCount":5,"zipByteSize":9030},{"version":"1.1.0","createdAt":"2026-08-17T09:11:33.864Z","changelog":"rotifer-guide v1.1.0 - Adds explicit Web Studio (rotifer.ai) workflow for LLM-backed scaffolding, including backend API endpoints and offline CLI fallback. - Updates onboarding to default to `rotifer hello` for fastest demo, and clarifies prerequisites and troubleshooting (e.g., `rotifer doctor`). - Improves clarity on when to use backend vs CLI for scaffold, showing network-aware instructions. - Clarifies and modernizes intent routing and related skills, with new references to `gene` modules. - Removes the obsolete skill-card and streamlines examples and next-step guidance.","fileCount":5,"zipByteSize":8462},{"version":"1.0.3","createdAt":"2026-04-15T15:13:05.361Z","changelog":"Add Prerequisites section with CLI and MCP setup instructions (no hardcoded versions)","fileCount":5,"zipByteSize":6650},{"version":"1.0.2","createdAt":"2026-04-15T14:02:47.092Z","changelog":"Fix untagged code blocks rendering as invisible text on ClawHub","fileCount":4,"zipByteSize":5184},{"version":"1.0.1","createdAt":"2026-04-15T13:59:32.080Z","changelog":"Translate to English; fix rendering","fileCount":4,"zipByteSize":5181}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s174dvd7sg66gw86h4t3c8575d83g51m:rotifer-guide","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s174dvd7sg66gw86h4t3c8575d83g51m:rotifer-guide` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/xiaoba-dev/rotifer-guide before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T07:39:56.250Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-guide/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:48:48.305Z","emptyReason":null},"readme":"Skill: rotifer-guide\n\nOwner: xiaoba-dev\n\nSummary: Entry point for Rotifer Protocol — onboarding to Rotifer Genes, scaffolding a Gene from a description, diagnosing a Gene's F(g) or compile failure, searching the Rotifer Gene registry, and upgrading a Gene's fidelity from Wrapped to Native. Invoke explicitly when starting with Rotifer, or when unsure which Rotifer capability to use. Do NOT use for general onboarding, tutorials, troubleshooting, or search — every capability here operates on Rotifer Genes and the Rotifer CLI, and nothing else.\n\nTags: latest:1.2.2\n\nVersion history:\n\nv1.2.2 | 2026-09-20T13:21:12.734Z | auto\n\nrotifer-guide v1.2.2\n\n- Pins Rotifer CLI to version 0.26.0 and MCP server to 0.17.0 for all commands and instructions, updating all user guidance and prerequisite checks accordingly.\n- Updates related skill references to use new consistent prefixes (e.g., `rotifer-gene`, `rotifer-genome`).\n- Improves CLI usage recommendations for reproducibility and reviewability, including lockfile and integrity guidance.\n- Removes deprecated file: skill-card.md.\n- Documentation and manifest updates to clarify exact versioning, installation, and routing behaviors.\n\nv1.2.1 | 2026-08-17T14:55:02.061Z | auto\n\nrotifer-guide v1.2.1\n\n- Improved intent routing: clearer guidance for when and how this skill should be invoked.\n- Updated onboarding and scaffold documentation for accuracy and concise user signals.\n- Clarified that this skill only operates in Rotifer contexts, preventing accidental invocation for non-Rotifer scenarios. \n- Minor edits for precision and directness in workflow descriptions.\n\nv1.2.0 | 2026-08-17T14:39:38.022Z | auto\n\nrotifer-guide v1.2.0\n\n- Clarified intended use: not for general onboarding, tutorials, troubleshooting, or search — Rotifer Genes/CLI only.\n- Updated SKILL.md description and instructions for clearer scope boundaries.\n- Removed deprecated skill-card.md file.\n- No changes to core workflow or sub-capabilities (onboarding, scaffold, doctor, explorer, upgrade).\n- Minor refinements to explanations, user prompts, and fallback logic.\n\nv1.1.1 | 2026-08-17T09:21:10.858Z | auto\n\nrotifer-guide 1.1.1\n\n- Added an explicit section detailing exactly what this Skill does on your machine, including which commands it runs, what it reads/writes, and when it sends data to the cloud.\n- Clarified in the scaffold (natural-language scaffolding) section that Path A transmits user content to rotifer.ai, and that local CLI fallback does not; users are prompted to confirm when content is sent online.\n- Enhanced transparency and user control by stating that commands which install, publish, or overwrite are only run with user approval.\n- No core workflow or command changes; all flows remain as before.\n- Documentation improvements for clarity and user privacy awareness.\n\nv1.1.0 | 2026-08-17T09:11:33.864Z | auto\n\nrotifer-guide v1.1.0\n\n- Adds explicit Web Studio (rotifer.ai) workflow for LLM-backed scaffolding, including backend API endpoints and offline CLI fallback.\n- Updates onboarding to default to `rotifer hello` for fastest demo, and clarifies prerequisites and troubleshooting (e.g., `rotifer doctor`).\n- Improves clarity on when to use backend vs CLI for scaffold, showing network-aware instructions.\n- Clarifies and modernizes intent routing and related skills, with new references to `gene` modules.\n- Removes the obsolete skill-card and streamlines examples and next-step guidance.\n\nv1.0.3 | 2026-04-15T15:13:05.361Z | user\n\nAdd Prerequisites section with CLI and MCP setup instructions (no hardcoded versions)\n\nv1.0.2 | 2026-04-15T14:02:47.092Z | user\n\nFix untagged code blocks rendering as invisible text on ClawHub\n\nv1.0.1 | 2026-04-15T13:59:32.080Z | user\n\nTranslate to English; fix rendering\n\nv1.0.0 | 2026-04-15T13:52:58.244Z | user\n\nInitial release: interactive onboarding, scaffold, doctor, explorer, upgrade\n\nArchive index:\n\nArchive v1.2.2: 5 files, 10365 bytes\n\nFiles: clawhub.json (871b), README.md (3758b), skill-card.md (2342b), SKILL.md (15555b), _meta.json (132b)\n\nFile v1.2.2:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Entry point for Rotifer Protocol — onboarding to Rotifer Genes, scaffolding a Gene from a\n description, diagnosing a Gene's F(g) or compile failure, searching the Rotifer Gene registry,\n and upgrading a Gene's fidelity from Wrapped to Native.\n Invoke explicitly when starting with Rotifer, or when unsure which Rotifer capability to use.\n Do NOT use for general onboarding, tutorials, troubleshooting, or search — every capability\n here operates on Rotifer Genes and the Rotifer CLI, and nothing else.\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Prerequisites\n\nBefore using this Skill, ensure the Rotifer CLI is available:\n\n```bash\nnpx --yes @rotifer/playground@0.26.0 --version\n```\n\nIf you prefer MCP integration instead of CLI, add this to your MCP config:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server@0.17.0\"]\n }\n }\n}\n```\n\nBoth commands name an exact version on purpose. An unversioned `npx` resolves to whatever the\nregistry serves at that moment, so the code you run would not be the code that was reviewed. The\n`@rotifer/mcp-server` pin is the one this repository agrees on everywhere; move it in one deliberate\nstep, not per file. Stronger than pinning the `npx` call: install the CLI into the project and run\nthe local binary.\n\n```bash\nnpm install --save-dev --save-exact @rotifer/playground@0.26.0\nnpm exec -- rotifer --version\n```\n\nCommit the lockfile and use `npm ci` in automation. Before moving a pin to a newer release, review\nwhat changed and record what you are accepting: `npm view @rotifer/playground@ dist.integrity`.\n\n---\n\n## Intent Router\n\n**Every row assumes the user is already asking about Rotifer.** The signals below\nroute *within* this Skill; they are not reasons to invoke it. A user asking \"how\ndo I get started\" or \"why is my score 0\" without Rotifer in view is asking\nsomeone else.\n\n| User signal (in a Rotifer context) | Sub-capability | Action |\n|-------------|---------------|--------|\n| What is a Gene / how does Rotifer work / new to Rotifer | **onboarding** | Interactive walkthrough, or `rotifer hello` |\n| Create a Gene / scaffold a Gene / wrap this as a Gene | **scaffold** | Natural-language scaffolding |\n| F(g) is 0 / `rotifer compile` fails / `rotifer publish` fails | **doctor** | `rotifer doctor` first, then the Gene |\n| Find a Gene that / any Gene for / search the registry | **explorer** | `rotifer search` |\n| Wrapped to Native / upgrade fidelity / rewrite this Gene | **upgrade** | Fidelity evolution |\n\nWhen the request is about Rotifer but the sub-capability is unclear, list all\nfive and let the user choose. When the request is **not** about Rotifer, say so\nand stop — do not map it onto the nearest row.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|---------------|\n| `rotifer-gene` → `modules/dev.md` | Deep technical manual for scaffold / onboarding | User needs full development workflow details |\n| `rotifer-gene` → `modules/migration.md` | Deep migration manual for upgrade | After user confirms migration plan |\n| `rotifer-arena/SKILL.md` | Comparison & evaluation entry | User wants to compare Genes / run Arena |\n| `rotifer-genome/SKILL.md` | Gene composition | User wants to combine multiple Genes into an Agent |\n\n---\n\n## What this Skill does on your machine\n\nIt has no code of its own — it tells your assistant which `rotifer` commands to\nrun. That is why its manifest declares process execution, filesystem read/write\nand outbound network access: every one of those is the CLI acting, not this\nSkill.\n\n| | |\n|---|---|\n| **Runs** | The `rotifer` CLI, pinned to `@rotifer/playground@0.26.0`; fetched from npm at that exact version if it is not already installed. |\n| **Reads** | Genes and Agent definitions in the current project workspace. |\n| **Writes** | Only what the commands below write — Genes into the project's `genes/`, Agent definitions into `.rotifer/agents/`. Nothing outside the project. |\n| **Sends** | Cloud registry and Arena queries, to the public Rotifer API. Your code is not uploaded unless you run `rotifer publish` yourself. |\n\nCommands that install, publish or overwrite are proposed for your approval\nfirst, never run silently.\n\n---\n\n## 1. onboarding — Interactive Walkthrough\n\n### Phase 1: Environment Check\n\n```bash\nnpx --yes @rotifer/playground@0.26.0 --version\nrotifer doctor\nrotifer list\n```\n\nIf the CLI is missing: `npm i -g @rotifer/playground@0.26.0`, which installs the `rotifer` binary at that exact version.\n\n`rotifer doctor` checks the TypeScript→WASM toolchain (esbuild / javy). Run it\nfirst: without that toolchain `rotifer compile` fails at the WASM step, and the\nerror looks like a code problem rather than a missing tool. It exits non-zero\nand prints the install line when something is absent.\n\n### Phase 2: Core Concepts\n\n| Concept | One-liner | Analogy |\n|---------|-----------|---------|\n| Gene | Self-contained logic unit: `express(input) → output` | Function |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure | Compiler optimization level |\n| Arena | Genes compete for ranking via F(g) fitness score | Leaderboard |\n| Domain | Two-level category like `content.grammar` | Namespace |\n| phenotype.json | Gene metadata | package.json |\n| R(g) / V(g) | Reputation score / Security score | Credit rating |\n\n### Phase 3: Hands-on Experience\n\nTwo paths — pick by what the user wants first, a result or an understanding.\n\n**Fastest result — `rotifer hello`:**\n\n```bash\nrotifer hello\n```\n\nAn interactive builder: pick one of six templates (quality-advisor,\nuiux-diagnosis, content-analysis, code-security, doc-qa, web3-toolkit), and it\nselects Genes, composes them, creates the Agent and runs it. Use this when the\nuser wants to *see* Rotifer work before learning what a Gene is.\n`rotifer hello --list-templates` shows what is on offer; `--template `,\n`--input `, `--file ` and `--dir ` skip the prompts.\n\n**Full lifecycle — one command per concept:**\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\nAfter each step, explain the output and confirm the user understands before proceeding.\n\n### Phase 4: Next Steps\n\nRecommend based on user background:\n- Has an existing SKILL.md → scaffold (`rotifer wrap`)\n- Wants to browse the ecosystem → explorer\n- Wants to dive deeper → route to `rotifer-gene` skill (`modules/dev.md`)\n\n---\n\n## 2. scaffold — Natural-Language Scaffolding\n\n> This sub-capability is **backend-backed**. When network is available, scaffold uses\n> the `/api/playground/*` endpoints on rotifer.ai for LLM-assisted Gene generation, V(g) scanning,\n> and one-click Cloud publish. The CLI path remains as fallback.\n\n### Phase 1: Intent Extraction\n\nExtract from the user's natural-language description:\n\n| Parameter | Extraction method | Default |\n|-----------|------------------|---------|\n| name | Generate kebab-case from description | Must confirm |\n| domain | Infer two-level domain from functionality | Must confirm |\n| fidelity | Needs external API → Hybrid, pure computation → Native, quick prototype → Wrapped | Wrapped |\n\n### Phase 2: Confirm Parameters\n\nPresent inferred results to the user, wait for confirmation before executing.\n\n### Phase 3: Scaffold Generation\n\n**Path A — Web Studio (backend-backed, preferred when online):**\n\nUse the rotifer.ai Playground API for LLM-assisted generation:\n\n```\n1. POST /api/playground/generate { prompt, domain } → { source, phenotype }\n2. POST /api/playground/scan { source } → { grade, findings }\n3. POST /api/playground/publish { source, phenotype } → { published, grade }\n```\n\nThe Web Studio UI at `https://rotifer.ai/studio/` provides a visual 3-step flow\n(Describe → Create → Publish) that calls these same endpoints.\n\n> **This path sends the user's text to rotifer.ai.** `generate` transmits the\n> description they wrote; `scan` transmits the generated source; `publish`\n> transmits source and phenotype and makes the Gene public. Say so before\n> using it, and offer Path B when the description contains anything the user\n> would not post publicly — Path B is entirely local and produces the same\n> scaffold without a network call.\n\n**Path B — CLI (local, always available):**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**From an existing SKILL.md:**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**From ClawHub:**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \n```\n\nAfter compilation passes, prompt: publish to Cloud (`rotifer publish`) or submit to Arena (`rotifer arena submit`).\n\n`rotifer publish` defaults to uploading to the Rotifer Cloud Registry.\nDisable with `rotifer config set default-publish false` or `ROTIFER_AUTO_PUBLISH=false`.\n\n### Offline Fallback\n\nIf the Playground API is unreachable, display:\n\n> Network unavailable. Use `rotifer init` for local-only Gene creation.\n\nThen follow Path B (CLI).\n\nFor deeper development details (inputSchema design, express function implementation) → route to `rotifer-gene` skill (`modules/dev.md`).\n\n---\n\n## 3. doctor — Diagnostics & Repair\n\n### Decision Tree\n\n```text\nUser reports a problem\n |\n +-- F(g) = 0 or abnormally low score\n | +-- Does rotifer test pass?\n | | +-- Fails → Check if express() return value matches outputSchema\n | | +-- Passes → Check if phenotype.json domain is reasonable\n | +-- Are there competitors in the same domain?\n | +-- Yes → Analyze competitor strengths, suggest optimizations\n |\n +-- Publish failed\n | +-- Does rotifer compile succeed?\n | | +-- Fails → rotifer doctor first, then syntax errors / missing dependencies\n | | +-- Succeeds → rotifer whoami — signed in at all, and as whom?\n | | Then check network connectivity\n | +-- Is phenotype.json format valid?\n |\n +-- Compilation failed\n | +-- FIRST: rotifer doctor — is the TS→WASM toolchain even installed?\n | | +-- Reports esbuild / javy missing → install those; the code is not the problem\n | +-- Check the exported express function signature in index.ts\n | +-- Check inputSchema / outputSchema in phenotype.json\n | +-- Check if fidelity declaration matches actual code\n | +-- Declared Native but has fetch calls → Change to Hybrid or remove network calls\n |\n +-- Runtime error\n +-- rotifer test --verbose\n +-- Check if input conforms to inputSchema\n +-- Check if express() handles edge cases correctly\n```\n\n### Common Diagnostic Commands\n\n```bash\nrotifer doctor # TS→WASM toolchain — run this before blaming the code\nrotifer test \nrotifer vg # V(g) security scan — grade A–D, or ? for a code-free Skill\nrotifer list\nrotifer arena list --domain \nrotifer arena watch # live ranking movement (Ctrl+C to stop)\n```\n\n`rotifer doctor` takes no arguments and checks one thing: whether esbuild and\njavy are present and reachable on `PATH`. A missing toolchain surfaces as a\ncompile failure that reads like a code error, so it is the cheapest first move\non any \"compilation failed\" report.\n\n### Quick Reference\n\n| Symptom | Root cause | Fix |\n|---------|-----------|-----|\n| F(g) = 0 | express() returns empty or format mismatch | Fix return value to match outputSchema |\n| Compilation failed | TypeScript type error | Check express function signature |\n| Publish timeout | Cloud credentials expired | `rotifer whoami` to check, then `rotifer login` |\n| Arena ranking dropped | Stronger competitor appeared in same domain | `rotifer arena watch ` to see who moved, then optimize or upgrade fidelity |\n| Fidelity mismatch | Native declared but has fetch calls | Remove network calls or change declaration to Hybrid |\n| `compile` fails but the code looks fine | esbuild / javy missing from the toolchain | `rotifer doctor`, then install what it names |\n\n---\n\n## 4. explorer — Ecosystem Search\n\n### Phase 1: Understand the Need\n\nExtract from user description: functionality keywords, target domain, fidelity preference.