{"id":"6b1f463f-1af8-4c58-8009-69bc8214cc90","entityType":"agent","slug":"clawhub-xiaoba-dev-rotifer-arena","name":"rotifer-arena","canonicalUrl":"https://www.xpersona.co/agent/clawhub-xiaoba-dev-rotifer-arena","canonicalPath":"/agent/clawhub-xiaoba-dev-rotifer-arena","generatedAt":"2026-10-12T13:11:33.090Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:13:23.315Z","emptyReason":null},"description":"Benchmark Rotifer Genes against each other in the Arena — import from ClawHub / local / scratch, compile, match opponents, run Arena evaluation, and produce a Markdown report with F(g) fitness and V(g) security grades. Invoke explicitly to compare or benchmark Rotifer Genes. Do NOT use for general benchmarking, load testing, or comparing anything that is not a Rotifer Gene or Agent.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 986 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s174dvd7sg66gw86h4t3c8575d83g51m:rotifer-arena","sourceUrl":"https://clawhub.ai/xiaoba-dev/rotifer-arena","homepage":"https://clawhub.ai/xiaoba-dev/skills/rotifer-arena","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/xiaoba-dev/rotifer-arena","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/xiaoba-dev/skills/rotifer-arena","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"rotifer-arena technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:13:23.315Z","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":"2026-10-11T22:13:23.315Z","emptyReason":null},"stars":null,"forks":null,"downloads":986,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.2.1","tractionLabel":"986 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:13:23.245Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T22:13:23.315Z","lastCrawledAt":"2026-10-11T22:13:23.245Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T22:13:23.245Z","lastVerifiedAt":null,"highlights":[{"version":"1.2.1","createdAt":"2026-08-17T14:54:29.504Z","changelog":"rotifer-arena 1.2.1 - Updated project metadata in clawhub.json. - No functional or workflow changes; documentation and workflow remain unchanged.","fileCount":5,"zipByteSize":8350},{"version":"1.2.0","createdAt":"2026-08-17T14:39:09.906Z","changelog":"rotifer-arena v1.2.0 - Clarified scope to emphasize benchmarking only Rotifer Genes/Agents; added warning against general benchmarking or non-Rotifer comparisons. - Updated description and instructions to focus on F(g) fitness and V(g) security grades. - Removed legacy skill-card.md file; documentation is now streamlined in SKILL.md. - Improved workflow and scenario guidance with explicit command references and examples. - Refined reporting requirements and formatting for clearer evaluation outputs.","fileCount":5,"zipByteSize":7619},{"version":"1.1.1","createdAt":"2026-08-17T09:20:46.194Z","changelog":"- Added explicit instructions that \"save\" only writes the report after user consent, explaining what it does and where the file is created. - Clarified that the full report appears in the conversation first, and will never be written automatically. - Updated Phase 5 in the workflow to describe the \"save\" command's behavior more clearly. - No functional or workflow changes beyond improved user guidance about report saving.","fileCount":5,"zipByteSize":7680},{"version":"1.1.0","createdAt":"2026-08-17T09:11:06.121Z","changelog":"rotifer-arena 1.1.0 - Added explicit steps for running `rotifer vg` to report V(g) security grades, clarifying the origin and necessity of this metric. - Clarified that all report numbers (F(g), V(g), downloads) must come from concrete commands, never guessed or omitted without explanation. - Updated prerequisites and checklist: now requires passing `rotifer doctor`, and clarified installation pathways. - Expanded Arena workflow examples to include live ranking commands (`arena watch`) and ecosystem reputation stats (`rotifer compare`, `rotifer stats`). - Streamlined the description and invocation instructions; report is now only auto-generated with explicit invocation. - Removed obsolete file (`skill-card.md`).","fileCount":5,"zipByteSize":7065},{"version":"1.0.3","createdAt":"2026-04-15T15:13:06.988Z","changelog":"Add Prerequisites section with CLI and MCP setup instructions (no hardcoded versions)","fileCount":5,"zipByteSize":6386},{"version":"1.0.2","createdAt":"2026-04-15T14:02:46.168Z","changelog":"Fix untagged code blocks rendering as invisible text on ClawHub","fileCount":4,"zipByteSize":4908},{"version":"1.0.1","createdAt":"2026-04-15T13:59:34.042Z","changelog":"Translate to English; fix nested code block rendering","fileCount":4,"zipByteSize":4905},{"version":"1.0.0","createdAt":"2026-04-15T13:53:05.807Z","changelog":"Initial release: one-click Gene comparison, Arena evaluation, structured reports","fileCount":4,"zipByteSize":5162}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s174dvd7sg66gw86h4t3c8575d83g51m:rotifer-arena","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s174dvd7sg66gw86h4t3c8575d83g51m:rotifer-arena` 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-arena 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-arena/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-arena/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-arena/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-arena/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-arena/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-arena/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T13:11:33.087Z"}},"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-arena/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-arena/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-arena/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-xiaoba-dev-rotifer-arena/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":"2026-10-11T22:13:23.315Z","emptyReason":null},"readme":"Skill: rotifer-arena\n\nOwner: xiaoba-dev\n\nSummary: Benchmark Rotifer Genes against each other in the Arena — import from ClawHub / local / scratch, compile, match opponents, run Arena evaluation, and produce a Markdown report with F(g) fitness and V(g) security grades. Invoke explicitly to compare or benchmark Rotifer Genes. Do NOT use for general benchmarking, load testing, or comparing anything that is not a Rotifer Gene or Agent.\n\nTags: latest:1.2.1\n\nVersion history:\n\nv1.2.1 | 2026-08-17T14:54:29.504Z | auto\n\nrotifer-arena 1.2.1\n\n- Updated project metadata in clawhub.json.\n- No functional or workflow changes; documentation and workflow remain unchanged.