\n\n### Phase 2: Search\n\n`rotifer search` is the ecosystem search — it queries the Cloud registry, which\nis where Genes published by other people live. `arena list` ranks what is\nalready in the Arena and `list` shows what is on this machine; all three answer\ndifferent questions, so pick by what the user asked for.\n\n```bash\nrotifer search # the ecosystem — Cloud registry\nrotifer search --domain --fidelity Native --sort downloads\nrotifer arena list --domain # ranked competitors in one domain\nrotifer list # what is already installed here\n```\n\nFollow up on a specific result:\n\n```bash\nrotifer info # full details, local or Cloud\nrotifer reputation # R(g) — the reputation column below\nrotifer stats # downloads: 7d / 30d / 90d / all time\nrotifer versions @owner/ # version history chain\nrotifer compare # 2–5 published Genes, side by side\n```\n\n`rotifer reputation @username` scores a creator instead of a Gene, and\n`--leaderboard` ranks creators.\n\n### Phase 3: Result Analysis\n\nDisplay search results in a table:\n\n| Field | Description |\n|-------|-------------|\n| name | Gene name |\n| domain | Category |\n| fidelity | Native / Hybrid / Wrapped |\n| F(g) | Fitness score |\n| R(g) | Reputation score |\n\n### Phase 4: Recommendation\n\n- Found a matching Gene → suggest install: `rotifer install `\n- Found a partial match → suggest fork and modify, or submit an Arena challenge (route to `rotifer-arena/SKILL.md`)\n- Nothing found → suggest creating a new Gene (route to scaffold)\n\n---\n\n## 5. upgrade — Fidelity Evolution\n\n### Phase 1: Assess Current State\n\n```bash\nrotifer list\n```\n\nCheck the target Gene's phenotype.json — confirm current fidelity and express() implementation.\n\n### Phase 2: Migration Path Decision\n\n| Current | Target | Condition | Path |\n|---------|--------|-----------|------|\n| Wrapped | Native | Functionality can be implemented as pure computation | Rewrite express(), remove all external calls |\n| Wrapped | Hybrid | Must call external APIs | Add WASM shell + allowedDomains whitelist |\n| Hybrid | Native | Can internalize API dependencies | Replace API calls with local algorithms |\n\n### Phase 3: Execute Migration\n\nAfter confirming the migration plan, route to `rotifer-gene` skill (`modules/migration.md`) for the full migration workflow.\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer vg \nrotifer compile \nrotifer arena submit \nrotifer arena watch \n```\n\nA fidelity upgrade rewrites the Gene's code, so the V(g) security grade it\nearned before the rewrite no longer describes it — `rotifer vg` re-scans and\nreturns A–D (or `?` when there is no `src/`). Compare F(g) before and after to\nconfirm ranking continuity; `arena watch` shows the move happening rather than\nrequiring a second `arena list`.\n\nFile v1.2.2:README.md\n\n# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n**Not a general help desk.** Every capability here operates on Rotifer Genes and\nthe Rotifer CLI. It is not for general onboarding, tutorials, troubleshooting or\nsearch — if the request is not about Rotifer, this is the wrong Skill.\n\n## What It Does\n\nOne Skill, five capabilities — each one asks about **Rotifer**:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — core concepts with hands-on CLI examples, or `rotifer hello` for a working Agent in one command |\n| \"Create a Rotifer Gene that checks grammar\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene's F(g) is 0\" / \"`rotifer compile` fails\" | **Doctor** — `rotifer doctor` for the toolchain first, then the Gene itself |\n| \"Find a Rotifer Gene for web search\" | **Explorer** — `rotifer search` across the Gene registry |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, re-scans V(g) after the rewrite |\n\n## Quick Start\n\nInvoke it explicitly when you are working with Rotifer, then describe what you\nneed in natural language:\n\n```\nI want to create a Rotifer Gene that summarizes web pages\n```\n\nThe Skill picks the right sub-capability and walks you through the workflow. It\ndoes not activate on ordinary requests that happen to mention creating,\nsearching or diagnosing something — Rotifer has to be what you are working on.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## What this Skill does on your machine\n\nIt has no code of its own — it tells your assistant which `rotifer` commands to\nrun. That is what its manifest's process-execution, filesystem and network\npermissions are for: the CLI acting, not this Skill.\n\n| | |\n|---|---|\n| **Runs** | The `rotifer` CLI, pinned to `@rotifer/playground@0.26.0`; fetched from npm at that exact version if it is not already installed. |\n| **Reads** | Genes and Agent definitions in the current project. |\n| **Writes** | Genes into the project's `genes/`, Agent definitions into `.rotifer/agents/`. Nothing outside the project. |\n| **Sends** | Registry and Arena queries to the public Rotifer API. Two paths send more than a query, and both are opt-in: the Web Studio scaffold path (`/api/playground/generate`, `scan`, `publish`) transmits the description you write and the generated Gene source to rotifer.ai, and `rotifer publish` transmits a Gene's source and makes it public. The CLI scaffold path is entirely local and produces the same result — prefer it for anything you would not post publicly. Nothing else in your project is read or uploaded. |\n\nCommands that install, publish or overwrite are proposed for your approval\nfirst, never run silently. Full detail in [SKILL.md](SKILL.md).\n\n## Related Skills\n\n- [rotifer-arena](https://clawhub.ai/skill/rotifer-arena) — Compare and evaluate Genes\n- [rotifer-agent](https://clawhub.ai/skill/rotifer-agent) — Compose Genes into Agents\n- [rotifer-self-evolving-agent](https://clawhub.ai/skill/rotifer-self-evolving-agent) — Auto-evolve your Agent\n\n## Links\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n\n## License\n\nApache-2.0\n\nFile v1.2.2:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.2.2\",\n \"publishedAt\": 1789910472734\n}\n\nFile v1.2.2:skill-card.md\n\n## Description:\n\nRotifer Guide routes Rotifer-related requests into onboarding, Gene scaffolding, diagnostics, registry search, and fidelity-upgrade workflows for the Rotifer CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[xiaoba-dev](https://clawhub.ai/user/xiaoba-dev)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent builders use this skill when working with Rotifer Genes to choose the right workflow for learning Rotifer concepts, creating Genes, diagnosing compile or fitness issues, searching the registry, or planning fidelity upgrades.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Web Studio scaffold and publish workflows can send the user's prompt and generated Gene source to rotifer.ai, and publishing makes the Gene public.\n\nMitigation: Use the local CLI scaffold path for private work and confirm publish intent before running any command that uploads or publishes a Gene.\n\nRisk: The skill proposes Rotifer CLI commands that may install packages, read project Genes or Agent definitions, and write generated files in the project workspace.\n\nMitigation: Review proposed commands before execution, keep Rotifer package versions pinned, and commit lockfiles for reproducible installs.\n\n## Reference(s):\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Rotifer Documentation](https://rotifer.dev/docs)\n- [Rotifer Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n- [Rotifer Playground Repository](https://github.com/rotifer-protocol/rotifer-playground)\n\n## Skill Output:\n\n**Output Type(s):** [guidance, markdown, shell commands, configuration]\n\n**Output Format:** [Markdown guidance with inline shell commands and JSON configuration snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Routes the user to one of five Rotifer workflows and proposes install, scaffold, diagnostic, search, publish, or upgrade commands for review before execution.]\n\n## Skill Version(s):\n\n1.2.2 (source: server release metadata and clawhub.json)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.2:clawhub.json\n\n{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.2.2\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [\n \"process:exec\",\n \"filesystem:read\",\n \"filesystem:write\",\n \"network:outbound\"\n ],\n \"screenshots\": [],\n \"demo_video\": null\n}\n\nArchive v1.2.1: 5 files, 9848 bytes\n\nFiles: clawhub.json (871b), README.md (3321b), skill-card.md (2298b), SKILL.md (14762b), _meta.json (132b)\n\nFile v1.2.1:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Entry point for Rotifer Protocol — onboarding to Rotifer Genes, scaffolding a Gene from a\n description, diagnosing a Gene's F(g) or compile failure, searching the Rotifer Gene registry,\n and upgrading a Gene's fidelity from Wrapped to Native.\n Invoke explicitly when starting with Rotifer, or when unsure which Rotifer capability to use.\n Do NOT use for general onboarding, tutorials, troubleshooting, or search — every capability\n here operates on Rotifer Genes and the Rotifer CLI, and nothing else.\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Prerequisites\n\nBefore using this Skill, ensure the Rotifer CLI is available:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nIf you prefer MCP integration instead of CLI, add this to your MCP config:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\nNo version pinning needed — both packages resolve to the latest release automatically.\n\n---\n\n## Intent Router\n\n**Every row assumes the user is already asking about Rotifer.** The signals below\nroute *within* this Skill; they are not reasons to invoke it. A user asking \"how\ndo I get started\" or \"why is my score 0\" without Rotifer in view is asking\nsomeone else.\n\n| User signal (in a Rotifer context) | Sub-capability | Action |\n|-------------|---------------|--------|\n| What is a Gene / how does Rotifer work / new to Rotifer | **onboarding** | Interactive walkthrough, or `rotifer hello` |\n| Create a Gene / scaffold a Gene / wrap this as a Gene | **scaffold** | Natural-language scaffolding |\n| F(g) is 0 / `rotifer compile` fails / `rotifer publish` fails | **doctor** | `rotifer doctor` first, then the Gene |\n| Find a Gene that / any Gene for / search the registry | **explorer** | `rotifer search` |\n| Wrapped to Native / upgrade fidelity / rewrite this Gene | **upgrade** | Fidelity evolution |\n\nWhen the request is about Rotifer but the sub-capability is unclear, list all\nfive and let the user choose. When the request is **not** about Rotifer, say so\nand stop — do not map it onto the nearest row.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|---------------|\n| `gene` → `modules/dev.md` | Deep technical manual for scaffold / onboarding | User needs full development workflow details |\n| `gene` → `modules/migration.md` | Deep migration manual for upgrade | After user confirms migration plan |\n| `rotifer-arena/SKILL.md` | Comparison & evaluation entry | User wants to compare Genes / run Arena |\n| `genome/SKILL.md` | Gene composition | User wants to combine multiple Genes into an Agent |\n\n---\n\n## What this Skill does on your machine\n\nIt has no code of its own — it tells your assistant which `rotifer` commands to\nrun. That is why its manifest declares process execution, filesystem read/write\nand outbound network access: every one of those is the CLI acting, not this\nSkill.\n\n| | |\n|---|---|\n| **Runs** | The `rotifer` CLI (`@rotifer/playground`), fetched from npm if not installed. |\n| **Reads** | Genes and Agent definitions in the current project workspace. |\n| **Writes** | Only what the commands below write — Genes into the project's `genes/`, Agent definitions into `.rotifer/agents/`. Nothing outside the project. |\n| **Sends** | Cloud registry and Arena queries, to the public Rotifer API. Your code is not uploaded unless you run `rotifer publish` yourself. |\n\nCommands that install, publish or overwrite are proposed for your approval\nfirst, never run silently.\n\n---\n\n## 1. onboarding — Interactive Walkthrough\n\n### Phase 1: Environment Check\n\n```bash\nnpx @rotifer/playground --version\nrotifer doctor\nrotifer list\n```\n\nIf the CLI is missing: `npm i -g @rotifer/playground`, which installs the `rotifer` binary.\n\n`rotifer doctor` checks the TypeScript→WASM toolchain (esbuild / javy). Run it\nfirst: without that toolchain `rotifer compile` fails at the WASM step, and the\nerror looks like a code problem rather than a missing tool. It exits non-zero\nand prints the install line when something is absent.\n\n### Phase 2: Core Concepts\n\n| Concept | One-liner | Analogy |\n|---------|-----------|---------|\n| Gene | Self-contained logic unit: `express(input) → output` | Function |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure | Compiler optimization level |\n| Arena | Genes compete for ranking via F(g) fitness score | Leaderboard |\n| Domain | Two-level category like `content.grammar` | Namespace |\n| phenotype.json | Gene metadata | package.json |\n| R(g) / V(g) | Reputation score / Security score | Credit rating |\n\n### Phase 3: Hands-on Experience\n\nTwo paths — pick by what the user wants first, a result or an understanding.\n\n**Fastest result — `rotifer hello`:**\n\n```bash\nrotifer hello\n```\n\nAn interactive builder: pick one of six templates (quality-advisor,\nuiux-diagnosis, content-analysis, code-security, doc-qa, web3-toolkit), and it\nselects Genes, composes them, creates the Agent and runs it. Use this when the\nuser wants to *see* Rotifer work before learning what a Gene is.\n`rotifer hello --list-templates` shows what is on offer; `--template `,\n`--input `, `--file ` and `--dir ` skip the prompts.\n\n**Full lifecycle — one command per concept:**\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\nAfter each step, explain the output and confirm the user understands before proceeding.\n\n### Phase 4: Next Steps\n\nRecommend based on user background:\n- Has an existing SKILL.md → scaffold (`rotifer wrap`)\n- Wants to browse the ecosystem → explorer\n- Wants to dive deeper → route to `gene` skill (`modules/dev.md`)\n\n---\n\n## 2. scaffold — Natural-Language Scaffolding\n\n> This sub-capability is **backend-backed**. When network is available, scaffold uses\n> the `/api/playground/*` endpoints on rotifer.ai for LLM-assisted Gene generation, V(g) scanning,\n> and one-click Cloud publish. The CLI path remains as fallback.\n\n### Phase 1: Intent Extraction\n\nExtract from the user's natural-language description:\n\n| Parameter | Extraction method | Default |\n|-----------|------------------|---------|\n| name | Generate kebab-case from description | Must confirm |\n| domain | Infer two-level domain from functionality | Must confirm |\n| fidelity | Needs external API → Hybrid, pure computation → Native, quick prototype → Wrapped | Wrapped |\n\n### Phase 2: Confirm Parameters\n\nPresent inferred results to the user, wait for confirmation before executing.\n\n### Phase 3: Scaffold Generation\n\n**Path A — Web Studio (backend-backed, preferred when online):**\n\nUse the rotifer.ai Playground API for LLM-assisted generation:\n\n```\n1. POST /api/playground/generate { prompt, domain } → { source, phenotype }\n2. POST /api/playground/scan { source } → { grade, findings }\n3. POST /api/playground/publish { source, phenotype } → { published, grade }\n```\n\nThe Web Studio UI at `https://rotifer.ai/studio/` provides a visual 3-step flow\n(Describe → Create → Publish) that calls these same endpoints.\n\n> **This path sends the user's text to rotifer.ai.** `generate` transmits the\n> description they wrote; `scan` transmits the generated source; `publish`\n> transmits source and phenotype and makes the Gene public. Say so before\n> using it, and offer Path B when the description contains anything the user\n> would not post publicly — Path B is entirely local and produces the same\n> scaffold without a network call.\n\n**Path B — CLI (local, always available):**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**From an existing SKILL.md:**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**From ClawHub:**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \n```\n\nAfter compilation passes, prompt: publish to Cloud (`rotifer publish`) or submit to Arena (`rotifer arena submit`).\n\n`rotifer publish` defaults to uploading to the Rotifer Cloud Registry.\nDisable with `rotifer config set default-publish false` or `ROTIFER_AUTO_PUBLISH=false`.\n\n### Offline Fallback\n\nIf the Playground API is unreachable, display:\n\n> Network unavailable. Use `rotifer init` for local-only Gene creation.\n\nThen follow Path B (CLI).\n\nFor deeper development details (inputSchema design, express function implementation) → route to `gene` skill (`modules/dev.md`).\n\n---\n\n## 3. doctor — Diagnostics & Repair\n\n### Decision Tree\n\n```text\nUser reports a problem\n |\n +-- F(g) = 0 or abnormally low score\n | +-- Does rotifer test pass?\n | | +-- Fails → Check if express() return value matches outputSchema\n | | +-- Passes → Check if phenotype.json domain is reasonable\n | +-- Are there competitors in the same domain?\n | +-- Yes → Analyze competitor strengths, suggest optimizations\n |\n +-- Publish failed\n | +-- Does rotifer compile succeed?\n | | +-- Fails → rotifer doctor first, then syntax errors / missing dependencies\n | | +-- Succeeds → rotifer whoami — signed in at all, and as whom?\n | | Then check network connectivity\n | +-- Is phenotype.json format valid?\n |\n +-- Compilation failed\n | +-- FIRST: rotifer doctor — is the TS→WASM toolchain even installed?\n | | +-- Reports esbuild / javy missing → install those; the code is not the problem\n | +-- Check the exported express function signature in index.ts\n | +-- Check inputSchema / outputSchema in phenotype.json\n | +-- Check if fidelity declaration matches actual code\n | +-- Declared Native but has fetch calls → Change to Hybrid or remove network calls\n |\n +-- Runtime error\n +-- rotifer test --verbose\n +-- Check if input conforms to inputSchema\n +-- Check if express() handles edge cases correctly\n```\n\n### Common Diagnostic Commands\n\n```bash\nrotifer doctor # TS→WASM toolchain — run this before blaming the code\nrotifer test \nrotifer vg # V(g) security scan — grade A–D, or ? for a code-free Skill\nrotifer list\nrotifer arena list --domain \nrotifer arena watch # live ranking movement (Ctrl+C to stop)\n```\n\n`rotifer doctor` takes no arguments and checks one thing: whether esbuild and\njavy are present and reachable on `PATH`. A missing toolchain surfaces as a\ncompile failure that reads like a code error, so it is the cheapest first move\non any \"compilation failed\" report.\n\n### Quick Reference\n\n| Symptom | Root cause | Fix |\n|---------|-----------|-----|\n| F(g) = 0 | express() returns empty or format mismatch | Fix return value to match outputSchema |\n| Compilation failed | TypeScript type error | Check express function signature |\n| Publish timeout | Cloud credentials expired | `rotifer whoami` to check, then `rotifer login` |\n| Arena ranking dropped | Stronger competitor appeared in same domain | `rotifer arena watch ` to see who moved, then optimize or upgrade fidelity |\n| Fidelity mismatch | Native declared but has fetch calls | Remove network calls or change declaration to Hybrid |\n| `compile` fails but the code looks fine | esbuild / javy missing from the toolchain | `rotifer doctor`, then install what it names |\n\n---\n\n## 4. explorer — Ecosystem Search\n\n### Phase 1: Understand the Need\n\nExtract from user description: functionality keywords, target domain, fidelity preference.\n\n### Phase 2: Search\n\n`rotifer search` is the ecosystem search — it queries the Cloud registry, which\nis where Genes published by other people live. `arena list` ranks what is\nalready in the Arena and `list` shows what is on this machine; all three answer\ndifferent questions, so pick by what the user asked for.\n\n```bash\nrotifer search # the ecosystem — Cloud registry\nrotifer search --domain --fidelity Native --sort downloads\nrotifer arena list --domain # ranked competitors in one domain\nrotifer list # what is already installed here\n```\n\nFollow up on a specific result:\n\n```bash\nrotifer info # full details, local or Cloud\nrotifer reputation # R(g) — the reputation column below\nrotifer stats # downloads: 7d / 30d / 90d / all time\nrotifer versions @owner/ # version history chain\nrotifer compare # 2–5 published Genes, side by side\n```\n\n`rotifer reputation @username` scores a creator instead of a Gene, and\n`--leaderboard` ranks creators.\n\n### Phase 3: Result Analysis\n\nDisplay search results in a table:\n\n| Field | Description |\n|-------|-------------|\n| name | Gene name |\n| domain | Category |\n| fidelity | Native / Hybrid / Wrapped |\n| F(g) | Fitness score |\n| R(g) | Reputation score |\n\n### Phase 4: Recommendation\n\n- Found a matching Gene → suggest install: `rotifer install `\n- Found a partial match → suggest fork and modify, or submit an Arena challenge (route to `rotifer-arena/SKILL.md`)\n- Nothing found → suggest creating a new Gene (route to scaffold)\n\n---\n\n## 5. upgrade — Fidelity Evolution\n\n### Phase 1: Assess Current State\n\n```bash\nrotifer list\n```\n\nCheck the target Gene's phenotype.json — confirm current fidelity and express() implementation.\n\n### Phase 2: Migration Path Decision\n\n| Current | Target | Condition | Path |\n|---------|--------|-----------|------|\n| Wrapped | Native | Functionality can be implemented as pure computation | Rewrite express(), remove all external calls |\n| Wrapped | Hybrid | Must call external APIs | Add WASM shell + allowedDomains whitelist |\n| Hybrid | Native | Can internalize API dependencies | Replace API calls with local algorithms |\n\n### Phase 3: Execute Migration\n\nAfter confirming the migration plan, route to `gene` skill (`modules/migration.md`) for the full migration workflow.\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer vg \nrotifer compile \nrotifer arena submit \nrotifer arena watch \n```\n\nA fidelity upgrade rewrites the Gene's code, so the V(g) security grade it\nearned before the rewrite no longer describes it — `rotifer vg` re-scans and\nreturns A–D (or `?` when there is no `src/`). Compare F(g) before and after to\nconfirm ranking continuity; `arena watch` shows the move happening rather than\nrequiring a second `arena list`.\n\nFile v1.2.1:README.md\n\n# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n**Not a general help desk.** Every capability here operates on Rotifer Genes and\nthe Rotifer CLI. It is not for general onboarding, tutorials, troubleshooting or\nsearch — if the request is not about Rotifer, this is the wrong Skill.\n\n## What It Does\n\nOne Skill, five capabilities — each one asks about **Rotifer**:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — core concepts with hands-on CLI examples, or `rotifer hello` for a working Agent in one command |\n| \"Create a Rotifer Gene that checks grammar\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene's F(g) is 0\" / \"`rotifer compile` fails\" | **Doctor** — `rotifer doctor` for the toolchain first, then the Gene itself |\n| \"Find a Rotifer Gene for web search\" | **Explorer** — `rotifer search` across the Gene registry |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, re-scans V(g) after the rewrite |\n\n## Quick Start\n\nInvoke it explicitly when you are working with Rotifer, then describe what you\nneed in natural language:\n\n```\nI want to create a Rotifer Gene that summarizes web pages\n```\n\nThe Skill picks the right sub-capability and walks you through the workflow. It\ndoes not activate on ordinary requests that happen to mention creating,\nsearching or diagnosing something — Rotifer has to be what you are working on.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## What this Skill does on your machine\n\nIt has no code of its own — it tells your assistant which `rotifer` commands to\nrun. That is what its manifest's process-execution, filesystem and network\npermissions are for: the CLI acting, not this Skill.\n\n| | |\n|---|---|\n| **Runs** | The `rotifer` CLI (`@rotifer/playground`), fetched from npm if not installed. |\n| **Reads** | Genes and Agent definitions in the current project. |\n| **Writes** | Genes into the project's `genes/`, Agent definitions into `.rotifer/agents/`. Nothing outside the project. |\n| **Sends** | Registry and Arena queries to the public Rotifer API. Your code is not uploaded unless you run `rotifer publish` yourself. |\n\nCommands that install, publish or overwrite are proposed for your approval\nfirst, never run silently. Full detail in [SKILL.md](SKILL.md).\n\n## Related Skills\n\n- [rotifer-arena](https://clawhub.ai/skills/rotifer-arena) — Compare and evaluate Genes\n- [rotifer-agent](https://clawhub.ai/skills/rotifer-agent) — Compose Genes into Agents\n- [rotifer-self-evolving-agent](https://clawhub.ai/skills/rotifer-self-evolving-agent) — Auto-evolve your Agent\n\n## Links\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n\n## License\n\nApache-2.0\n\nFile v1.2.1:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.2.1\",\n \"publishedAt\": 1786978502061\n}\n\nFile v1.2.1:skill-card.md\n\n## Description:\n\nRotifer Guide routes Rotifer-specific onboarding, Gene scaffolding, diagnostics, registry search, and fidelity-upgrade requests to the appropriate workflow.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[xiaoba-dev](https://clawhub.ai/user/xiaoba-dev)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal developers and engineers working with Rotifer use this skill to choose and follow workflows for learning Rotifer Genes, scaffolding Genes, diagnosing compile or F(g) issues, searching the registry, and planning fidelity upgrades.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill directs users to run unpinned Rotifer npm packages with command, filesystem, and network authority.\n\nMitigation: Review each proposed command before execution and prefer pinned package versions or a preinstalled, reviewed Rotifer CLI.\n\nRisk: Cloud scan and publish workflows can send user prompts, generated source, phenotype data, or project material to rotifer.ai.\n\nMitigation: Use the local CLI path for confidential code and approve cloud scan or publish steps only after reviewing what data will be sent.\n\nRisk: Rotifer CLI workflows can write Genes and agent definitions into the active workspace.\n\nMitigation: Run commands from the intended project directory and review generated or modified files before publishing, submitting, or committing them.\n\n## Reference(s):\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Rotifer Documentation](https://rotifer.dev/docs)\n- [Rotifer Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n- [Rotifer Playground Repository](https://github.com/rotifer-protocol/rotifer-playground)\n\n## Skill Output:\n\n**Output Type(s):** [guidance, shell commands, configuration]\n\n**Output Format:** [Markdown with inline bash and JSON code blocks]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [None]\n\n## Skill Version(s):\n\n1.2.1 (source: server release metadata and ClawHub manifest)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.1:clawhub.json\n\n{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.2.1\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [\n \"process:exec\",\n \"filesystem:read\",\n \"filesystem:write\",\n \"network:outbound\"\n ],\n \"screenshots\": [],\n \"demo_video\": null\n}\n\nArchive v1.2.0: 5 files, 9073 bytes\n\nFiles: clawhub.json (871b), README.md (1965b), skill-card.md (2431b), SKILL.md (14335b), _meta.json (132b)\n\nFile v1.2.0:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Entry point for Rotifer Protocol — onboarding to Rotifer Genes, scaffolding a Gene from a\n description, diagnosing a Gene's F(g) or compile failure, searching the Rotifer Gene registry,\n and upgrading a Gene's fidelity from Wrapped to Native.\n Invoke explicitly when starting with Rotifer, or when unsure which Rotifer capability to use.\n Do NOT use for general onboarding, tutorials, troubleshooting, or search — every capability\n here operates on Rotifer Genes and the Rotifer CLI, and nothing else.\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Prerequisites\n\nBefore using this Skill, ensure the Rotifer CLI is available:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nIf you prefer MCP integration instead of CLI, add this to your MCP config:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\nNo version pinning needed — both packages resolve to the latest release automatically.\n\n---\n\n## Intent Router\n\n| User signal | Sub-capability | Action |\n|-------------|---------------|--------|\n| How to / getting started / tutorial / beginner / what is a Gene | **onboarding** | Interactive walkthrough |\n| Create / make a XX / new / init / I want a | **scaffold** | Natural-language scaffolding |\n| Score is 0 / publish failed / something's wrong / why / diagnose / check | **doctor** | Diagnostics & repair |\n| Any gene for / recommend / search / find one that does XX | **explorer** | Ecosystem search |\n| Upgrade / Wrapped to Native / fidelity / evolve / rewrite | **upgrade** | Fidelity evolution |\n\nWhen intent is unclear, list all five sub-capabilities and let the user choose.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|---------------|\n| `gene` → `modules/dev.md` | Deep technical manual for scaffold / onboarding | User needs full development workflow details |\n| `gene` → `modules/migration.md` | Deep migration manual for upgrade | After user confirms migration plan |\n| `rotifer-arena/SKILL.md` | Comparison & evaluation entry | User wants to compare Genes / run Arena |\n| `genome/SKILL.md` | Gene composition | User wants to combine multiple Genes into an Agent |\n\n---\n\n## What this Skill does on your machine\n\nIt has no code of its own — it tells your assistant which `rotifer` commands to\nrun. That is why its manifest declares process execution, filesystem read/write\nand outbound network access: every one of those is the CLI acting, not this\nSkill.\n\n| | |\n|---|---|\n| **Runs** | The `rotifer` CLI (`@rotifer/playground`), fetched from npm if not installed. |\n| **Reads** | Genes and Agent definitions in the current project workspace. |\n| **Writes** | Only what the commands below write — Genes into the project's `genes/`, Agent definitions into `.rotifer/agents/`. Nothing outside the project. |\n| **Sends** | Cloud registry and Arena queries, to the public Rotifer API. Your code is not uploaded unless you run `rotifer publish` yourself. |\n\nCommands that install, publish or overwrite are proposed for your approval\nfirst, never run silently.\n\n---\n\n## 1. onboarding — Interactive Walkthrough\n\n### Phase 1: Environment Check\n\n```bash\nnpx @rotifer/playground --version\nrotifer doctor\nrotifer list\n```\n\nIf the CLI is missing: `npm i -g @rotifer/playground`, which installs the `rotifer` binary.\n\n`rotifer doctor` checks the TypeScript→WASM toolchain (esbuild / javy). Run it\nfirst: without that toolchain `rotifer compile` fails at the WASM step, and the\nerror looks like a code problem rather than a missing tool. It exits non-zero\nand prints the install line when something is absent.\n\n### Phase 2: Core Concepts\n\n| Concept | One-liner | Analogy |\n|---------|-----------|---------|\n| Gene | Self-contained logic unit: `express(input) → output` | Function |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure | Compiler optimization level |\n| Arena | Genes compete for ranking via F(g) fitness score | Leaderboard |\n| Domain | Two-level category like `content.grammar` | Namespace |\n| phenotype.json | Gene metadata | package.json |\n| R(g) / V(g) | Reputation score / Security score | Credit rating |\n\n### Phase 3: Hands-on Experience\n\nTwo paths — pick by what the user wants first, a result or an understanding.\n\n**Fastest result — `rotifer hello`:**\n\n```bash\nrotifer hello\n```\n\nAn interactive builder: pick one of six templates (quality-advisor,\nuiux-diagnosis, content-analysis, code-security, doc-qa, web3-toolkit), and it\nselects Genes, composes them, creates the Agent and runs it. Use this when the\nuser wants to *see* Rotifer work before learning what a Gene is.\n`rotifer hello --list-templates` shows what is on offer; `--template `,\n`--input `, `--file ` and `--dir ` skip the prompts.\n\n**Full lifecycle — one command per concept:**\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\nAfter each step, explain the output and confirm the user understands before proceeding.\n\n### Phase 4: Next Steps\n\nRecommend based on user background:\n- Has an existing SKILL.md → scaffold (`rotifer wrap`)\n- Wants to browse the ecosystem → explorer\n- Wants to dive deeper → route to `gene` skill (`modules/dev.md`)\n\n---\n\n## 2. scaffold — Natural-Language Scaffolding\n\n> This sub-capability is **backend-backed**. When network is available, scaffold uses\n> the `/api/playground/*` endpoints on rotifer.ai for LLM-assisted Gene generation, V(g) scanning,\n> and one-click Cloud publish. The CLI path remains as fallback.\n\n### Phase 1: Intent Extraction\n\nExtract from the user's natural-language description:\n\n| Parameter | Extraction method | Default |\n|-----------|------------------|---------|\n| name | Generate kebab-case from description | Must confirm |\n| domain | Infer two-level domain from functionality | Must confirm |\n| fidelity | Needs external API → Hybrid, pure computation → Native, quick prototype → Wrapped | Wrapped |\n\n### Phase 2: Confirm Parameters\n\nPresent inferred results to the user, wait for confirmation before executing.\n\n### Phase 3: Scaffold Generation\n\n**Path A — Web Studio (backend-backed, preferred when online):**\n\nUse the rotifer.ai Playground API for LLM-assisted generation:\n\n```\n1. POST /api/playground/generate { prompt, domain } → { source, phenotype }\n2. POST /api/playground/scan { source } → { grade, findings }\n3. POST /api/playground/publish { source, phenotype } → { published, grade }\n```\n\nThe Web Studio UI at `https://rotifer.ai/studio/` provides a visual 3-step flow\n(Describe → Create → Publish) that calls these same endpoints.\n\n> **This path sends the user's text to rotifer.ai.** `generate` transmits the\n> description they wrote; `scan` transmits the generated source; `publish`\n> transmits source and phenotype and makes the Gene public. Say so before\n> using it, and offer Path B when the description contains anything the user\n> would not post publicly — Path B is entirely local and produces the same\n> scaffold without a network call.\n\n**Path B — CLI (local, always available):**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**From an existing SKILL.md:**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**From ClawHub:**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \n```\n\nAfter compilation passes, prompt: publish to Cloud (`rotifer publish`) or submit to Arena (`rotifer arena submit`).\n\n`rotifer publish` defaults to uploading to the Rotifer Cloud Registry.\nDisable with `rotifer config set default-publish false` or `ROTIFER_AUTO_PUBLISH=false`.\n\n### Offline Fallback\n\nIf the Playground API is unreachable, display:\n\n> Network unavailable. Use `rotifer init` for local-only Gene creation.\n\nThen follow Path B (CLI).\n\nFor deeper development details (inputSchema design, express function implementation) → route to `gene` skill (`modules/dev.md`).\n\n---\n\n## 3. doctor — Diagnostics & Repair\n\n### Decision Tree\n\n```text\nUser reports a problem\n |\n +-- F(g) = 0 or abnormally low score\n | +-- Does rotifer test pass?