\n\nv1.2.0 | 2026-08-17T14:39:09.906Z | auto\n\nrotifer-arena v1.2.0\n\n- Clarified scope to emphasize benchmarking only Rotifer Genes/Agents; added warning against general benchmarking or non-Rotifer comparisons.\n- Updated description and instructions to focus on F(g) fitness and V(g) security grades.\n- Removed legacy skill-card.md file; documentation is now streamlined in SKILL.md.\n- Improved workflow and scenario guidance with explicit command references and examples.\n- Refined reporting requirements and formatting for clearer evaluation outputs.\n\nv1.1.1 | 2026-08-17T09:20:46.194Z | auto\n\n- Added explicit instructions that \"save\" only writes the report after user consent, explaining what it does and where the file is created.\n- Clarified that the full report appears in the conversation first, and will never be written automatically.\n- Updated Phase 5 in the workflow to describe the \"save\" command's behavior more clearly.\n- No functional or workflow changes beyond improved user guidance about report saving.\n\nv1.1.0 | 2026-08-17T09:11:06.121Z | auto\n\nrotifer-arena 1.1.0\n\n- Added explicit steps for running `rotifer vg` to report V(g) security grades, clarifying the origin and necessity of this metric.\n- Clarified that all report numbers (F(g), V(g), downloads) must come from concrete commands, never guessed or omitted without explanation.\n- Updated prerequisites and checklist: now requires passing `rotifer doctor`, and clarified installation pathways.\n- Expanded Arena workflow examples to include live ranking commands (`arena watch`) and ecosystem reputation stats (`rotifer compare`, `rotifer stats`).\n- Streamlined the description and invocation instructions; report is now only auto-generated with explicit invocation.\n- Removed obsolete file (`skill-card.md`).\n\nv1.0.3 | 2026-04-15T15:13:06.988Z | user\n\nAdd Prerequisites section with CLI and MCP setup instructions (no hardcoded versions)\n\nv1.0.2 | 2026-04-15T14:02:46.168Z | user\n\nFix untagged code blocks rendering as invisible text on ClawHub\n\nv1.0.1 | 2026-04-15T13:59:34.042Z | user\n\nTranslate to English; fix nested code block rendering\n\nv1.0.0 | 2026-04-15T13:53:05.807Z | user\n\nInitial release: one-click Gene comparison, Arena evaluation, structured reports\n\nArchive index:\n\nArchive v1.2.1: 5 files, 8350 bytes\n\nFiles: clawhub.json (908b), README.md (3199b), skill-card.md (2506b), SKILL.md (9907b), _meta.json (132b)\n\nFile v1.2.1:SKILL.md\n\n---\nname: rotifer-arena\ndescription: >-\n Benchmark Rotifer Genes against each other in the Arena — import from ClawHub / local /\n scratch, compile, match opponents, run Arena evaluation, and produce a Markdown report with\n F(g) fitness and V(g) security grades.\n Invoke explicitly to compare or benchmark Rotifer Genes.\n Do NOT use for general benchmarking, load testing, or comparing anything that is not a\n Rotifer Gene or Agent.\n---\n\n# Rotifer Arena — Gene Comparison & Evaluation\n\n> One Skill covering Gene/Genome/Agent comparison across all scenarios.\n\n## Prerequisites\n\nThis Skill requires the Rotifer CLI:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nOr use the MCP Server for IDE integration:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\n---\n\n## Overview\n\nThis Skill wraps Rotifer Protocol's core value — **objective, quantifiable capability evaluation** — into a one-click workflow. Users don't need to understand Gene, Arena, or F(g) concepts upfront; the Skill introduces them naturally during execution.\n\n**Cross-platform**: This SKILL.md runs in any AI development environment that supports Skills/Agents.\n\n---\n\n## Workflow\n\n### Phase 1: Identify Evaluation Target\n\nUnderstand user intent through conversation and determine the evaluation mode:\n\n| User signal | Mode | Action |\n|-------------|------|--------|\n| \"Evaluate the X skill from ClawHub\" | **ClawHub migration evaluation** | `rotifer wrap --from-clawhub ` |\n| \"Compare my two implementations\" | **Local comparison** | Confirm both Gene names, skip to Phase 3 |\n| \"I have a Skill I want to test\" | **Skill import evaluation** | `rotifer wrap --from-skill ` |\n| \"Help me build a XX scenario\" | **Scenario scaffolding** | Guide Gene creation (`rotifer init` or manual phenotype) |\n\n**If the user doesn't specify a domain**: auto-read from phenotype.json, or guide the user to choose.\n\n### Phase 2: Compile & Verify\n\n```bash\nrotifer compile \n```\n\nOutput guidance based on fidelity result:\n- **Wrapped**: Verification passed, deterministic evaluation mode\n- **Hybrid/Native**: WASM compilation, real sandbox execution mode (requires NAPI binding)\n\n### Phase 3: Automatic Opponent Matching\n\n**Priority order**:\n\n1. **User-specified**: If the user says \"compare X and Y\", use those directly\n2. **Same-domain local search**: Highest-ranked Gene from `rotifer arena list --domain `\n3. **Same-fidelity preferred**: If target is Wrapped, prefer Wrapped opponents (avoid cross-fidelity blowouts)\n4. **No opponent found**: Inform the user, show current cross-domain Arena rankings for reference\n\n**Opponent selection requires user confirmation** — show candidate F(g) and fidelity.\n\n### Phase 4: Arena Submit & Compare\n\n```bash\nrotifer vg \nrotifer vg \nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain \n```\n\n`rotifer vg` is where the report's **V(g)** column comes from — it scans a Gene's\ncode and returns a grade of A–D, or `?` when there is no `src/` to read (a\npure-prompt Skill earns `?`, which is not a failing grade and should be\nreported as \"no code to scan\"). Without this step there is no V(g) to put in\nthe table, and a guessed one is worse than an absent one.\n\nTo watch the ranking settle after both submissions rather than re-running\n`arena list`:\n\n```bash\nrotifer arena watch # live; Ctrl+C to stop\nrotifer arena watch all --interval 10000\n```\n\nIt marks each change as new / improved / dropped / eliminated, which is what\nthe report's \"← new entry\" markers are describing.\n\n**If both Genes are already published to Cloud**, two further commands add\nadoption data the Arena does not measure:\n\n```bash\nrotifer compare # 2–5 published Genes, by reputation and downloads\nrotifer stats # download history: 7d / 30d / 90d / all time\n```\n\nKeep the two kinds of comparison apart in the report. `rotifer compare` ranks\nby **reputation and downloads** — how much the ecosystem uses something. The\nArena run measures **F(g)** — how well it performs. A Gene can lead on one and\ntrail on the other, and saying which is which is the point of the report.\n\nCollect evaluation results for both Genes.\n\n### Phase 5: Generate Evaluation Report\n\n**Output the full report in the conversation** (rendered Markdown).\nAppend at the end: `> Reply \"save\" to write the report to arena-reports/`.\nWhen the user replies \"save\", write to `/arena-reports/--vs-.md`.\n\nSay what \"save\" does when you offer it — it creates a file in their project,\nunder `arena-reports/`, creating that directory if it is missing. The report is\nshown in full in the conversation first, so saving is a choice rather than the\nonly way to read it. Never write it without being asked.\n\n**Report format requirements**:\n\n1. **Title = conclusion**: Use scenario name + both Gene names, not a generic title\n2. **Conclusion first**: Immediately below the title, a `>` blockquote with one-sentence summary of winner and key data\n3. **Concise comparison table**: Only decision-relevant metrics (rank, F(g), V(g), Fidelity, success rate, latency, source), bold the winner. Every number in it must come from a command actually run — F(g) from `arena list`, V(g) from `rotifer vg`, downloads from `rotifer stats`. Leave a cell empty and say why rather than estimating it\n4. **Ranking visualization**: Fixed-width ASCII table showing the full domain ranking, mark new entries with `←`\n5. **Reproduction commands in a standalone bash block**: Pure commands (no comments/output) for easy copy-paste\n6. **No internal references**: No ADR numbers, plan section numbers, or internal version notes\n7. **Minimal metadata**: One line at the bottom with date + CLI version + evaluation mode\n\n**Report structure** (output directly in conversation):\n\n- **Title**: `# Comparison: vs `\n- **Conclusion blockquote**: One sentence — who won, key metric delta, core reason\n- **Comparison table**: Rank, F(g), V(g), Fidelity, Success rate, Latency score, Source\n- **Current ranking**: Full domain leaderboard (ASCII table, `←` marks new entries)\n- **Analysis**: 2–3 paragraphs on fitness gap attribution, security comparison, same-fidelity positioning\n- **Upgrade path**: Table with path / action / expected improvement / effort\n- **Reproduction steps**: 4–5 pure CLI commands\n- **Next steps**: 4 commands with brief descriptions\n- **Footer**: `Generated on YYYY-MM-DD · @rotifer/playground@X.Y.Z · Mode: deterministic estimation`\n\n---\n\n## Scenario Examples\n\n### Example 1: Evaluate a ClawHub Skill's Competitiveness\n\n```text\nUser: Evaluate the web-search skill from ClawHub in the Rotifer ecosystem\n\nSkill execution:\n1. rotifer wrap clawhub-web-search --from-clawhub web-search -d search\n2. rotifer compile clawhub-web-search\n3. Auto-discover same-domain opponent: genesis-web-search (Native, F(g)=0.9470)\n4. rotifer arena submit clawhub-web-search\n5. Generate comparison report\n```\n\n### Example 2: Compare Two Custom Genes\n\n```text\nUser: Compare my particle-brute and particle-spatial — which is better?\n\nSkill execution:\n1. Confirm both Genes exist with phenotype.json\n2. rotifer arena submit particle-brute\n3. rotifer arena submit particle-spatial\n4. rotifer arena list --domain sim.particle\n5. Generate comparison report\n```\n\n### Example 3: Build a Quantitative Scenario\n\n```text\nUser: Help me build a quantitative strategy comparison scenario\n\nSkill execution:\n1. Guide user to define domain (e.g. quant.strategy)\n2. Guide creation of two Gene phenotype.json files (Strategy A vs Strategy B)\n3. If compilable source exists, compile to WASM\n4. rotifer arena submit both Genes\n5. Generate scenario comparison report\n```\n\n---\n\n## Checklist Before Running\n\n- Project has a `rotifer.json` (if not, guide `rotifer init`)\n- CLI is installed: `npm i -g @rotifer/playground`, or invoke it as `npx @rotifer/playground`\n- `rotifer doctor` passes — compiling to Native WASM needs esbuild and javy, and\n without them `rotifer compile` fails in a way that reads like a code error\n- ClawHub imports require network connectivity\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## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `gene` (dev module) | Route here when users need to create a Gene from scratch |\n| `gene` (migration module) | Route here when the report recommends a fidelity upgrade |\n| `gene` (audit module) | Suggest running when the report shows low security scores |\n\n## Constraints\n\n- **No automatic Cloud publishing**: Comparison evaluation is a local operation; Cloud publishing requires explicit user confirmation\n- **Cross-fidelity comparisons need a disclaimer**: The baseFitness gap between Wrapped and Native comes from the scoring model, not actual capability differences\n- **Reports are Markdown format**: Ready for blogs, community sharing, or GitHub Issues\n\nFile v1.2.1:README.md\n\n# Rotifer Arena\n\n> Objective, quantifiable evaluation of Rotifer Genes.\n\nHead-to-head Gene comparison in the Arena of [Rotifer Protocol](https://rotifer.dev).\n\n**Not for general benchmarking.** Everything here operates on Rotifer Genes and\nthe Rotifer CLI — it does not evaluate arbitrary AI capabilities, load-test\nservices, or compare things that are not Genes. A ClawHub Skill can be evaluated\nonly by first importing it *as* a Gene, which is a step you approve.\n\n## What It Does\n\nCompare Rotifer Genes and produce a report you can act on:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub as a Rotifer Gene\" | Imports it as a Gene, compiles, finds the top opponent in its domain, runs the Arena evaluation |\n| \"Compare my two Rotifer Genes\" | Head-to-head F(g) comparison with fitness breakdown |\n| \"Build a Rotifer Gene benchmark for this domain\" | Scaffolds the scenario, creates the Genes, runs evaluation |\n\n**Setup it does need**: a Rotifer workspace (`rotifer.json`), the CLI\n(`npm i -g @rotifer/playground`), and — for Native Genes — the TS→WASM toolchain\nthat `rotifer doctor` checks.\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\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** | Compiled Gene artifacts in the project, and — only when you reply \"save\" — an evaluation report under `arena-reports/`. Nothing outside the project. |\n| **Sends** | Arena submissions and registry queries to the public Rotifer API. Your Gene's source is not uploaded unless you run `rotifer publish` yourself. |\n\nFull detail in [SKILL.md](SKILL.md).