\n | | +-- Fails → Check if express() return value matches outputSchema\n | | +-- Passes → Check if phenotype.json domain is reasonable\n | +-- Are there competitors in the same domain?\n | +-- Yes → Analyze competitor strengths, suggest optimizations\n |\n +-- Publish failed\n | +-- Does rotifer compile succeed?\n | | +-- Fails → rotifer doctor first, then syntax errors / missing dependencies\n | | +-- Succeeds → rotifer whoami — signed in at all, and as whom?\n | | Then check network connectivity\n | +-- Is phenotype.json format valid?\n |\n +-- Compilation failed\n | +-- FIRST: rotifer doctor — is the TS→WASM toolchain even installed?\n | | +-- Reports esbuild / javy missing → install those; the code is not the problem\n | +-- Check the exported express function signature in index.ts\n | +-- Check inputSchema / outputSchema in phenotype.json\n | +-- Check if fidelity declaration matches actual code\n | +-- Declared Native but has fetch calls → Change to Hybrid or remove network calls\n |\n +-- Runtime error\n +-- rotifer test --verbose\n +-- Check if input conforms to inputSchema\n +-- Check if express() handles edge cases correctly\n```\n\n### Common Diagnostic Commands\n\n```bash\nrotifer doctor # TS→WASM toolchain — run this before blaming the code\nrotifer test \nrotifer vg # V(g) security scan — grade A–D, or ? for a code-free Skill\nrotifer list\nrotifer arena list --domain \nrotifer arena watch # live ranking movement (Ctrl+C to stop)\n```\n\n`rotifer doctor` takes no arguments and checks one thing: whether esbuild and\njavy are present and reachable on `PATH`. A missing toolchain surfaces as a\ncompile failure that reads like a code error, so it is the cheapest first move\non any \"compilation failed\" report.\n\n### Quick Reference\n\n| Symptom | Root cause | Fix |\n|---------|-----------|-----|\n| F(g) = 0 | express() returns empty or format mismatch | Fix return value to match outputSchema |\n| Compilation failed | TypeScript type error | Check express function signature |\n| Publish timeout | Cloud credentials expired | `rotifer whoami` to check, then `rotifer login` |\n| Arena ranking dropped | Stronger competitor appeared in same domain | `rotifer arena watch ` to see who moved, then optimize or upgrade fidelity |\n| Fidelity mismatch | Native declared but has fetch calls | Remove network calls or change declaration to Hybrid |\n| `compile` fails but the code looks fine | esbuild / javy missing from the toolchain | `rotifer doctor`, then install what it names |\n\n---\n\n## 4. explorer — Ecosystem Search\n\n### Phase 1: Understand the Need\n\nExtract from user description: functionality keywords, target domain, fidelity preference.\n\n### Phase 2: Search\n\n`rotifer search` is the ecosystem search — it queries the Cloud registry, which\nis where Genes published by other people live. `arena list` ranks what is\nalready in the Arena and `list` shows what is on this machine; all three answer\ndifferent questions, so pick by what the user asked for.\n\n```bash\nrotifer search # the ecosystem — Cloud registry\nrotifer search --domain --fidelity Native --sort downloads\nrotifer arena list --domain # ranked competitors in one domain\nrotifer list # what is already installed here\n```\n\nFollow up on a specific result:\n\n```bash\nrotifer info # full details, local or Cloud\nrotifer reputation # R(g) — the reputation column below\nrotifer stats # downloads: 7d / 30d / 90d / all time\nrotifer versions @owner/ # version history chain\nrotifer compare # 2–5 published Genes, side by side\n```\n\n`rotifer reputation @username` scores a creator instead of a Gene, and\n`--leaderboard` ranks creators.\n\n### Phase 3: Result Analysis\n\nDisplay search results in a table:\n\n| Field | Description |\n|-------|-------------|\n| name | Gene name |\n| domain | Category |\n| fidelity | Native / Hybrid / Wrapped |\n| F(g) | Fitness score |\n| R(g) | Reputation score |\n\n### Phase 4: Recommendation\n\n- Found a matching Gene → suggest install: `rotifer install `\n- Found a partial match → suggest fork and modify, or submit an Arena challenge (route to `rotifer-arena/SKILL.md`)\n- Nothing found → suggest creating a new Gene (route to scaffold)\n\n---\n\n## 5. upgrade — Fidelity Evolution\n\n### Phase 1: Assess Current State\n\n```bash\nrotifer list\n```\n\nCheck the target Gene's phenotype.json — confirm current fidelity and express() implementation.\n\n### Phase 2: Migration Path Decision\n\n| Current | Target | Condition | Path |\n|---------|--------|-----------|------|\n| Wrapped | Native | Functionality can be implemented as pure computation | Rewrite express(), remove all external calls |\n| Wrapped | Hybrid | Must call external APIs | Add WASM shell + allowedDomains whitelist |\n| Hybrid | Native | Can internalize API dependencies | Replace API calls with local algorithms |\n\n### Phase 3: Execute Migration\n\nAfter confirming the migration plan, route to `gene` skill (`modules/migration.md`) for the full migration workflow.\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer vg \nrotifer compile \nrotifer arena submit \nrotifer arena watch \n```\n\nA fidelity upgrade rewrites the Gene's code, so the V(g) security grade it\nearned before the rewrite no longer describes it — `rotifer vg` re-scans and\nreturns A–D (or `?` when there is no `src/`). Compare F(g) before and after to\nconfirm ranking continuity; `arena watch` shows the move happening rather than\nrequiring a second `arena list`.\n\nFile v1.2.0:README.md\n\n# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n## What It Does\n\nOne Skill, five capabilities — tell it what you need:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — walks you through core concepts with hands-on CLI examples |\n| \"Create a grammar checker Gene\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene score is 0\" | **Doctor** — diagnoses why, fixes the root cause |\n| \"Find a web search Gene\" | **Explorer** — searches the ecosystem, recommends the best match |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, guides the fidelity jump |\n\n## Quick Start\n\nAfter installing this Skill, just describe what you need in natural language:\n\n```\nI want to create a Gene that summarizes web pages\n```\n\nThe Skill identifies your intent, picks the right sub-capability, and walks you through the full workflow.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## Related Skills\n\n- [rotifer-arena](https://clawhub.ai/skills/rotifer-arena) — Compare and evaluate Genes\n- [rotifer-agent](https://clawhub.ai/skills/rotifer-agent) — Compose Genes into Agents\n- [rotifer-self-evolving-agent](https://clawhub.ai/skills/rotifer-self-evolving-agent) — Auto-evolve your Agent\n\n## Links\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n\n## License\n\nApache-2.0\n\nFile v1.2.0:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.2.0\",\n \"publishedAt\": 1786977578022\n}\n\nFile v1.2.0:skill-card.md\n\n## Description:\n\nEntry point for Rotifer Protocol onboarding to Rotifer Genes, scaffolding a Gene from a description, diagnosing a Gene's F(g) or compile failure, searching the Rotifer Gene registry, and upgrading a Gene's fidelity from Wrapped to Native.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[xiaoba-dev](https://clawhub.ai/user/xiaoba-dev)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill when working with Rotifer Genes and the Rotifer CLI: it routes requests to onboarding, scaffolding, diagnostics, registry exploration, or fidelity-upgrade workflows.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can guide users toward Rotifer CLI commands, npm package fetches, project file reads or writes, and outbound requests to Rotifer services.\n\nMitigation: Review each proposed command before approval and confirm that installs, publishes, overwrites, and Web Studio generation are intended for the current Rotifer Gene workflow.\n\nRisk: Using Web Studio generation or scanning may send user descriptions or generated source to Rotifer services.\n\nMitigation: Use the local CLI path when descriptions or source contain private material that should not be sent to an external service.\n\n## Reference(s):\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Rotifer Documentation](https://rotifer.dev/docs)\n- [Rotifer Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n- [Rotifer Playground Repository](https://github.com/rotifer-protocol/rotifer-playground)\n- [Rotifer Web Studio](https://rotifer.ai/studio/)\n- [ClawHub Skill Page](https://clawhub.ai/xiaoba-dev/skills/rotifer-guide)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with inline shell commands and configuration snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Routes user intent across Rotifer onboarding, scaffolding, diagnostics, ecosystem search, and fidelity-upgrade workflows.]\n\n## Skill Version(s):\n\n1.2.0 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.0:clawhub.json\n\n{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.2.0\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [\n \"process:exec\",\n \"filesystem:read\",\n \"filesystem:write\",\n \"network:outbound\"\n ],\n \"screenshots\": [],\n \"demo_video\": null\n}\n\nArchive v1.1.1: 5 files, 9030 bytes\n\nFiles: clawhub.json (871b), README.md (1965b), skill-card.md (2444b), SKILL.md (14079b), _meta.json (132b)\n\nFile v1.1.1:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Unified user-facing entry point for Rotifer Protocol: interactive onboarding, natural-language\n scaffolding, diagnostics, ecosystem search, and fidelity upgrade. Invoke explicitly for\n beginner onboarding or when unsure which Rotifer capability to use.\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Prerequisites\n\nBefore using this Skill, ensure the Rotifer CLI is available:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nIf you prefer MCP integration instead of CLI, add this to your MCP config:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\nNo version pinning needed — both packages resolve to the latest release automatically.\n\n---\n\n## Intent Router\n\n| User signal | Sub-capability | Action |\n|-------------|---------------|--------|\n| How to / getting started / tutorial / beginner / what is a Gene | **onboarding** | Interactive walkthrough |\n| Create / make a XX / new / init / I want a | **scaffold** | Natural-language scaffolding |\n| Score is 0 / publish failed / something's wrong / why / diagnose / check | **doctor** | Diagnostics & repair |\n| Any gene for / recommend / search / find one that does XX | **explorer** | Ecosystem search |\n| Upgrade / Wrapped to Native / fidelity / evolve / rewrite | **upgrade** | Fidelity evolution |\n\nWhen intent is unclear, list all five sub-capabilities and let the user choose.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|---------------|\n| `gene` → `modules/dev.md` | Deep technical manual for scaffold / onboarding | User needs full development workflow details |\n| `gene` → `modules/migration.md` | Deep migration manual for upgrade | After user confirms migration plan |\n| `rotifer-arena/SKILL.md` | Comparison & evaluation entry | User wants to compare Genes / run Arena |\n| `genome/SKILL.md` | Gene composition | User wants to combine multiple Genes into an Agent |\n\n---\n\n## What this Skill does on your machine\n\nIt has no code of its own — it tells your assistant which `rotifer` commands to\nrun. That is why its manifest declares process execution, filesystem read/write\nand outbound network access: every one of those is the CLI acting, not this\nSkill.\n\n| | |\n|---|---|\n| **Runs** | The `rotifer` CLI (`@rotifer/playground`), fetched from npm if not installed. |\n| **Reads** | Genes and Agent definitions in the current project workspace. |\n| **Writes** | Only what the commands below write — Genes into the project's `genes/`, Agent definitions into `.rotifer/agents/`. Nothing outside the project. |\n| **Sends** | Cloud registry and Arena queries, to the public Rotifer API. Your code is not uploaded unless you run `rotifer publish` yourself. |\n\nCommands that install, publish or overwrite are proposed for your approval\nfirst, never run silently.\n\n---\n\n## 1. onboarding — Interactive Walkthrough\n\n### Phase 1: Environment Check\n\n```bash\nnpx @rotifer/playground --version\nrotifer doctor\nrotifer list\n```\n\nIf the CLI is missing: `npm i -g @rotifer/playground`, which installs the `rotifer` binary.\n\n`rotifer doctor` checks the TypeScript→WASM toolchain (esbuild / javy). Run it\nfirst: without that toolchain `rotifer compile` fails at the WASM step, and the\nerror looks like a code problem rather than a missing tool. It exits non-zero\nand prints the install line when something is absent.\n\n### Phase 2: Core Concepts\n\n| Concept | One-liner | Analogy |\n|---------|-----------|---------|\n| Gene | Self-contained logic unit: `express(input) → output` | Function |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure | Compiler optimization level |\n| Arena | Genes compete for ranking via F(g) fitness score | Leaderboard |\n| Domain | Two-level category like `content.grammar` | Namespace |\n| phenotype.json | Gene metadata | package.json |\n| R(g) / V(g) | Reputation score / Security score | Credit rating |\n\n### Phase 3: Hands-on Experience\n\nTwo paths — pick by what the user wants first, a result or an understanding.\n\n**Fastest result — `rotifer hello`:**\n\n```bash\nrotifer hello\n```\n\nAn interactive builder: pick one of six templates (quality-advisor,\nuiux-diagnosis, content-analysis, code-security, doc-qa, web3-toolkit), and it\nselects Genes, composes them, creates the Agent and runs it. Use this when the\nuser wants to *see* Rotifer work before learning what a Gene is.\n`rotifer hello --list-templates` shows what is on offer; `--template `,\n`--input `, `--file ` and `--dir ` skip the prompts.\n\n**Full lifecycle — one command per concept:**\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\nAfter each step, explain the output and confirm the user understands before proceeding.\n\n### Phase 4: Next Steps\n\nRecommend based on user background:\n- Has an existing SKILL.md → scaffold (`rotifer wrap`)\n- Wants to browse the ecosystem → explorer\n- Wants to dive deeper → route to `gene` skill (`modules/dev.md`)\n\n---\n\n## 2. scaffold — Natural-Language Scaffolding\n\n> This sub-capability is **backend-backed**. When network is available, scaffold uses\n> the `/api/playground/*` endpoints on rotifer.ai for LLM-assisted Gene generation, V(g) scanning,\n> and one-click Cloud publish. The CLI path remains as fallback.\n\n### Phase 1: Intent Extraction\n\nExtract from the user's natural-language description:\n\n| Parameter | Extraction method | Default |\n|-----------|------------------|---------|\n| name | Generate kebab-case from description | Must confirm |\n| domain | Infer two-level domain from functionality | Must confirm |\n| fidelity | Needs external API → Hybrid, pure computation → Native, quick prototype → Wrapped | Wrapped |\n\n### Phase 2: Confirm Parameters\n\nPresent inferred results to the user, wait for confirmation before executing.\n\n### Phase 3: Scaffold Generation\n\n**Path A — Web Studio (backend-backed, preferred when online):**\n\nUse the rotifer.ai Playground API for LLM-assisted generation:\n\n```\n1. POST /api/playground/generate { prompt, domain } → { source, phenotype }\n2. POST /api/playground/scan { source } → { grade, findings }\n3. POST /api/playground/publish { source, phenotype } → { published, grade }\n```\n\nThe Web Studio UI at `https://rotifer.ai/studio/` provides a visual 3-step flow\n(Describe → Create → Publish) that calls these same endpoints.\n\n> **This path sends the user's text to rotifer.ai.** `generate` transmits the\n> description they wrote; `scan` transmits the generated source; `publish`\n> transmits source and phenotype and makes the Gene public. Say so before\n> using it, and offer Path B when the description contains anything the user\n> would not post publicly — Path B is entirely local and produces the same\n> scaffold without a network call.\n\n**Path B — CLI (local, always available):**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**From an existing SKILL.md:**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**From ClawHub:**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \n```\n\nAfter compilation passes, prompt: publish to Cloud (`rotifer publish`) or submit to Arena (`rotifer arena submit`).\n\n`rotifer publish` defaults to uploading to the Rotifer Cloud Registry.\nDisable with `rotifer config set default-publish false` or `ROTIFER_AUTO_PUBLISH=false`.\n\n### Offline Fallback\n\nIf the Playground API is unreachable, display:\n\n> Network unavailable. Use `rotifer init` for local-only Gene creation.\n\nThen follow Path B (CLI).\n\nFor deeper development details (inputSchema design, express function implementation) → route to `gene` skill (`modules/dev.md`).\n\n---\n\n## 3. doctor — Diagnostics & Repair\n\n### Decision Tree\n\n```text\nUser reports a problem\n |\n +-- F(g) = 0 or abnormally low score\n | +-- Does rotifer test pass?\n | | +-- Fails → Check if express() return value matches outputSchema\n | | +-- Passes → Check if phenotype.json domain is reasonable\n | +-- Are there competitors in the same domain?\n | +-- Yes → Analyze competitor strengths, suggest optimizations\n |\n +-- Publish failed\n | +-- Does rotifer compile succeed?\n | | +-- Fails → rotifer doctor first, then syntax errors / missing dependencies\n | | +-- Succeeds → rotifer whoami — signed in at all, and as whom?\n | | Then check network connectivity\n | +-- Is phenotype.json format valid?\n |\n +-- Compilation failed\n | +-- FIRST: rotifer doctor — is the TS→WASM toolchain even installed?