\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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-arena\",\n \"version\": \"1.2.1\",\n \"publishedAt\": 1786978469504\n}\n\nFile v1.2.1:skill-card.md\n\n## Description:\n\nRotifer Arena helps developers compare Rotifer Genes by importing or selecting Genes, compiling them, matching opponents, running Arena evaluation, and producing a Markdown report with fitness and security grades.\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 benchmark and compare Rotifer Genes or imported ClawHub Skills as Genes, then review a concise Markdown report with Arena fitness, security grading, rankings, and upgrade guidance.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The workflow runs Rotifer npm packages that are not pinned to exact versions, which can change behavior or supply-chain exposure between runs.\n\nMitigation: Pin exact @rotifer/playground and @rotifer/mcp-server versions where possible, avoid global installation when practical, and review proposed commands before execution.\n\nRisk: Rotifer evaluations may read project Genes, Agent definitions, and workspace files while running local CLI commands and public Arena or registry queries.\n\nMitigation: Run evaluations in a low-privilege project or sandbox when the workspace contains sensitive code or credentials, and publish only after explicit user approval.\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- [ClawHub Skill Page](https://clawhub.ai/xiaoba-dev/skills/rotifer-arena)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown report with comparison tables, ranking summaries, analysis, upgrade guidance, and bash command blocks.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports are shown in the conversation first and are written to arena-reports/ only when the user explicitly asks to save them.]\n\n## Skill Version(s):\n\n1.2.1 (source: server release evidence 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 v1.2.1:clawhub.json\n\n{\n \"name\": \"rotifer-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\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 \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\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, 7619 bytes\n\nFiles: clawhub.json (908b), README.md (1861b), skill-card.md (2305b), SKILL.md (9907b), _meta.json (132b)\n\nFile v1.2.0:SKILL.md\n\n---\nname: rotifer-arena\ndescription: >-\n Benchmark Rotifer Genes against each other in the Arena — import from ClawHub / local /\n scratch, compile, match opponents, run Arena evaluation, and produce a Markdown report with\n F(g) fitness and V(g) security grades.\n Invoke explicitly to compare or benchmark Rotifer Genes.\n Do NOT use for general benchmarking, load testing, or comparing anything that is not a\n Rotifer Gene or Agent.\n---\n\n# Rotifer Arena — Gene Comparison & Evaluation\n\n> One Skill covering Gene/Genome/Agent comparison across all scenarios.\n\n## Prerequisites\n\nThis Skill requires the Rotifer CLI:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nOr use the MCP Server for IDE integration:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\n---\n\n## Overview\n\nThis Skill wraps Rotifer Protocol's core value — **objective, quantifiable capability evaluation** — into a one-click workflow. Users don't need to understand Gene, Arena, or F(g) concepts upfront; the Skill introduces them naturally during execution.\n\n**Cross-platform**: This SKILL.md runs in any AI development environment that supports Skills/Agents.\n\n---\n\n## Workflow\n\n### Phase 1: Identify Evaluation Target\n\nUnderstand user intent through conversation and determine the evaluation mode:\n\n| User signal | Mode | Action |\n|-------------|------|--------|\n| \"Evaluate the X skill from ClawHub\" | **ClawHub migration evaluation** | `rotifer wrap --from-clawhub ` |\n| \"Compare my two implementations\" | **Local comparison** | Confirm both Gene names, skip to Phase 3 |\n| \"I have a Skill I want to test\" | **Skill import evaluation** | `rotifer wrap --from-skill ` |\n| \"Help me build a XX scenario\" | **Scenario scaffolding** | Guide Gene creation (`rotifer init` or manual phenotype) |\n\n**If the user doesn't specify a domain**: auto-read from phenotype.json, or guide the user to choose.\n\n### Phase 2: Compile & Verify\n\n```bash\nrotifer compile \n```\n\nOutput guidance based on fidelity result:\n- **Wrapped**: Verification passed, deterministic evaluation mode\n- **Hybrid/Native**: WASM compilation, real sandbox execution mode (requires NAPI binding)\n\n### Phase 3: Automatic Opponent Matching\n\n**Priority order**:\n\n1. **User-specified**: If the user says \"compare X and Y\", use those directly\n2. **Same-domain local search**: Highest-ranked Gene from `rotifer arena list --domain `\n3. **Same-fidelity preferred**: If target is Wrapped, prefer Wrapped opponents (avoid cross-fidelity blowouts)\n4. **No opponent found**: Inform the user, show current cross-domain Arena rankings for reference\n\n**Opponent selection requires user confirmation** — show candidate F(g) and fidelity.\n\n### Phase 4: Arena Submit & Compare\n\n```bash\nrotifer vg \nrotifer vg \nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain \n```\n\n`rotifer vg` is where the report's **V(g)** column comes from — it scans a Gene's\ncode and returns a grade of A–D, or `?` when there is no `src/` to read (a\npure-prompt Skill earns `?`, which is not a failing grade and should be\nreported as \"no code to scan\"). Without this step there is no V(g) to put in\nthe table, and a guessed one is worse than an absent one.\n\nTo watch the ranking settle after both submissions rather than re-running\n`arena list`:\n\n```bash\nrotifer arena watch # live; Ctrl+C to stop\nrotifer arena watch all --interval 10000\n```\n\nIt marks each change as new / improved / dropped / eliminated, which is what\nthe report's \"← new entry\" markers are describing.\n\n**If both Genes are already published to Cloud**, two further commands add\nadoption data the Arena does not measure:\n\n```bash\nrotifer compare # 2–5 published Genes, by reputation and downloads\nrotifer stats # download history: 7d / 30d / 90d / all time\n```\n\nKeep the two kinds of comparison apart in the report. `rotifer compare` ranks\nby **reputation and downloads** — how much the ecosystem uses something. The\nArena run measures **F(g)** — how well it performs. A Gene can lead on one and\ntrail on the other, and saying which is which is the point of the report.\n\nCollect evaluation results for both Genes.\n\n### Phase 5: Generate Evaluation Report\n\n**Output the full report in the conversation** (rendered Markdown).\nAppend at the end: `> Reply \"save\" to write the report to arena-reports/`.\nWhen the user replies \"save\", write to `/arena-reports/--vs-.md`.\n\nSay what \"save\" does when you offer it — it creates a file in their project,\nunder `arena-reports/`, creating that directory if it is missing. The report is\nshown in full in the conversation first, so saving is a choice rather than the\nonly way to read it. Never write it without being asked.\n\n**Report format requirements**:\n\n1. **Title = conclusion**: Use scenario name + both Gene names, not a generic title\n2. **Conclusion first**: Immediately below the title, a `>` blockquote with one-sentence summary of winner and key data\n3. **Concise comparison table**: Only decision-relevant metrics (rank, F(g), V(g), Fidelity, success rate, latency, source), bold the winner. Every number in it must come from a command actually run — F(g) from `arena list`, V(g) from `rotifer vg`, downloads from `rotifer stats`. Leave a cell empty and say why rather than estimating it\n4. **Ranking visualization**: Fixed-width ASCII table showing the full domain ranking, mark new entries with `←`\n5. **Reproduction commands in a standalone bash block**: Pure commands (no comments/output) for easy copy-paste\n6. **No internal references**: No ADR numbers, plan section numbers, or internal version notes\n7. **Minimal metadata**: One line at the bottom with date + CLI version + evaluation mode\n\n**Report structure** (output directly in conversation):\n\n- **Title**: `# Comparison: vs `\n- **Conclusion blockquote**: One sentence — who won, key metric delta, core reason\n- **Comparison table**: Rank, F(g), V(g), Fidelity, Success rate, Latency score, Source\n- **Current ranking**: Full domain leaderboard (ASCII table, `←` marks new entries)\n- **Analysis**: 2–3 paragraphs on fitness gap attribution, security comparison, same-fidelity positioning\n- **Upgrade path**: Table with path / action / expected improvement / effort\n- **Reproduction steps**: 4–5 pure CLI commands\n- **Next steps**: 4 commands with brief descriptions\n- **Footer**: `Generated on YYYY-MM-DD · @rotifer/playground@X.Y.Z · Mode: deterministic estimation`\n\n---\n\n## Scenario Examples\n\n### Example 1: Evaluate a ClawHub Skill's Competitiveness\n\n```text\nUser: Evaluate the web-search skill from ClawHub in the Rotifer ecosystem\n\nSkill execution:\n1. rotifer wrap clawhub-web-search --from-clawhub web-search -d search\n2. rotifer compile clawhub-web-search\n3. Auto-discover same-domain opponent: genesis-web-search (Native, F(g)=0.9470)\n4. rotifer arena submit clawhub-web-search\n5. Generate comparison report\n```\n\n### Example 2: Compare Two Custom Genes\n\n```text\nUser: Compare my particle-brute and particle-spatial — which is better?\n\nSkill execution:\n1. Confirm both Genes exist with phenotype.json\n2. rotifer arena submit particle-brute\n3. rotifer arena submit particle-spatial\n4. rotifer arena list --domain sim.particle\n5. Generate comparison report\n```\n\n### Example 3: Build a Quantitative Scenario\n\n```text\nUser: Help me build a quantitative strategy comparison scenario\n\nSkill execution:\n1. Guide user to define domain (e.g. quant.strategy)\n2. Guide creation of two Gene phenotype.json files (Strategy A vs Strategy B)\n3. If compilable source exists, compile to WASM\n4. rotifer arena submit both Genes\n5. Generate scenario comparison report\n```\n\n---\n\n## Checklist Before Running\n\n- Project has a `rotifer.json` (if not, guide `rotifer init`)\n- CLI is installed: `npm i -g @rotifer/playground`, or invoke it as `npx @rotifer/playground`\n- `rotifer doctor` passes — compiling to Native WASM needs esbuild and javy, and\n without them `rotifer compile` fails in a way that reads like a code error\n- ClawHub imports require network connectivity\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## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `gene` (dev module) | Route here when users need to create a Gene from scratch |\n| `gene` (migration module) | Route here when the report recommends a fidelity upgrade |\n| `gene` (audit module) | Suggest running when the report shows low security scores |\n\n## Constraints\n\n- **No automatic Cloud publishing**: Comparison evaluation is a local operation; Cloud publishing requires explicit user confirmation\n- **Cross-fidelity comparisons need a disclaimer**: The baseFitness gap between Wrapped and Native comes from the scoring model, not actual capability differences\n- **Reports are Markdown format**: Ready for blogs, community sharing, or GitHub Issues\n\nFile v1.2.0:README.md\n\n# Rotifer Arena\n\n> Objective, quantifiable capability evaluation for AI agents.\n\nOne-click Gene comparison and evaluation powered by [Rotifer Protocol](https://rotifer.dev).\n\n## What It Does\n\nEvaluate any AI capability against the Arena — no setup required:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub\" | Imports, compiles, finds the top opponent, runs Arena battle |\n| \"Compare my two implementations\" | Head-to-head comparison with fitness breakdown |\n| \"Build a quantitative strategy benchmark\" | Scaffolds the scenario, creates Genes, runs evaluation |\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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-arena\",\n \"version\": \"1.2.0\",\n \"publishedAt\": 1786977549906\n}\n\nFile v1.2.0:skill-card.md\n\n## Description:\n\nBenchmark Rotifer Genes in the Arena by importing or selecting Genes, compiling them, submitting comparisons, and producing Markdown reports with F(g) fitness and V(g) security grades.\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 compare Rotifer Genes or Agents with Rotifer Arena workflows and produce decision-ready evaluation reports. It is intended for Rotifer-specific benchmarking, not general load testing or non-Rotifer comparisons.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The workflow may run Rotifer CLI commands, including npm or npx commands, and may use outbound network access for registry or Arena operations.\n\nMitigation: Review commands before execution and install this skill only when Rotifer CLI and Arena network activity are expected.\n\nRisk: The workflow can create or update project-local Rotifer files and saved Arena reports.\n\nMitigation: Require user approval before publishing, overwriting, or saving reports, and keep generated files inside the active project workspace.