\n | | +-- Reports esbuild / javy missing → install those; the code is not the problem\n | +-- Check the exported express function signature in index.ts\n | +-- Check inputSchema / outputSchema in phenotype.json\n | +-- Check if fidelity declaration matches actual code\n | +-- Declared Native but has fetch calls → Change to Hybrid or remove network calls\n |\n +-- Runtime error\n +-- rotifer test --verbose\n +-- Check if input conforms to inputSchema\n +-- Check if express() handles edge cases correctly\n```\n\n### Common Diagnostic Commands\n\n```bash\nrotifer doctor # TS→WASM toolchain — run this before blaming the code\nrotifer test \nrotifer vg # V(g) security scan — grade A–D, or ? for a code-free Skill\nrotifer list\nrotifer arena list --domain \nrotifer arena watch # live ranking movement (Ctrl+C to stop)\n```\n\n`rotifer doctor` takes no arguments and checks one thing: whether esbuild and\njavy are present and reachable on `PATH`. A missing toolchain surfaces as a\ncompile failure that reads like a code error, so it is the cheapest first move\non any \"compilation failed\" report.\n\n### Quick Reference\n\n| Symptom | Root cause | Fix |\n|---------|-----------|-----|\n| F(g) = 0 | express() returns empty or format mismatch | Fix return value to match outputSchema |\n| Compilation failed | TypeScript type error | Check express function signature |\n| Publish timeout | Cloud credentials expired | `rotifer whoami` to check, then `rotifer login` |\n| Arena ranking dropped | Stronger competitor appeared in same domain | `rotifer arena watch ` to see who moved, then optimize or upgrade fidelity |\n| Fidelity mismatch | Native declared but has fetch calls | Remove network calls or change declaration to Hybrid |\n| `compile` fails but the code looks fine | esbuild / javy missing from the toolchain | `rotifer doctor`, then install what it names |\n\n---\n\n## 4. explorer — Ecosystem Search\n\n### Phase 1: Understand the Need\n\nExtract from user description: functionality keywords, target domain, fidelity preference.\n\n### Phase 2: Search\n\n`rotifer search` is the ecosystem search — it queries the Cloud registry, which\nis where Genes published by other people live. `arena list` ranks what is\nalready in the Arena and `list` shows what is on this machine; all three answer\ndifferent questions, so pick by what the user asked for.\n\n```bash\nrotifer search # the ecosystem — Cloud registry\nrotifer search --domain --fidelity Native --sort downloads\nrotifer arena list --domain # ranked competitors in one domain\nrotifer list # what is already installed here\n```\n\nFollow up on a specific result:\n\n```bash\nrotifer info # full details, local or Cloud\nrotifer reputation # R(g) — the reputation column below\nrotifer stats # downloads: 7d / 30d / 90d / all time\nrotifer versions @owner/ # version history chain\nrotifer compare # 2–5 published Genes, side by side\n```\n\n`rotifer reputation @username` scores a creator instead of a Gene, and\n`--leaderboard` ranks creators.\n\n### Phase 3: Result Analysis\n\nDisplay search results in a table:\n\n| Field | Description |\n|-------|-------------|\n| name | Gene name |\n| domain | Category |\n| fidelity | Native / Hybrid / Wrapped |\n| F(g) | Fitness score |\n| R(g) | Reputation score |\n\n### Phase 4: Recommendation\n\n- Found a matching Gene → suggest install: `rotifer install `\n- Found a partial match → suggest fork and modify, or submit an Arena challenge (route to `rotifer-arena/SKILL.md`)\n- Nothing found → suggest creating a new Gene (route to scaffold)\n\n---\n\n## 5. upgrade — Fidelity Evolution\n\n### Phase 1: Assess Current State\n\n```bash\nrotifer list\n```\n\nCheck the target Gene's phenotype.json — confirm current fidelity and express() implementation.\n\n### Phase 2: Migration Path Decision\n\n| Current | Target | Condition | Path |\n|---------|--------|-----------|------|\n| Wrapped | Native | Functionality can be implemented as pure computation | Rewrite express(), remove all external calls |\n| Wrapped | Hybrid | Must call external APIs | Add WASM shell + allowedDomains whitelist |\n| Hybrid | Native | Can internalize API dependencies | Replace API calls with local algorithms |\n\n### Phase 3: Execute Migration\n\nAfter confirming the migration plan, route to `gene` skill (`modules/migration.md`) for the full migration workflow.\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer vg \nrotifer compile \nrotifer arena submit \nrotifer arena watch \n```\n\nA fidelity upgrade rewrites the Gene's code, so the V(g) security grade it\nearned before the rewrite no longer describes it — `rotifer vg` re-scans and\nreturns A–D (or `?` when there is no `src/`). Compare F(g) before and after to\nconfirm ranking continuity; `arena watch` shows the move happening rather than\nrequiring a second `arena list`.\n\nFile v1.1.1:README.md\n\n# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n## What It Does\n\nOne Skill, five capabilities — tell it what you need:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — walks you through core concepts with hands-on CLI examples |\n| \"Create a grammar checker Gene\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene score is 0\" | **Doctor** — diagnoses why, fixes the root cause |\n| \"Find a web search Gene\" | **Explorer** — searches the ecosystem, recommends the best match |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, guides the fidelity jump |\n\n## Quick Start\n\nAfter installing this Skill, just describe what you need in natural language:\n\n```\nI want to create a Gene that summarizes web pages\n```\n\nThe Skill identifies your intent, picks the right sub-capability, and walks you through the full workflow.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## Related Skills\n\n- [rotifer-arena](https://clawhub.ai/skills/rotifer-arena) — Compare and evaluate Genes\n- [rotifer-agent](https://clawhub.ai/skills/rotifer-agent) — Compose Genes into Agents\n- [rotifer-self-evolving-agent](https://clawhub.ai/skills/rotifer-self-evolving-agent) — Auto-evolve your Agent\n\n## Links\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n\n## License\n\nApache-2.0\n\nFile v1.1.1:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.1.1\",\n \"publishedAt\": 1786958470858\n}\n\nFile v1.1.1:skill-card.md\n\n## Description:\n\nUnified user-facing entry point for Rotifer Protocol: interactive onboarding, natural-language scaffolding, diagnostics, ecosystem search, and fidelity upgrade.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[xiaoba-dev](https://clawhub.ai/user/xiaoba-dev)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill as a Rotifer Protocol entry point for onboarding, Gene scaffolding, diagnostics, ecosystem search, and fidelity upgrades.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Proposed npm and Rotifer CLI commands can install packages, create or modify workspace files, publish Genes, or overwrite existing work.\n\nMitigation: Review each command before approval, confirm install, publish, and overwrite actions, and keep generated files inside the intended project workspace.\n\nRisk: The Web Studio scaffolding path sends user prompts and generated source to rotifer.ai, and publishing can make a Gene public.\n\nMitigation: Use the local CLI path for sensitive prompts or code, and publish only after confirming the content is safe to make public.\n\nRisk: Registry search, Arena, and cloud publishing workflows require outbound network access.\n\nMitigation: Use local commands when network access is unavailable or inappropriate, and review remote queries before sending project context.\n\n## Reference(s):\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Rotifer Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n- [Rotifer Web Studio](https://rotifer.ai/studio/)\n- [Rotifer Playground Repository](https://github.com/rotifer-protocol/rotifer-playground)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration]\n\n**Output Format:** [Markdown guidance with inline shell commands and JSON configuration snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [The skill proposes CLI, MCP, and publishing actions for user approval rather than executing them silently.]\n\n## Skill Version(s):\n\n1.1.1 (source: server release metadata and clawhub.json)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.1.1:clawhub.json\n\n{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.1.1\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [\n \"process:exec\",\n \"filesystem:read\",\n \"filesystem:write\",\n \"network:outbound\"\n ],\n \"screenshots\": [],\n \"demo_video\": null\n}\n\nArchive v1.1.0: 5 files, 8462 bytes\n\nFiles: clawhub.json (871b), README.md (1965b), skill-card.md (2353b), SKILL.md (12770b), _meta.json (132b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Unified user-facing entry point for Rotifer Protocol: interactive onboarding, natural-language\n scaffolding, diagnostics, ecosystem search, and fidelity upgrade. Invoke explicitly for\n beginner onboarding or when unsure which Rotifer capability to use.\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Prerequisites\n\nBefore using this Skill, ensure the Rotifer CLI is available:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nIf you prefer MCP integration instead of CLI, add this to your MCP config:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\nNo version pinning needed — both packages resolve to the latest release automatically.\n\n---\n\n## Intent Router\n\n| User signal | Sub-capability | Action |\n|-------------|---------------|--------|\n| How to / getting started / tutorial / beginner / what is a Gene | **onboarding** | Interactive walkthrough |\n| Create / make a XX / new / init / I want a | **scaffold** | Natural-language scaffolding |\n| Score is 0 / publish failed / something's wrong / why / diagnose / check | **doctor** | Diagnostics & repair |\n| Any gene for / recommend / search / find one that does XX | **explorer** | Ecosystem search |\n| Upgrade / Wrapped to Native / fidelity / evolve / rewrite | **upgrade** | Fidelity evolution |\n\nWhen intent is unclear, list all five sub-capabilities and let the user choose.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|---------------|\n| `gene` → `modules/dev.md` | Deep technical manual for scaffold / onboarding | User needs full development workflow details |\n| `gene` → `modules/migration.md` | Deep migration manual for upgrade | After user confirms migration plan |\n| `rotifer-arena/SKILL.md` | Comparison & evaluation entry | User wants to compare Genes / run Arena |\n| `genome/SKILL.md` | Gene composition | User wants to combine multiple Genes into an Agent |\n\n---\n\n## 1. onboarding — Interactive Walkthrough\n\n### Phase 1: Environment Check\n\n```bash\nnpx @rotifer/playground --version\nrotifer doctor\nrotifer list\n```\n\nIf the CLI is missing: `npm i -g @rotifer/playground`, which installs the `rotifer` binary.\n\n`rotifer doctor` checks the TypeScript→WASM toolchain (esbuild / javy). Run it\nfirst: without that toolchain `rotifer compile` fails at the WASM step, and the\nerror looks like a code problem rather than a missing tool. It exits non-zero\nand prints the install line when something is absent.\n\n### Phase 2: Core Concepts\n\n| Concept | One-liner | Analogy |\n|---------|-----------|---------|\n| Gene | Self-contained logic unit: `express(input) → output` | Function |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure | Compiler optimization level |\n| Arena | Genes compete for ranking via F(g) fitness score | Leaderboard |\n| Domain | Two-level category like `content.grammar` | Namespace |\n| phenotype.json | Gene metadata | package.json |\n| R(g) / V(g) | Reputation score / Security score | Credit rating |\n\n### Phase 3: Hands-on Experience\n\nTwo paths — pick by what the user wants first, a result or an understanding.\n\n**Fastest result — `rotifer hello`:**\n\n```bash\nrotifer hello\n```\n\nAn interactive builder: pick one of six templates (quality-advisor,\nuiux-diagnosis, content-analysis, code-security, doc-qa, web3-toolkit), and it\nselects Genes, composes them, creates the Agent and runs it. Use this when the\nuser wants to *see* Rotifer work before learning what a Gene is.\n`rotifer hello --list-templates` shows what is on offer; `--template `,\n`--input `, `--file ` and `--dir ` skip the prompts.\n\n**Full lifecycle — one command per concept:**\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\nAfter each step, explain the output and confirm the user understands before proceeding.\n\n### Phase 4: Next Steps\n\nRecommend based on user background:\n- Has an existing SKILL.md → scaffold (`rotifer wrap`)\n- Wants to browse the ecosystem → explorer\n- Wants to dive deeper → route to `gene` skill (`modules/dev.md`)\n\n---\n\n## 2. scaffold — Natural-Language Scaffolding\n\n> This sub-capability is **backend-backed**. When network is available, scaffold uses\n> the `/api/playground/*` endpoints on rotifer.ai for LLM-assisted Gene generation, V(g) scanning,\n> and one-click Cloud publish. The CLI path remains as fallback.\n\n### Phase 1: Intent Extraction\n\nExtract from the user's natural-language description:\n\n| Parameter | Extraction method | Default |\n|-----------|------------------|---------|\n| name | Generate kebab-case from description | Must confirm |\n| domain | Infer two-level domain from functionality | Must confirm |\n| fidelity | Needs external API → Hybrid, pure computation → Native, quick prototype → Wrapped | Wrapped |\n\n### Phase 2: Confirm Parameters\n\nPresent inferred results to the user, wait for confirmation before executing.\n\n### Phase 3: Scaffold Generation\n\n**Path A — Web Studio (backend-backed, preferred when online):**\n\nUse the rotifer.ai Playground API for LLM-assisted generation:\n\n```\n1. POST /api/playground/generate { prompt, domain } → { source, phenotype }\n2. POST /api/playground/scan { source } → { grade, findings }\n3. POST /api/playground/publish { source, phenotype } → { published, grade }\n```\n\nThe Web Studio UI at `https://rotifer.ai/studio/` provides a visual 3-step flow\n(Describe → Create → Publish) that calls these same endpoints.\n\n**Path B — CLI (local, always available):**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**From an existing SKILL.md:**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**From ClawHub:**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \n```\n\nAfter compilation passes, prompt: publish to Cloud (`rotifer publish`) or submit to Arena (`rotifer arena submit`).\n\n`rotifer publish` defaults to uploading to the Rotifer Cloud Registry.\nDisable with `rotifer config set default-publish false` or `ROTIFER_AUTO_PUBLISH=false`.\n\n### Offline Fallback\n\nIf the Playground API is unreachable, display:\n\n> Network unavailable. Use `rotifer init` for local-only Gene creation.\n\nThen follow Path B (CLI).\n\nFor deeper development details (inputSchema design, express function implementation) → route to `gene` skill (`modules/dev.md`).\n\n---\n\n## 3. doctor — Diagnostics & Repair\n\n### Decision Tree\n\n```text\nUser reports a problem\n |\n +-- F(g) = 0 or abnormally low score\n | +-- Does rotifer test pass?\n | | +-- Fails → Check if express() return value matches outputSchema\n | | +-- Passes → Check if phenotype.json domain is reasonable\n | +-- Are there competitors in the same domain?\n | +-- Yes → Analyze competitor strengths, suggest optimizations\n |\n +-- Publish failed\n | +-- Does rotifer compile succeed?\n | | +-- Fails → rotifer doctor first, then syntax errors / missing dependencies\n | | +-- Succeeds → rotifer whoami — signed in at all, and as whom?\n | | Then check network connectivity\n | +-- Is phenotype.json format valid?\n |\n +-- Compilation failed\n | +-- FIRST: rotifer doctor — is the TS→WASM toolchain even installed?\n | | +-- Reports esbuild / javy missing → install those; the code is not the problem\n | +-- Check the exported express function signature in index.ts\n | +-- Check inputSchema / outputSchema in phenotype.json\n | +-- Check if fidelity declaration matches actual code\n | +-- Declared Native but has fetch calls → Change to Hybrid or remove network calls\n |\n +-- Runtime error\n +-- rotifer test --verbose\n +-- Check if input conforms to inputSchema\n +-- Check if express() handles edge cases correctly\n```\n\n### Common Diagnostic Commands\n\n```bash\nrotifer doctor # TS→WASM toolchain — run this before blaming the code\nrotifer test \nrotifer vg # V(g) security scan — grade A–D, or ? for a code-free Skill\nrotifer list\nrotifer arena list --domain \nrotifer arena watch # live ranking movement (Ctrl+C to stop)\n```\n\n`rotifer doctor` takes no arguments and checks one thing: whether esbuild and\njavy are present and reachable on `PATH`. A missing toolchain surfaces as a\ncompile failure that reads like a code error, so it is the cheapest first move\non any \"compilation failed\" report.\n\n### Quick Reference\n\n| Symptom | Root cause | Fix |\n|---------|-----------|-----|\n| F(g) = 0 | express() returns empty or format mismatch | Fix return value to match outputSchema |\n| Compilation failed | TypeScript type error | Check express function signature |\n| Publish timeout | Cloud credentials expired | `rotifer whoami` to check, then `rotifer login` |\n| Arena ranking dropped | Stronger competitor appeared in same domain | `rotifer arena watch ` to see who moved, then optimize or upgrade fidelity |\n| Fidelity mismatch | Native declared but has fetch calls | Remove network calls or change declaration to Hybrid |\n| `compile` fails but the code looks fine | esbuild / javy missing from the toolchain | `rotifer doctor`, then install what it names |\n\n---\n\n## 4. explorer — Ecosystem Search\n\n### Phase 1: Understand the Need\n\nExtract from user description: functionality keywords, target domain, fidelity preference.