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/xiaoba-dev/skills/rotifer-arena)\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):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown reports with inline bash command blocks and concise guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports are shown in the conversation first; saving to arena-reports/ requires explicit user confirmation.]\n\n## Skill Version(s):\n\n1.2.0 (source: server release evidence 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 v1.2.0:clawhub.json\n\n{\n \"name\": \"rotifer-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\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 \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\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, 7680 bytes\n\nFiles: clawhub.json (908b), README.md (1861b), skill-card.md (2621b), SKILL.md (9745b), _meta.json (132b)\n\nFile v1.1.1:SKILL.md\n\n---\nname: rotifer-arena\ndescription: >-\n One-click Gene comparison and evaluation for Rotifer Protocol: import from ClawHub / local /\n scratch, auto-compile, match opponents, run Arena battles, and generate Markdown reports.\n Invoke explicitly to compare or benchmark Genes.\n---\n\n# Rotifer Arena — Gene Comparison & Evaluation\n\n> One Skill covering Gene/Genome/Agent comparison across all scenarios.\n\n## Prerequisites\n\nThis Skill requires the Rotifer CLI:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nOr use the MCP Server for IDE integration:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\n---\n\n## Overview\n\nThis Skill wraps Rotifer Protocol's core value — **objective, quantifiable capability evaluation** — into a one-click workflow. Users don't need to understand Gene, Arena, or F(g) concepts upfront; the Skill introduces them naturally during execution.\n\n**Cross-platform**: This SKILL.md runs in any AI development environment that supports Skills/Agents.\n\n---\n\n## Workflow\n\n### Phase 1: Identify Evaluation Target\n\nUnderstand user intent through conversation and determine the evaluation mode:\n\n| User signal | Mode | Action |\n|-------------|------|--------|\n| \"Evaluate the X skill from ClawHub\" | **ClawHub migration evaluation** | `rotifer wrap --from-clawhub ` |\n| \"Compare my two implementations\" | **Local comparison** | Confirm both Gene names, skip to Phase 3 |\n| \"I have a Skill I want to test\" | **Skill import evaluation** | `rotifer wrap --from-skill ` |\n| \"Help me build a XX scenario\" | **Scenario scaffolding** | Guide Gene creation (`rotifer init` or manual phenotype) |\n\n**If the user doesn't specify a domain**: auto-read from phenotype.json, or guide the user to choose.\n\n### Phase 2: Compile & Verify\n\n```bash\nrotifer compile \n```\n\nOutput guidance based on fidelity result:\n- **Wrapped**: Verification passed, deterministic evaluation mode\n- **Hybrid/Native**: WASM compilation, real sandbox execution mode (requires NAPI binding)\n\n### Phase 3: Automatic Opponent Matching\n\n**Priority order**:\n\n1. **User-specified**: If the user says \"compare X and Y\", use those directly\n2. **Same-domain local search**: Highest-ranked Gene from `rotifer arena list --domain `\n3. **Same-fidelity preferred**: If target is Wrapped, prefer Wrapped opponents (avoid cross-fidelity blowouts)\n4. **No opponent found**: Inform the user, show current cross-domain Arena rankings for reference\n\n**Opponent selection requires user confirmation** — show candidate F(g) and fidelity.\n\n### Phase 4: Arena Submit & Compare\n\n```bash\nrotifer vg \nrotifer vg \nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain \n```\n\n`rotifer vg` is where the report's **V(g)** column comes from — it scans a Gene's\ncode and returns a grade of A–D, or `?` when there is no `src/` to read (a\npure-prompt Skill earns `?`, which is not a failing grade and should be\nreported as \"no code to scan\"). Without this step there is no V(g) to put in\nthe table, and a guessed one is worse than an absent one.\n\nTo watch the ranking settle after both submissions rather than re-running\n`arena list`:\n\n```bash\nrotifer arena watch # live; Ctrl+C to stop\nrotifer arena watch all --interval 10000\n```\n\nIt marks each change as new / improved / dropped / eliminated, which is what\nthe report's \"← new entry\" markers are describing.\n\n**If both Genes are already published to Cloud**, two further commands add\nadoption data the Arena does not measure:\n\n```bash\nrotifer compare # 2–5 published Genes, by reputation and downloads\nrotifer stats # download history: 7d / 30d / 90d / all time\n```\n\nKeep the two kinds of comparison apart in the report. `rotifer compare` ranks\nby **reputation and downloads** — how much the ecosystem uses something. The\nArena run measures **F(g)** — how well it performs. A Gene can lead on one and\ntrail on the other, and saying which is which is the point of the report.\n\nCollect evaluation results for both Genes.\n\n### Phase 5: Generate Evaluation Report\n\n**Output the full report in the conversation** (rendered Markdown).\nAppend at the end: `> Reply \"save\" to write the report to arena-reports/`.\nWhen the user replies \"save\", write to `/arena-reports/--vs-.md`.\n\nSay what \"save\" does when you offer it — it creates a file in their project,\nunder `arena-reports/`, creating that directory if it is missing. The report is\nshown in full in the conversation first, so saving is a choice rather than the\nonly way to read it. Never write it without being asked.\n\n**Report format requirements**:\n\n1. **Title = conclusion**: Use scenario name + both Gene names, not a generic title\n2. **Conclusion first**: Immediately below the title, a `>` blockquote with one-sentence summary of winner and key data\n3. **Concise comparison table**: Only decision-relevant metrics (rank, F(g), V(g), Fidelity, success rate, latency, source), bold the winner. Every number in it must come from a command actually run — F(g) from `arena list`, V(g) from `rotifer vg`, downloads from `rotifer stats`. Leave a cell empty and say why rather than estimating it\n4. **Ranking visualization**: Fixed-width ASCII table showing the full domain ranking, mark new entries with `←`\n5. **Reproduction commands in a standalone bash block**: Pure commands (no comments/output) for easy copy-paste\n6. **No internal references**: No ADR numbers, plan section numbers, or internal version notes\n7. **Minimal metadata**: One line at the bottom with date + CLI version + evaluation mode\n\n**Report structure** (output directly in conversation):\n\n- **Title**: `# Comparison: vs `\n- **Conclusion blockquote**: One sentence — who won, key metric delta, core reason\n- **Comparison table**: Rank, F(g), V(g), Fidelity, Success rate, Latency score, Source\n- **Current ranking**: Full domain leaderboard (ASCII table, `←` marks new entries)\n- **Analysis**: 2–3 paragraphs on fitness gap attribution, security comparison, same-fidelity positioning\n- **Upgrade path**: Table with path / action / expected improvement / effort\n- **Reproduction steps**: 4–5 pure CLI commands\n- **Next steps**: 4 commands with brief descriptions\n- **Footer**: `Generated on YYYY-MM-DD · @rotifer/playground@X.Y.Z · Mode: deterministic estimation`\n\n---\n\n## Scenario Examples\n\n### Example 1: Evaluate a ClawHub Skill's Competitiveness\n\n```text\nUser: Evaluate the web-search skill from ClawHub in the Rotifer ecosystem\n\nSkill execution:\n1. rotifer wrap clawhub-web-search --from-clawhub web-search -d search\n2. rotifer compile clawhub-web-search\n3. Auto-discover same-domain opponent: genesis-web-search (Native, F(g)=0.9470)\n4. rotifer arena submit clawhub-web-search\n5. Generate comparison report\n```\n\n### Example 2: Compare Two Custom Genes\n\n```text\nUser: Compare my particle-brute and particle-spatial — which is better?\n\nSkill execution:\n1. Confirm both Genes exist with phenotype.json\n2. rotifer arena submit particle-brute\n3. rotifer arena submit particle-spatial\n4. rotifer arena list --domain sim.particle\n5. Generate comparison report\n```\n\n### Example 3: Build a Quantitative Scenario\n\n```text\nUser: Help me build a quantitative strategy comparison scenario\n\nSkill execution:\n1. Guide user to define domain (e.g. quant.strategy)\n2. Guide creation of two Gene phenotype.json files (Strategy A vs Strategy B)\n3. If compilable source exists, compile to WASM\n4. rotifer arena submit both Genes\n5. Generate scenario comparison report\n```\n\n---\n\n## Checklist Before Running\n\n- Project has a `rotifer.json` (if not, guide `rotifer init`)\n- CLI is installed: `npm i -g @rotifer/playground`, or invoke it as `npx @rotifer/playground`\n- `rotifer doctor` passes — compiling to Native WASM needs esbuild and javy, and\n without them `rotifer compile` fails in a way that reads like a code error\n- ClawHub imports require network connectivity\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## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `gene` (dev module) | Route here when users need to create a Gene from scratch |\n| `gene` (migration module) | Route here when the report recommends a fidelity upgrade |\n| `gene` (audit module) | Suggest running when the report shows low security scores |\n\n## Constraints\n\n- **No automatic Cloud publishing**: Comparison evaluation is a local operation; Cloud publishing requires explicit user confirmation\n- **Cross-fidelity comparisons need a disclaimer**: The baseFitness gap between Wrapped and Native comes from the scoring model, not actual capability differences\n- **Reports are Markdown format**: Ready for blogs, community sharing, or GitHub Issues\n\nFile v1.1.1:README.md\n\n# Rotifer Arena\n\n> Objective, quantifiable capability evaluation for AI agents.\n\nOne-click Gene comparison and evaluation powered by [Rotifer Protocol](https://rotifer.dev).\n\n## What It Does\n\nEvaluate any AI capability against the Arena — no setup required:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub\" | Imports, compiles, finds the top opponent, runs Arena battle |\n| \"Compare my two implementations\" | Head-to-head comparison with fitness breakdown |\n| \"Build a quantitative strategy benchmark\" | Scaffolds the scenario, creates Genes, runs evaluation |\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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-arena\",\n \"version\": \"1.1.1\",\n \"publishedAt\": 1786958446194\n}\n\nFile v1.1.1:skill-card.md\n\n## Description:\n\nRotifer Arena guides agents through Rotifer Protocol Gene comparison and evaluation by importing or creating Genes, compiling them, matching opponents, running Arena battles, and producing Markdown reports.\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 benchmark or compare AI agent capabilities represented as Rotifer Genes, including ClawHub skill imports, local implementations, and scratch scenarios. It helps run Arena evaluations and summarize rankings, fitness scores, security grades, and upgrade paths.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill guides an assistant to run the Rotifer CLI, read project Gene and agent files, write generated Genes or optional reports, and contact the public Rotifer API.\n\nMitigation: Install and use it only when those command, file, and network actions are acceptable for the current project; review proposed commands before execution.\n\nRisk: Private or proprietary Genes may be evaluated through Rotifer CLI Arena workflows.\n\nMitigation: Verify the Rotifer CLI's Arena submission behavior before running evaluations on private or proprietary Genes.\n\nRisk: Generated evaluation reports can be written into the project workspace.\n\nMitigation: Show the full report in the conversation first and write it to arena-reports/ only after explicit user consent.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/xiaoba-dev/skills/rotifer-arena)\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):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown reports with CLI command blocks and concise evaluation guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports are shown in the conversation first; optional save writes Markdown under arena-reports/ after user consent.]\n\n## Skill Version(s):\n\n1.1.1 (source: server release evidence 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-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\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 \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\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, 7065 bytes\n\nFiles: clawhub.json (908b), README.md (1861b), skill-card.md (2421b), SKILL.md (8557b), _meta.json (132b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: rotifer-arena\ndescription: >-\n One-click Gene comparison and evaluation for Rotifer Protocol: import from ClawHub / local /\n scratch, auto-compile, match opponents, run Arena battles, and generate Markdown reports.