\n\n### Phase 2: Search\n\n`rotifer search` is the ecosystem search — it queries the Cloud registry, which\nis where Genes published by other people live. `arena list` ranks what is\nalready in the Arena and `list` shows what is on this machine; all three answer\ndifferent questions, so pick by what the user asked for.\n\n```bash\nrotifer search # the ecosystem — Cloud registry\nrotifer search --domain --fidelity Native --sort downloads\nrotifer arena list --domain # ranked competitors in one domain\nrotifer list # what is already installed here\n```\n\nFollow up on a specific result:\n\n```bash\nrotifer info # full details, local or Cloud\nrotifer reputation # R(g) — the reputation column below\nrotifer stats # downloads: 7d / 30d / 90d / all time\nrotifer versions @owner/ # version history chain\nrotifer compare # 2–5 published Genes, side by side\n```\n\n`rotifer reputation @username` scores a creator instead of a Gene, and\n`--leaderboard` ranks creators.\n\n### Phase 3: Result Analysis\n\nDisplay search results in a table:\n\n| Field | Description |\n|-------|-------------|\n| name | Gene name |\n| domain | Category |\n| fidelity | Native / Hybrid / Wrapped |\n| F(g) | Fitness score |\n| R(g) | Reputation score |\n\n### Phase 4: Recommendation\n\n- Found a matching Gene → suggest install: `rotifer install `\n- Found a partial match → suggest fork and modify, or submit an Arena challenge (route to `rotifer-arena/SKILL.md`)\n- Nothing found → suggest creating a new Gene (route to scaffold)\n\n---\n\n## 5. upgrade — Fidelity Evolution\n\n### Phase 1: Assess Current State\n\n```bash\nrotifer list\n```\n\nCheck the target Gene's phenotype.json — confirm current fidelity and express() implementation.\n\n### Phase 2: Migration Path Decision\n\n| Current | Target | Condition | Path |\n|---------|--------|-----------|------|\n| Wrapped | Native | Functionality can be implemented as pure computation | Rewrite express(), remove all external calls |\n| Wrapped | Hybrid | Must call external APIs | Add WASM shell + allowedDomains whitelist |\n| Hybrid | Native | Can internalize API dependencies | Replace API calls with local algorithms |\n\n### Phase 3: Execute Migration\n\nAfter confirming the migration plan, route to `gene` skill (`modules/migration.md`) for the full migration workflow.\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer vg \nrotifer compile \nrotifer arena submit \nrotifer arena watch \n```\n\nA fidelity upgrade rewrites the Gene's code, so the V(g) security grade it\nearned before the rewrite no longer describes it — `rotifer vg` re-scans and\nreturns A–D (or `?` when there is no `src/`). Compare F(g) before and after to\nconfirm ranking continuity; `arena watch` shows the move happening rather than\nrequiring a second `arena list`.\n\nFile v1.1.0:README.md\n\n# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n## What It Does\n\nOne Skill, five capabilities — tell it what you need:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — walks you through core concepts with hands-on CLI examples |\n| \"Create a grammar checker Gene\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene score is 0\" | **Doctor** — diagnoses why, fixes the root cause |\n| \"Find a web search Gene\" | **Explorer** — searches the ecosystem, recommends the best match |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, guides the fidelity jump |\n\n## Quick Start\n\nAfter installing this Skill, just describe what you need in natural language:\n\n```\nI want to create a Gene that summarizes web pages\n```\n\nThe Skill identifies your intent, picks the right sub-capability, and walks you through the full workflow.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## Related Skills\n\n- [rotifer-arena](https://clawhub.ai/skills/rotifer-arena) — Compare and evaluate Genes\n- [rotifer-agent](https://clawhub.ai/skills/rotifer-agent) — Compose Genes into Agents\n- [rotifer-self-evolving-agent](https://clawhub.ai/skills/rotifer-self-evolving-agent) — Auto-evolve your Agent\n\n## Links\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n\n## License\n\nApache-2.0\n\nFile v1.1.0:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.1.0\",\n \"publishedAt\": 1786957893864\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nUnified user-facing entry point for Rotifer Protocol: interactive onboarding, natural-language scaffolding, diagnostics, ecosystem search, and fidelity upgrade.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[xiaoba-dev](https://clawhub.ai/user/xiaoba-dev)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to learn Rotifer concepts, scaffold Genes, diagnose Rotifer CLI and publishing issues, search the Gene ecosystem, and plan fidelity upgrades.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill may guide an agent to run local shell commands, install global npm packages, or use packages that resolve to the latest release.\n\nMitigation: Review commands before execution, prefer pinned package versions where reproducibility matters, and run diagnostics such as rotifer doctor before changing project files.\n\nRisk: Scaffolding and publishing workflows can send source code or metadata to Rotifer Web Studio, Rotifer Cloud, or Arena services.\n\nMitigation: Confirm network use and publishing intent before submitting source, metadata, or generated Genes to external services.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/xiaoba-dev/skills/rotifer-guide)\n- [Rotifer Protocol](https://rotifer.dev)\n- [Rotifer documentation](https://rotifer.dev/docs)\n- [Rotifer Web Studio](https://rotifer.ai/studio/)\n- [Rotifer Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n- [Rotifer Playground repository](https://github.com/rotifer-protocol/rotifer-playground)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline bash, JSON, and text command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May propose command execution, file changes, outbound network use, Rotifer Cloud publishing, and Arena submission workflows for user review.]\n\n## Skill Version(s):\n\n1.1.0 (source: server release metadata and clawhub.json)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.1.0:clawhub.json\n\n{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.1.0\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [\n \"process:exec\",\n \"filesystem:read\",\n \"filesystem:write\",\n \"network:outbound\"\n ],\n \"screenshots\": [],\n \"demo_video\": null\n}\n\nArchive v1.0.3: 5 files, 6650 bytes\n\nFiles: clawhub.json (778b), README.md (1965b), skill-card.md (2448b), SKILL.md (8509b), _meta.json (132b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Unified user-facing entry point for Rotifer Protocol: interactive onboarding, natural-language\n scaffolding, diagnostics, ecosystem search, and fidelity upgrade.\n Use when the user mentions \"how to use Rotifer\", \"getting started\", \"tutorial\", \"beginner\",\n \"create gene\", \"make a\", \"init\", \"score is 0\", \"publish failed\", \"diagnose\", \"check\",\n \"find a gene\", \"recommend\", \"search\", \"upgrade\", \"Wrapped to Native\", \"fidelity\", \"evolve\".\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Prerequisites\n\nBefore using this Skill, ensure the Rotifer CLI is available:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nIf you prefer MCP integration instead of CLI, add this to your MCP config:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\nNo version pinning needed — both packages resolve to the latest release automatically.\n\n---\n\n## Intent Router\n\n| User signal | Sub-capability | Action |\n|-------------|---------------|--------|\n| How to / getting started / tutorial / beginner / what is a Gene | **onboarding** | Interactive walkthrough |\n| Create / make a XX / new / init / I want a | **scaffold** | Natural-language scaffolding |\n| Score is 0 / publish failed / something's wrong / why / diagnose / check | **doctor** | Diagnostics & repair |\n| Any gene for / recommend / search / find one that does XX | **explorer** | Ecosystem search |\n| Upgrade / Wrapped to Native / fidelity / evolve / rewrite | **upgrade** | Fidelity evolution |\n\nWhen intent is unclear, list all five sub-capabilities and let the user choose.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|---------------|\n| `gene-dev/SKILL.md` | Deep technical manual for scaffold / onboarding | User needs full development workflow details |\n| `gene-migration/SKILL.md` | Deep migration manual for upgrade | After user confirms migration plan |\n| `rotifer-arena/SKILL.md` | Comparison & evaluation entry | User wants to compare Genes / run Arena |\n| `genome/SKILL.md` | Gene composition | User wants to combine multiple Genes into an Agent |\n\n---\n\n## 1. onboarding — Interactive Walkthrough\n\n### Phase 1: Environment Check\n\n```bash\ncd rotifer-playground\nnode dist/index.js --version\nnode dist/index.js list\n```\n\nIf not installed, guide: `git clone` → `npm install` → `npm run build`.\n\n### Phase 2: Core Concepts\n\n| Concept | One-liner | Analogy |\n|---------|-----------|---------|\n| Gene | Self-contained logic unit: `express(input) → output` | Function |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure | Compiler optimization level |\n| Arena | Genes compete for ranking via F(g) fitness score | Leaderboard |\n| Domain | Two-level category like `content.grammar` | Namespace |\n| phenotype.json | Gene metadata | package.json |\n| R(g) / V(g) | Reputation score / Security score | Credit rating |\n\n### Phase 3: Hands-on Experience\n\nWalk the user through a Gene's complete lifecycle:\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\nAfter each step, explain the output and confirm the user understands before proceeding.\n\n### Phase 4: Next Steps\n\nRecommend based on user background:\n- Has an existing SKILL.md → scaffold (`rotifer wrap`)\n- Wants to browse the ecosystem → explorer\n- Wants to dive deeper → route to `gene-dev/SKILL.md`\n\n---\n\n## 2. scaffold — Natural-Language Scaffolding\n\n### Phase 1: Intent Extraction\n\nExtract from the user's natural-language description:\n\n| Parameter | Extraction method | Default |\n|-----------|------------------|---------|\n| name | Generate kebab-case from description | Must confirm |\n| domain | Infer two-level domain from functionality | Must confirm |\n| fidelity | Needs external API → Hybrid, pure computation → Native, quick prototype → Wrapped | Wrapped |\n\n### Phase 2: Confirm Parameters\n\nPresent inferred results to the user, wait for confirmation before executing.\n\n### Phase 3: Scaffold Generation\n\n**From scratch:**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**From an existing SKILL.md:**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**From ClawHub:**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \n```\n\nAfter compilation passes, prompt: publish to Cloud (`rotifer publish`) or submit to Arena (`rotifer arena submit`).\n\nFor deeper development details (inputSchema design, express function implementation) → route to `gene-dev/SKILL.md`.\n\n---\n\n## 3. doctor — Diagnostics & Repair\n\n### Decision Tree\n\n```text\nUser reports a problem\n |\n +-- F(g) = 0 or abnormally low score\n | +-- Does rotifer test pass?\n | | +-- Fails → Check if express() return value matches outputSchema\n | | +-- Passes → Check if phenotype.json domain is reasonable\n | +-- Are there competitors in the same domain?\n | +-- Yes → Analyze competitor strengths, suggest optimizations\n |\n +-- Publish failed\n | +-- Does rotifer compile succeed?\n | | +-- Fails → Check for syntax errors, missing dependencies\n | | +-- Succeeds → Check network connection, Cloud credentials\n | +-- Is phenotype.json format valid?\n |\n +-- Compilation failed\n | +-- Check the exported express function signature in index.ts\n | +-- Check inputSchema / outputSchema in phenotype.json\n | +-- Check if fidelity declaration matches actual code\n | +-- Declared Native but has fetch calls → Change to Hybrid or remove network calls\n |\n +-- Runtime error\n +-- rotifer test --verbose\n +-- Check if input conforms to inputSchema\n +-- Check if express() handles edge cases correctly\n```\n\n### Common Diagnostic Commands\n\n```bash\nrotifer test \nrotifer list\nrotifer arena list --domain \n```\n\n### Quick Reference\n\n| Symptom | Root cause | Fix |\n|---------|-----------|-----|\n| F(g) = 0 | express() returns empty or format mismatch | Fix return value to match outputSchema |\n| Compilation failed | TypeScript type error | Check express function signature |\n| Publish timeout | Cloud credentials expired | Refresh Cloud credentials |\n| Arena ranking dropped | Stronger competitor appeared in same domain | Optimize algorithm or upgrade fidelity |\n| Fidelity mismatch | Native declared but has fetch calls | Remove network calls or change declaration to Hybrid |\n\n---\n\n## 4. explorer — Ecosystem Search\n\n### Phase 1: Understand the Need\n\nExtract from user description: functionality keywords, target domain, fidelity preference.\n\n### Phase 2: Search\n\n```bash\nrotifer arena list\nrotifer arena list --domain \nrotifer list\n```\n\n### Phase 3: Result Analysis\n\nDisplay search results in a table:\n\n| Field | Description |\n|-------|-------------|\n| name | Gene name |\n| domain | Category |\n| fidelity | Native / Hybrid / Wrapped |\n| F(g) | Fitness score |\n| R(g) | Reputation score |\n\n### Phase 4: Recommendation\n\n- Found a matching Gene → suggest install: `rotifer install `\n- Found a partial match → suggest fork and modify, or submit an Arena challenge (route to `rotifer-arena/SKILL.md`)\n- Nothing found → suggest creating a new Gene (route to scaffold)\n\n---\n\n## 5. upgrade — Fidelity Evolution\n\n### Phase 1: Assess Current State\n\n```bash\nrotifer list\n```\n\nCheck the target Gene's phenotype.json — confirm current fidelity and express() implementation.\n\n### Phase 2: Migration Path Decision\n\n| Current | Target | Condition | Path |\n|---------|--------|-----------|------|\n| Wrapped | Native | Functionality can be implemented as pure computation | Rewrite express(), remove all external calls |\n| Wrapped | Hybrid | Must call external APIs | Add WASM shell + allowedDomains whitelist |\n| Hybrid | Native | Can internalize API dependencies | Replace API calls with local algorithms |\n\n### Phase 3: Execute Migration\n\nAfter confirming the migration plan, route to `gene-migration/SKILL.md` for the full migration workflow.\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \nrotifer arena submit \n```\n\nCompare F(g) scores before and after migration to confirm ranking continuity.\n\nFile v1.0.3:README.md\n\n# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n## What It Does\n\nOne Skill, five capabilities — tell it what you need:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — walks you through core concepts with hands-on CLI examples |\n| \"Create a grammar checker Gene\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene score is 0\" | **Doctor** — diagnoses why, fixes the root cause |\n| \"Find a web search Gene\" | **Explorer** — searches the ecosystem, recommends the best match |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, guides the fidelity jump |\n\n## Quick Start\n\nAfter installing this Skill, just describe what you need in natural language:\n\n```\nI want to create a Gene that summarizes web pages\n```\n\nThe Skill identifies your intent, picks the right sub-capability, and walks you through the full workflow.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## Related Skills\n\n- [rotifer-arena](https://clawhub.ai/skills/rotifer-arena) — Compare and evaluate Genes\n- [rotifer-agent](https://clawhub.ai/skills/rotifer-agent) — Compose Genes into Agents\n- [rotifer-self-evolving-agent](https://clawhub.ai/skills/rotifer-self-evolving-agent) — Auto-evolve your Agent\n\n## Links\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n\n## License\n\nApache-2.0\n\nFile v1.0.3:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.0.3\",\n \"publishedAt\": 1776265985361\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:
\nInteractive onboarding for Rotifer Protocol that helps users learn core concepts, scaffold Genes, diagnose issues, explore the ecosystem, and upgrade fidelity.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[xiaoba-dev](https://clawhub.ai/user/xiaoba-dev)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and external users use this skill as a Rotifer Protocol entry point for onboarding, natural-language Gene scaffolding, troubleshooting, ecosystem search, and fidelity migration guidance.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Broad trigger wording can route unrelated Rotifer or Gene prompts into this skill.
\nMitigation: Use explicit prompts that mention Rotifer or Genes, and confirm the user's intended sub-capability when intent is unclear.
\nRisk: Generated scaffolds or repair guidance can introduce incorrect Gene metadata, schemas, or commands.
\nMitigation: Review generated scaffold plans and run Rotifer test and compile checks before publishing or submitting to Arena.
\nRisk: The skill suggests npm-based CLI and MCP commands that resolve packages at the latest version.
\nMitigation: Pin npm package versions or Git tags before running install or build commands in sensitive environments.
\n\n\n## Reference(s):
\n- [ClawHub Skill Page](https://clawhub.ai/xiaoba-dev/rotifer-guide)
\n- [Rotifer Protocol](https://rotifer.dev)
\n- [Rotifer Documentation](https://rotifer.dev/docs)
\n- [Rotifer Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)
\n\n\n## Skill Output:
\n**Output Type(s):** [guidance, markdown, shell commands, configuration]
\n**Output Format:** [Markdown guidance with inline shell commands, tables, and configuration snippets]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May include recommended Rotifer CLI commands, MCP configuration snippets, diagnostic tables, and scaffold plans.]
\n\n## Skill Version(s):
\n1.0.3 (source: evidence.release.version and artifact clawhub.json)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nFile v1.0.3:clawhub.json\n\n{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.0.3\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [],\n \"screenshots\": [],\n \"demo_video\": null\n}\n\nArchive v1.0.2: 4 files, 5184 bytes\n\nFiles: clawhub.json (778b), README.md (1965b), SKILL.md (8086b), _meta.json (132b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Unified user-facing entry point for Rotifer Protocol: interactive onboarding, natural-language\n scaffolding, diagnostics, ecosystem search, and fidelity upgrade.\n Use when the user mentions \"how to use Rotifer\", \"getting started\", \"tutorial\", \"beginner\",\n \"create gene\", \"make a\", \"init\", \"score is 0\", \"publish failed\", \"diagnose\", \"check\",\n \"find a gene\", \"recommend\", \"search\", \"upgrade\", \"Wrapped to Native\", \"fidelity\", \"evolve\".\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Intent Router\n\n| User signal | Sub-capability | Action |\n|-------------|---------------|--------|\n| How to / getting started / tutorial / beginner / what is a Gene | **onboarding** | Interactive walkthrough |\n| Create / make a XX / new / init / I want a | **scaffold** | Natural-language scaffolding |\n| Score is 0 / publish failed / something's wrong / why / diagnose / check | **doctor** | Diagnostics & repair |\n| Any gene for / recommend / search / find one that does XX | **explorer** | Ecosystem search |\n| Upgrade / Wrapped to Native / fidelity / evolve / rewrite | **upgrade** | Fidelity evolution |\n\nWhen intent is unclear, list all five sub-capabilities and let the user choose.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|---------------|\n| `gene-dev/SKILL.md` | Deep technical manual for scaffold / onboarding | User needs full development workflow details |\n| `gene-migration/SKILL.md` | Deep migration manual for upgrade | After user confirms migration plan |\n| `rotifer-arena/SKILL.md` | Comparison & evaluation entry | User wants to compare Genes / run Arena |\n| `genome/SKILL.md` | Gene composition | User wants to combine multiple Genes into an Agent |\n\n---\n\n## 1. onboarding — Interactive Walkthrough\n\n### Phase 1: Environment Check\n\n```bash\ncd rotifer-playground\nnode dist/index.js --version\nnode dist/index.js list\n```\n\nIf not installed, guide: `git clone` → `npm install` → `npm run build`.\n\n### Phase 2: Core Concepts\n\n| Concept | One-liner | Analogy |\n|---------|-----------|---------|\n| Gene | Self-contained logic unit: `express(input) → output` | Function |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure | Compiler optimization level |\n| Arena | Genes compete for ranking via F(g) fitness score | Leaderboard |\n| Domain | Two-level category like `content.grammar` | Namespace |\n| phenotype.json | Gene metadata | package.json |\n| R(g) / V(g) | Reputation score / Security score | Credit rating |\n\n### Phase 3: Hands-on Experience\n\nWalk the user through a Gene's complete lifecycle:\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\nAfter each step, explain the output and confirm the user understands before proceeding.\n\n### Phase 4: Next Steps\n\nRecommend based on user background:\n- Has an existing SKILL.md → scaffold (`rotifer wrap`)\n- Wants to browse the ecosystem → explorer\n- Wants to dive deeper → route to `gene-dev/SKILL.md`\n\n---\n\n## 2. scaffold — Natural-Language Scaffolding\n\n### Phase 1: Intent Extraction\n\nExtract from the user's natural-language description:\n\n| Parameter | Extraction method | Default |\n|-----------|------------------|---------|\n| name | Generate kebab-case from description | Must confirm |\n| domain | Infer two-level domain from functionality | Must confirm |\n| fidelity | Needs external API → Hybrid, pure computation → Native, quick prototype → Wrapped | Wrapped |\n\n### Phase 2: Confirm Parameters\n\nPresent inferred results to the user, wait for confirmation before executing.\n\n### Phase 3: Scaffold Generation\n\n**From scratch:**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**From an existing SKILL.md:**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**From ClawHub:**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \n```\n\nAfter compilation passes, prompt: publish to Cloud (`rotifer publish`) or submit to Arena (`rotifer arena submit`).\n\nFor deeper development details (inputSchema design, express function implementation) → route to `gene-dev/SKILL.md`.\n\n---\n\n## 3. doctor — Diagnostics & Repair\n\n### Decision Tree\n\n```text\nUser reports a problem\n |\n +-- F(g) = 0 or abnormally low score\n | +-- Does rotifer test pass?\n | | +-- Fails → Check if express() return value matches outputSchema\n | | +-- Passes → Check if phenotype.json domain is reasonable\n | +-- Are there competitors in the same domain?\n | +-- Yes → Analyze competitor strengths, suggest optimizations\n |\n +-- Publish failed\n | +-- Does rotifer compile succeed?\n | | +-- Fails → Check for syntax errors, missing dependencies\n | | +-- Succeeds → Check network connection, Cloud credentials\n | +-- Is phenotype.json format valid?\n |\n +-- Compilation failed\n | +-- Check the exported express function signature in index.ts\n | +-- Check inputSchema / outputSchema in phenotype.json\n | +-- Check if fidelity declaration matches actual code\n | +-- Declared Native but has fetch calls → Change to Hybrid or remove network calls\n |\n +-- Runtime error\n +-- rotifer test --verbose\n +-- Check if input conforms to inputSchema\n +-- Check if express() handles edge cases correctly\n```\n\n### Common Diagnostic Commands\n\n```bash\nrotifer test \nrotifer list\nrotifer arena list --domain \n```\n\n### Quick Reference\n\n| Symptom | Root cause | Fix |\n|---------|-----------|-----|\n| F(g) = 0 | express() returns empty or format mismatch | Fix return value to match outputSchema |\n| Compilation failed | TypeScript type error | Check express function signature |\n| Publish timeout | Cloud credentials expired | Refresh Cloud credentials |\n| Arena ranking dropped | Stronger competitor appeared in same domain | Optimize algorithm or upgrade fidelity |\n| Fidelity mismatch | Native declared but has fetch calls | Remove network calls or change declaration to Hybrid |\n\n---\n\n## 4. explorer — Ecosystem Search\n\n### Phase 1: Understand the Need\n\nExtract from user description: functionality keywords, target domain, fidelity preference.\n\n### Phase 2: Search\n\n```bash\nrotifer arena list\nrotifer arena list --domain \nrotifer list\n```\n\n### Phase 3: Result Analysis\n\nDisplay search results in a table:\n\n| Field | Description |\n|-------|-------------|\n| name | Gene name |\n| domain | Category |\n| fidelity | Native / Hybrid / Wrapped |\n| F(g) | Fitness score |\n| R(g) | Reputation score |\n\n### Phase 4: Recommendation\n\n- Found a matching Gene → suggest install: `rotifer install `\n- Found a partial match → suggest fork and modify, or submit an Arena challenge (route to `rotifer-arena/SKILL.md`)\n- Nothing found → suggest creating a new Gene (route to scaffold)\n\n---\n\n## 5. upgrade — Fidelity Evolution\n\n### Phase 1: Assess Current State\n\n```bash\nrotifer list\n```\n\nCheck the target Gene's phenotype.json — confirm current fidelity and express() implementation.\n\n### Phase 2: Migration Path Decision\n\n| Current | Target | Condition | Path |\n|---------|--------|-----------|------|\n| Wrapped | Native | Functionality can be implemented as pure computation | Rewrite express(), remove all external calls |\n| Wrapped | Hybrid | Must call external APIs | Add WASM shell + allowedDomains whitelist |\n| Hybrid | Native | Can internalize API dependencies | Replace API calls with local algorithms |\n\n### Phase 3: Execute Migration\n\nAfter confirming the migration plan, route to `gene-migration/SKILL.md` for the full migration workflow.\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \nrotifer arena submit \n```\n\nCompare F(g) scores before and after migration to confirm ranking continuity.\n\nFile v1.0.2:README.md\n\n# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n## What It Does\n\nOne Skill, five capabilities — tell it what you need:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — walks you through core concepts with hands-on CLI examples |\n| \"Create a grammar checker Gene\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene score is 0\" | **Doctor** — diagnoses why, fixes the root cause |\n| \"Find a web search Gene\" | **Explorer** — searches the ecosystem, recommends the best match |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, guides the fidelity jump |\n\n## Quick Start\n\nAfter installing this Skill, just describe what you need in natural language:\n\n```\nI want to create a Gene that summarizes web pages\n```\n\nThe Skill identifies your intent, picks the right sub-capability, and walks you through the full workflow.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## Related Skills\n\n- [rotifer-arena](https://clawhub.ai/skills/rotifer-arena) — Compare and evaluate Genes\n- [rotifer-agent](https://clawhub.ai/skills/rotifer-agent) — Compose Genes into Agents\n- [rotifer-self-evolving-agent](https://clawhub.ai/skills/rotifer-self-evolving-agent) — Auto-evolve your Agent\n\n## Links\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n\n## License\n\nApache-2.0\n\nFile v1.0.2:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1776261767092\n}\n\nFile v1.0.2:clawhub.json\n\n{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.0.2\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [],\n \"screenshots\": [],\n \"demo_video\": null\n}\n\nArchive v1.0.1: 4 files, 5181 bytes\n\nFiles: clawhub.json (778b), README.md (1965b), SKILL.md (8082b), _meta.json (132b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Unified user-facing entry point for Rotifer Protocol: interactive onboarding, natural-language\n scaffolding, diagnostics, ecosystem search, and fidelity upgrade.\n Use when the user mentions \"how to use Rotifer\", \"getting started\", \"tutorial\", \"beginner\",\n \"create gene\", \"make a\", \"init\", \"score is 0\", \"publish failed\", \"diagnose\", \"check\",\n \"find a gene\", \"recommend\", \"search\", \"upgrade\", \"Wrapped to Native\", \"fidelity\", \"evolve\".\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Intent Router\n\n| User signal | Sub-capability | Action |\n|-------------|---------------|--------|\n| How to / getting started / tutorial / beginner / what is a Gene | **onboarding** | Interactive walkthrough |\n| Create / make a XX / new / init / I want a | **scaffold** | Natural-language scaffolding |\n| Score is 0 / publish failed / something's wrong / why / diagnose / check | **doctor** | Diagnostics & repair |\n| Any gene for / recommend / search / find one that does XX | **explorer** | Ecosystem search |\n| Upgrade / Wrapped to Native / fidelity / evolve / rewrite | **upgrade** | Fidelity evolution |\n\nWhen intent is unclear, list all five sub-capabilities and let the user choose.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|---------------|\n| `gene-dev/SKILL.md` | Deep technical manual for scaffold / onboarding | User needs full development workflow details |\n| `gene-migration/SKILL.md` | Deep migration manual for upgrade | After user confirms migration plan |\n| `rotifer-arena/SKILL.md` | Comparison & evaluation entry | User wants to compare Genes / run Arena |\n| `genome/SKILL.md` | Gene composition | User wants to combine multiple Genes into an Agent |\n\n---\n\n## 1. onboarding — Interactive Walkthrough\n\n### Phase 1: Environment Check\n\n```bash\ncd rotifer-playground\nnode dist/index.js --version\nnode dist/index.js list\n```\n\nIf not installed, guide: `git clone` → `npm install` → `npm run build`.\n\n### Phase 2: Core Concepts\n\n| Concept | One-liner | Analogy |\n|---------|-----------|---------|\n| Gene | Self-contained logic unit: `express(input) → output` | Function |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure | Compiler optimization level |\n| Arena | Genes compete for ranking via F(g) fitness score | Leaderboard |\n| Domain | Two-level category like `content.grammar` | Namespace |\n| phenotype.json | Gene metadata | package.json |\n| R(g) / V(g) | Reputation score / Security score | Credit rating |\n\n### Phase 3: Hands-on Experience\n\nWalk the user through a Gene's complete lifecycle:\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\nAfter each step, explain the output and confirm the user understands before proceeding.\n\n### Phase 4: Next Steps\n\nRecommend based on user background:\n- Has an existing SKILL.md → scaffold (`rotifer wrap`)\n- Wants to browse the ecosystem → explorer\n- Wants to dive deeper → route to `gene-dev/SKILL.md`\n\n---\n\n## 2. scaffold — Natural-Language Scaffolding\n\n### Phase 1: Intent Extraction\n\nExtract from the user's natural-language description:\n\n| Parameter | Extraction method | Default |\n|-----------|------------------|---------|\n| name | Generate kebab-case from description | Must confirm |\n| domain | Infer two-level domain from functionality | Must confirm |\n| fidelity | Needs external API → Hybrid, pure computation → Native, quick prototype → Wrapped | Wrapped |\n\n### Phase 2: Confirm Parameters\n\nPresent inferred results to the user, wait for confirmation before executing.\n\n### Phase 3: Scaffold Generation\n\n**From scratch:**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**From an existing SKILL.md:**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**From ClawHub:**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \n```\n\nAfter compilation passes, prompt: publish to Cloud (`rotifer publish`) or submit to Arena (`rotifer arena submit`).\n\nFor deeper development details (inputSchema design, express function implementation) → route to `gene-dev/SKILL.md`.\n\n---\n\n## 3. doctor — Diagnostics & Repair\n\n### Decision Tree\n\n```\nUser reports a problem\n |\n +-- F(g) = 0 or abnormally low score\n | +-- Does rotifer test pass?\n | | +-- Fails → Check if express() return value matches outputSchema\n | | +-- Passes → Check if phenotype.json domain is reasonable\n | +-- Are there competitors in the same domain?\n | +-- Yes → Analyze competitor strengths, suggest optimizations\n |\n +-- Publish failed\n | +-- Does rotifer compile succeed?\n | | +-- Fails → Check for syntax errors, missing dependencies\n | | +-- Succeeds → Check network connection, Cloud credentials\n | +-- Is phenotype.json format valid?\n |\n +-- Compilation failed\n | +-- Check the exported express function signature in index.ts\n | +-- Check inputSchema / outputSchema in phenotype.json\n | +-- Check if fidelity declaration matches actual code\n | +-- Declared Native but has fetch calls → Change to Hybrid or remove network calls\n |\n +-- Runtime error\n +-- rotifer test --verbose\n +-- Check if input conforms to inputSchema\n +-- Check if express() handles edge cases correctly\n```\n\n### Common Diagnostic Commands\n\n```bash\nrotifer test \nrotifer list\nrotifer arena list --domain \n```\n\n### Quick Reference\n\n| Symptom | Root cause | Fix |\n|---------|-----------|-----|\n| F(g) = 0 | express() returns empty or format mismatch | Fix return value to match outputSchema |\n| Compilation failed | TypeScript type error | Check express function signature |\n| Publish timeout | Cloud credentials expired | Refresh Cloud credentials |\n| Arena ranking dropped | Stronger competitor appeared in same domain | Optimize algorithm or upgrade fidelity |\n| Fidelity mismatch | Native declared but has fetch calls | Remove network calls or change declaration to Hybrid |\n\n---\n\n## 4. explorer — Ecosystem Search\n\n### Phase 1: Understand the Need\n\nExtract from user description: functionality keywords, target domain, fidelity preference.\n\n### Phase 2: Search\n\n```bash\nrotifer arena list\nrotifer arena list --domain \nrotifer list\n```\n\n### Phase 3: Result Analysis\n\nDisplay search results in a table:\n\n| Field | Description |\n|-------|-------------|\n| name | Gene name |\n| domain | Category |\n| fidelity | Native / Hybrid / Wrapped |\n| F(g) | Fitness score |\n| R(g) | Reputation score |\n\n### Phase 4: Recommendation\n\n- Found a matching Gene → suggest install: `rotifer install `\n- Found a partial match → suggest fork and modify, or submit an Arena challenge (route to `rotifer-arena/SKILL.md`)\n- Nothing found → suggest creating a new Gene (route to scaffold)\n\n---\n\n## 5. upgrade — Fidelity Evolution\n\n### Phase 1: Assess Current State\n\n```bash\nrotifer list\n```\n\nCheck the target Gene's phenotype.json — confirm current fidelity and express() implementation.\n\n### Phase 2: Migration Path Decision\n\n| Current | Target | Condition | Path |\n|---------|--------|-----------|------|\n| Wrapped | Native | Functionality can be implemented as pure computation | Rewrite express(), remove all external calls |\n| Wrapped | Hybrid | Must call external APIs | Add WASM shell + allowedDomains whitelist |\n| Hybrid | Native | Can internalize API dependencies | Replace API calls with local algorithms |\n\n### Phase 3: Execute Migration\n\nAfter confirming the migration plan, route to `gene-migration/SKILL.md` for the full migration workflow.\n\n### Phase 4: Verification\n\n```bash\nrotifer test \nrotifer compile \nrotifer arena submit \n```\n\nCompare F(g) scores before and after migration to confirm ranking continuity.\n\nFile v1.0.1:README.md\n\n# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n## What It Does\n\nOne Skill, five capabilities — tell it what you need:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — walks you through core concepts with hands-on CLI examples |\n| \"Create a grammar checker Gene\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene score is 0\" | **Doctor** — diagnoses why, fixes the root cause |\n| \"Find a web search Gene\" | **Explorer** — searches the ecosystem, recommends the best match |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, guides the fidelity jump |\n\n## Quick Start\n\nAfter installing this Skill, just describe what you need in natural language:\n\n```\nI want to create a Gene that summarizes web pages\n```\n\nThe Skill identifies your intent, picks the right sub-capability, and walks you through the full workflow.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## Related Skills\n\n- [rotifer-arena](https://clawhub.ai/skills/rotifer-arena) — Compare and evaluate Genes\n- [rotifer-agent](https://clawhub.ai/skills/rotifer-agent) — Compose Genes into Agents\n- [rotifer-self-evolving-agent](https://clawhub.ai/skills/rotifer-self-evolving-agent) — Auto-evolve your Agent\n\n## Links\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Documentation](https://rotifer.dev/docs)\n- [Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n\n## License\n\nApache-2.0\n\nFile v1.0.1:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1776261572080\n}\n\nFile v1.0.1:clawhub.json\n\n{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.0.1\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [],\n \"screenshots\": [],\n \"demo_video\": null\n}\n\nArchive v1.0.0: 4 files, 5235 bytes\n\nFiles: clawhub.json (778b), README.md (1965b), SKILL.md (7398b), _meta.json (132b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: rotifer-guide\ndescription: >-\n Rotifer Protocol 用户侧统一入口：新手引导、自然语言脚手架、诊断修复、生态搜索、Fidelity 进化。\n 当用户提到 \"怎么用 Rotifer\" \"入门\" \"教程\" \"新手\" \"学习\" \"创建 gene\" \"做一个\"\n \"新建\" \"init\" \"分数为 0\" \"发布失败\" \"有问题\" \"为什么\" \"诊断\" \"检查\"\n \"有什么 gene\" \"推荐\" \"搜索\" \"有没有做 XX 的\" \"升级\" \"Wrapped 转 Native\"\n \"fidelity\" \"进化\" 时使用。\n---\n\n# Rotifer Guide — 用户侧统一入口\n\n> 本 Skill 负责意图识别和流程编排，深层技术细节路由到专项 Skill。\n\n## 意图路由表\n\n| 用户信号 | 子能力 | 动作 |\n|---------|--------|------|\n| 怎么用 / 入门 / 教程 / 新手 / 学习 / 什么是 Gene | **onboarding** | 交互式新手引导 |\n| 创建 / 做一个 XX / 新建 / init / 我想要一个 | **scaffold** | 自然语言脚手架 |\n| 分数为 0 / 发布失败 / 有问题 / 为什么 / 诊断 / 检查 / 报错 | **doctor** | 诊断修复 |\n| 有什么 gene / 推荐 / 搜索 / 有没有做 XX 的 / 找一个 | **explorer** | 生态搜索 |\n| 升级 / Wrapped 转 Native / fidelity / 进化 / 重写 | **upgrade** | Fidelity 进化 |\n\n无法匹配时列出 5 个子能力供用户选择。\n\n## 关联 Skill\n\n| Skill | 关系 | 何时路由 |\n|-------|------|---------|\n| `gene-dev/SKILL.md` | scaffold / onboarding 的深层技术手册 | 用户需要完整开发流程细节 |\n| `gene-migration/SKILL.md` | upgrade 的深层迁移手册 | 用户确认迁移方案后执行 |\n| `rotifer-arena/SKILL.md` | 对比评估入口 | 用户想对比 Gene / 跑 Arena |\n| `genome/SKILL.md` | Gene 组合编排 | 用户想把多个 Gene 组成 Agent |\n\n---\n\n## 1. onboarding — 交互式新手引导\n\n### Phase 1：环境检查\n\n```bash\ncd rotifer-playground\nnode dist/index.js --version\nnode dist/index.js list\n```\n\n未安装时引导：`git clone` → `npm install` → `npm run build`。\n\n### Phase 2：核心概念速览\n\n| 概念 | 一句话 | 类比 |\n|------|--------|------|\n| Gene | 自包含逻辑单元，`express(input) → output` | 函数 |\n| Fidelity | Native > Hybrid > Wrapped，越高越安全 | 编译优化级别 |\n| Arena | Gene 竞争排名，F(g) 适应度评分 | 排行榜 |\n| Domain | 二级分类 `content.grammar` | 命名空间 |\n| phenotype.json | Gene 元数据 | package.json |\n| R(g) / V(g) | 声誉分 / 安全分 | 信用评级 |\n\n### Phase 3：动手体验\n\n引导用户完成第一个 Gene 的完整生命周期：\n\n```bash\nrotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting\n```\n\n每步执行后解释输出含义，确认用户理解再进入下一步。\n\n### Phase 4：下一步建议\n\n根据用户背景推荐方向：\n- 有现成 SKILL.md → scaffold（`rotifer wrap`）\n- 想浏览生态 → explorer\n- 想深入开发 → 路由到 `gene-dev/SKILL.md`\n\n---\n\n## 2. scaffold — 自然语言脚手架\n\n### Phase 1：意图提取\n\n从用户自然语言中提取：\n\n| 参数 | 提取方式 | 默认值 |\n|------|---------|--------|\n| name | 从描述生成 kebab-case 名称 | 必须确认 |\n| domain | 从功能描述推断二级域 | 必须确认 |\n| fidelity | 需要外部 API → Hybrid，纯计算 → Native，快速原型 → Wrapped | Wrapped |\n\n### Phase 2：确认参数\n\n向用户展示推断结果，等待确认后执行。\n\n### Phase 3：脚手架生成\n\n**从零创建：**\n\n```bash\nrotifer init --domain --fidelity \n```\n\n**从 SKILL.md 转换：**\n\n```bash\nrotifer scan --skills\nrotifer wrap --from-skill \n```\n\n**从 ClawHub 导入：**\n\n```bash\nrotifer wrap --from-clawhub \n```\n\n### Phase 4：验证\n\n```bash\nrotifer test \nrotifer compile \n```\n\n编译通过后提示：可发布到 Cloud（`rotifer publish`）或提交 Arena（`rotifer arena submit`）。\n\n深层开发细节（inputSchema 设计、express 函数编写）→ 路由到 `gene-dev/SKILL.md`。\n\n---\n\n## 3. doctor — 诊断修复\n\n### 诊断决策树\n\n```\n用户报告问题\n |\n +-- F(g) = 0 或分数异常低\n | +-- rotifer test 是否通过？\n | | +-- 失败 → 检查 express() 返回值是否匹配 outputSchema\n | | +-- 通过 → 检查 phenotype.json 的 domain 是否合理\n | +-- Arena 中是否有同域竞争者？\n | +-- 有 → 分析竞争者优势，建议优化\n |\n +-- 发布失败\n | +-- rotifer compile 是否成功？\n | | +-- 失败 → 检查语法错误、缺少依赖\n | | +-- 成功 → 检查网络连接、Cloud 凭证\n | +-- phenotype.json 格式是否合法？\n |\n +-- 编译失败\n | +-- 检查 index.ts 导出的 express 函数签名\n | +-- 检查 phenotype.json 的 inputSchema / outputSchema\n | +-- 检查 fidelity 声明与实际代码是否一致\n | +-- 声明 Native 但有 fetch 调用 → 改为 Hybrid 或移除网络调用\n |\n +-- 运行时错误\n +-- rotifer test --verbose\n +-- 检查输入是否符合 inputSchema\n +-- 检查 express() 是否正确处理边界情况\n```\n\n### 常用诊断命令\n\n```bash\nrotifer test \nrotifer list\nrotifer arena list --domain \n```\n\n### 常见问题速查\n\n| 症状 | 根因 | 修复 |\n|------|------|------|\n| F(g) = 0 | express() 返回空或格式不匹配 | 修正返回值匹配 outputSchema |\n| 编译失败 | TypeScript 类型错误 | 检查 express 函数签名 |\n| 发布超时 | Cloud 凭证过期 | 刷新 Cloud 凭证 |\n| Arena 排名下降 | 同域出现更强竞争者 | 优化算法或升级 fidelity |\n| fidelity 声明不一致 |","readmeExcerpt":"Skill: rotifer-guide Owner: xiaoba-dev Summary: Entry point for Rotifer Protocol — onboarding to Rotifer Genes, scaffolding a Gene from a description, diagnosing a Gene's F(g) or compile failure, searching the Rotifer Gene registry, and upgrading a Gene's fidelity from Wrapped to Native. Invoke explicitly when starting with Rotifer, or when unsure which Rotifer capability to use. Do NOT use for general onboarding, tu","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"npx --yes @rotifer/playground@0.26.0 --version"},{"language":"json","snippet":"{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server@0.17.0\"]\n }\n }\n}"},{"language":"bash","snippet":"npm install --save-dev --save-exact @rotifer/playground@0.26.0\nnpm exec -- rotifer --version"},{"language":"bash","snippet":"npx --yes @rotifer/playground@0.26.0 --version\nrotifer doctor\nrotifer list"},{"language":"bash","snippet":"rotifer hello"},{"language":"bash","snippet":"rotifer init hello-world --domain content.greeting --fidelity Wrapped\nrotifer test hello-world\nrotifer compile hello-world\nrotifer arena submit hello-world\nrotifer arena list --domain content.greeting"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: rotifer-guide\ndescription: >-\n Entry point for Rotifer Protocol — onboarding to Rotifer Genes, scaffolding a Gene from a\n description, diagnosing a Gene's F(g) or compile failure, searching the Rotifer Gene registry,\n and upgrading a Gene's fidelity from Wrapped to Native.\n Invoke explicitly when starting with Rotifer, or when unsure which Rotifer capability to use.\n Do NOT use for general onboarding, tutorials, troubleshooting, or search — every capability\n here operates on Rotifer Genes and the Rotifer CLI, and nothing else.\n---\n\n# Rotifer Guide — User Entry Point\n\n> This Skill handles intent recognition and workflow routing. Deep technical details are delegated to specialized Skills.\n\n## Prerequisites\n\nBefore using this Skill, ensure the Rotifer CLI is available:\n\n```bash\nnpx --yes @rotifer/playground@0.26.0 --version\n```\n\nIf you prefer MCP integration instead of CLI, add this to your MCP config:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server@0.17.0\"]\n }\n }\n}\n```\n\nBoth commands name an exact version on purpose. An unversioned `npx` resolves to whatever the\nregistry serves at that moment, so the code you run would not be the code that was reviewed. The\n`@rotifer/mcp-server` pin is the one this repository agrees on everywhere; move it in one deliberate\nstep, not per file. Stronger than pinning the `npx` call: install the CLI into the project and run\nthe local binary.\n\n```bash\nnpm install --save-dev --save-exact @rotifer/playground@0.26.0\nnpm exec -- rotifer --version\n```\n\nCommit the lockfile and use `npm ci` in automation. Before moving a pin to a newer release, review\nwhat changed and record what you are accepting: `npm view @rotifer/playground@ dist.integrity`.\n\n---\n\n## Intent Router\n\n**Every row assumes the user is already asking about Rotifer.** The signals below\nroute *within* this Skill; they are not reasons to invoke it. A user asking \"how\ndo I get started\" or \"why is my score 0\" without Rotifer in view is asking\nsomeone else.\n\n| User signal (in a Rotifer context) | Sub-capability | Action |\n|-------------|---------------|--------|\n| What is a Gene / how does Rotifer work / new to Rotifer | **onboarding** | Interactive walkthrough, or `rotifer hello` |\n| Create a Gene / scaffold a Gene / wrap this as a Gene | **scaffold** | Natural-language scaffolding |\n| F(g) is 0 / `rotifer compile` fails / `rotifer publish` fails | **doctor** | `rotifer doctor` first, then the Gene |\n| Find a Gene that / any Gene for / search the registry | **explorer** | `rotifer search` |\n| Wrapped to Native / upgrade fidelity / rewrite this Gene | **upgrade** | Fidelity evolution |\n\nWhen the request is about Rotifer but the sub-capability is unclear, list all\nfive and let the user choose. When the request is **not** about Rotifer, say so\nand stop — do not map it onto the nearest row.\n\n## Related Skills\n\n| Skill | Relationship | When to route |\n|-------|-------------|------------"},{"path":"README.md","content":"# Rotifer Guide\n\n> From zero to your first Gene in five minutes.\n\nInteractive onboarding for [Rotifer Protocol](https://rotifer.dev) — the open-source evolution framework for AI agents.\n\n**Not a general help desk.** Every capability here operates on Rotifer Genes and\nthe Rotifer CLI. It is not for general onboarding, tutorials, troubleshooting or\nsearch — if the request is not about Rotifer, this is the wrong Skill.\n\n## What It Does\n\nOne Skill, five capabilities — each one asks about **Rotifer**:\n\n| Say this | It does this |\n|----------|-------------|\n| \"How does Rotifer work?\" | **Onboarding** — core concepts with hands-on CLI examples, or `rotifer hello` for a working Agent in one command |\n| \"Create a Rotifer Gene that checks grammar\" | **Scaffold** — extracts intent, generates the Gene skeleton |\n| \"My Gene's F(g) is 0\" / \"`rotifer compile` fails\" | **Doctor** — `rotifer doctor` for the toolchain first, then the Gene itself |\n| \"Find a Rotifer Gene for web search\" | **Explorer** — `rotifer search` across the Gene registry |\n| \"Upgrade my Wrapped Gene to Native\" | **Upgrade** — evaluates migration path, re-scans V(g) after the rewrite |\n\n## Quick Start\n\nInvoke it explicitly when you are working with Rotifer, then describe what you\nneed in natural language:\n\n```\nI want to create a Rotifer Gene that summarizes web pages\n```\n\nThe Skill picks the right sub-capability and walks you through the workflow. It\ndoes not activate on ordinary requests that happen to mention creating,\nsearching or diagnosing something — Rotifer has to be what you are working on.\n\n## Core Concepts\n\n| Concept | One-liner |\n|---------|-----------|\n| Gene | Self-contained logic unit: `express(input) → output` |\n| Fidelity | Native > Hybrid > Wrapped — higher = more secure |\n| Arena | Genes compete for ranking via F(g) fitness score |\n| Domain | Two-level category like `content.grammar` |\n| phenotype.json | Gene metadata (like package.json for Genes) |\n\n## What this Skill does on your machine\n\nIt has no code of its own — it tells your assistant which `rotifer` commands to\nrun. That is what its manifest's process-execution, filesystem and network\npermissions are for: the CLI acting, not this Skill.\n\n| | |\n|---|---|\n| **Runs** | The `rotifer` CLI, pinned to `@rotifer/playground@0.26.0`; fetched from npm at that exact version if it is not already installed. |\n| **Reads** | Genes and Agent definitions in the current project. |\n| **Writes** | Genes into the project's `genes/`, Agent definitions into `.rotifer/agents/`. Nothing outside the project. |\n| **Sends** | Registry and Arena queries to the public Rotifer API. Two paths send more than a query, and both are opt-in: the Web Studio scaffold path (`/api/playground/generate`, `scan`, `publish`) transmits the description you write and the generated Gene source to rotifer.ai, and `rotifer publish` transmits a Gene's source and makes it public. The CLI scaffold path is entirely local and produces the same result — prefer it for anythi"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-guide\",\n \"version\": \"1.2.2\",\n \"publishedAt\": 1789910472734\n}"},{"path":"skill-card.md","content":"## Description:\n\nRotifer Guide routes Rotifer-related requests into onboarding, Gene scaffolding, diagnostics, registry search, and fidelity-upgrade workflows for the Rotifer CLI.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[xiaoba-dev](https://clawhub.ai/user/xiaoba-dev)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent builders use this skill when working with Rotifer Genes to choose the right workflow for learning Rotifer concepts, creating Genes, diagnosing compile or fitness issues, searching the registry, or planning fidelity upgrades.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Web Studio scaffold and publish workflows can send the user's prompt and generated Gene source to rotifer.ai, and publishing makes the Gene public.\n\nMitigation: Use the local CLI scaffold path for private work and confirm publish intent before running any command that uploads or publishes a Gene.\n\nRisk: The skill proposes Rotifer CLI commands that may install packages, read project Genes or Agent definitions, and write generated files in the project workspace.\n\nMitigation: Review proposed commands before execution, keep Rotifer package versions pinned, and commit lockfiles for reproducible installs.\n\n## Reference(s):\n\n- [Rotifer Protocol](https://rotifer.dev)\n- [Rotifer Documentation](https://rotifer.dev/docs)\n- [Rotifer Protocol Specification](https://github.com/rotifer-protocol/rotifer-spec)\n- [Rotifer Playground Repository](https://github.com/rotifer-protocol/rotifer-playground)\n\n## Skill Output:\n\n**Output Type(s):** [guidance, markdown, shell commands, configuration]\n\n**Output Format:** [Markdown guidance with inline shell commands and JSON configuration snippets]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Routes the user to one of five Rotifer workflows and proposes install, scaffold, diagnostic, search, publish, or upgrade commands for review before execution.]\n\n## Skill Version(s):\n\n1.2.2 (source: server release metadata and clawhub.json)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"clawhub.json","content":"{\n \"name\": \"rotifer-guide\",\n \"display_name\": \"Rotifer Guide\",\n \"description\": \"Interactive onboarding for Rotifer Protocol — learn core concepts, scaffold your first Gene, diagnose issues, explore the ecosystem, and upgrade fidelity. Five sub-capabilities in one entry point.\",\n \"tagline\": \"From zero to your first Gene in five minutes\",\n \"version\": \"1.2.2\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"onboarding\",\n \"gene\",\n \"tutorial\",\n \"scaffold\",\n \"diagnostics\",\n \"fidelity\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [\n \"process:exec\",\n \"filesystem:read\",\n \"filesystem:write\",\n \"network:outbound\"\n ],\n \"screenshots\": [],\n \"demo_video\": null\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":2011,"uniquenessScore":38,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T04:48:48.305Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T04:48:48.305Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T07:39:56.256Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}