\n Invoke explicitly to compare or benchmark Genes.\n---\n\n# Rotifer Arena — Gene Comparison & Evaluation\n\n> One Skill covering Gene/Genome/Agent comparison across all scenarios.\n\n## Prerequisites\n\nThis Skill requires the Rotifer CLI:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nOr use the MCP Server for IDE integration:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\n---\n\n## Overview\n\nThis Skill wraps Rotifer Protocol's core value — **objective, quantifiable capability evaluation** — into a one-click workflow. Users don't need to understand Gene, Arena, or F(g) concepts upfront; the Skill introduces them naturally during execution.\n\n**Cross-platform**: This SKILL.md runs in any AI development environment that supports Skills/Agents.\n\n---\n\n## Workflow\n\n### Phase 1: Identify Evaluation Target\n\nUnderstand user intent through conversation and determine the evaluation mode:\n\n| User signal | Mode | Action |\n|-------------|------|--------|\n| \"Evaluate the X skill from ClawHub\" | **ClawHub migration evaluation** | `rotifer wrap --from-clawhub ` |\n| \"Compare my two implementations\" | **Local comparison** | Confirm both Gene names, skip to Phase 3 |\n| \"I have a Skill I want to test\" | **Skill import evaluation** | `rotifer wrap --from-skill ` |\n| \"Help me build a XX scenario\" | **Scenario scaffolding** | Guide Gene creation (`rotifer init` or manual phenotype) |\n\n**If the user doesn't specify a domain**: auto-read from phenotype.json, or guide the user to choose.\n\n### Phase 2: Compile & Verify\n\n```bash\nrotifer compile \n```\n\nOutput guidance based on fidelity result:\n- **Wrapped**: Verification passed, deterministic evaluation mode\n- **Hybrid/Native**: WASM compilation, real sandbox execution mode (requires NAPI binding)\n\n### Phase 3: Automatic Opponent Matching\n\n**Priority order**:\n\n1. **User-specified**: If the user says \"compare X and Y\", use those directly\n2. **Same-domain local search**: Highest-ranked Gene from `rotifer arena list --domain `\n3. **Same-fidelity preferred**: If target is Wrapped, prefer Wrapped opponents (avoid cross-fidelity blowouts)\n4. **No opponent found**: Inform the user, show current cross-domain Arena rankings for reference\n\n**Opponent selection requires user confirmation** — show candidate F(g) and fidelity.\n\n### Phase 4: Arena Submit & Compare\n\n```bash\nrotifer vg \nrotifer vg \nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain \n```\n\n`rotifer vg` is where the report's **V(g)** column comes from — it scans a Gene's\ncode and returns a grade of A–D, or `?` when there is no `src/` to read (a\npure-prompt Skill earns `?`, which is not a failing grade and should be\nreported as \"no code to scan\"). Without this step there is no V(g) to put in\nthe table, and a guessed one is worse than an absent one.\n\nTo watch the ranking settle after both submissions rather than re-running\n`arena list`:\n\n```bash\nrotifer arena watch # live; Ctrl+C to stop\nrotifer arena watch all --interval 10000\n```\n\nIt marks each change as new / improved / dropped / eliminated, which is what\nthe report's \"← new entry\" markers are describing.\n\n**If both Genes are already published to Cloud**, two further commands add\nadoption data the Arena does not measure:\n\n```bash\nrotifer compare # 2–5 published Genes, by reputation and downloads\nrotifer stats # download history: 7d / 30d / 90d / all time\n```\n\nKeep the two kinds of comparison apart in the report. `rotifer compare` ranks\nby **reputation and downloads** — how much the ecosystem uses something. The\nArena run measures **F(g)** — how well it performs. A Gene can lead on one and\ntrail on the other, and saying which is which is the point of the report.\n\nCollect evaluation results for both Genes.\n\n### Phase 5: Generate Evaluation Report\n\n**Output the full report in the conversation** (rendered Markdown).\nAppend at the end: `> Reply \"save\" to write the report to arena-reports/`.\nWhen the user replies \"save\", write to `/arena-reports/--vs-.md`.\n\n**Report format requirements**:\n\n1. **Title = conclusion**: Use scenario name + both Gene names, not a generic title\n2. **Conclusion first**: Immediately below the title, a `>` blockquote with one-sentence summary of winner and key data\n3. **Concise comparison table**: Only decision-relevant metrics (rank, F(g), V(g), Fidelity, success rate, latency, source), bold the winner. Every number in it must come from a command actually run — F(g) from `arena list`, V(g) from `rotifer vg`, downloads from `rotifer stats`. Leave a cell empty and say why rather than estimating it\n4. **Ranking visualization**: Fixed-width ASCII table showing the full domain ranking, mark new entries with `←`\n5. **Reproduction commands in a standalone bash block**: Pure commands (no comments/output) for easy copy-paste\n6. **No internal references**: No ADR numbers, plan section numbers, or internal version notes\n7. **Minimal metadata**: One line at the bottom with date + CLI version + evaluation mode\n\n**Report structure** (output directly in conversation):\n\n- **Title**: `# Comparison: vs `\n- **Conclusion blockquote**: One sentence — who won, key metric delta, core reason\n- **Comparison table**: Rank, F(g), V(g), Fidelity, Success rate, Latency score, Source\n- **Current ranking**: Full domain leaderboard (ASCII table, `←` marks new entries)\n- **Analysis**: 2–3 paragraphs on fitness gap attribution, security comparison, same-fidelity positioning\n- **Upgrade path**: Table with path / action / expected improvement / effort\n- **Reproduction steps**: 4–5 pure CLI commands\n- **Next steps**: 4 commands with brief descriptions\n- **Footer**: `Generated on YYYY-MM-DD · @rotifer/playground@X.Y.Z · Mode: deterministic estimation`\n\n---\n\n## Scenario Examples\n\n### Example 1: Evaluate a ClawHub Skill's Competitiveness\n\n```text\nUser: Evaluate the web-search skill from ClawHub in the Rotifer ecosystem\n\nSkill execution:\n1. rotifer wrap clawhub-web-search --from-clawhub web-search -d search\n2. rotifer compile clawhub-web-search\n3. Auto-discover same-domain opponent: genesis-web-search (Native, F(g)=0.9470)\n4. rotifer arena submit clawhub-web-search\n5. Generate comparison report\n```\n\n### Example 2: Compare Two Custom Genes\n\n```text\nUser: Compare my particle-brute and particle-spatial — which is better?\n\nSkill execution:\n1. Confirm both Genes exist with phenotype.json\n2. rotifer arena submit particle-brute\n3. rotifer arena submit particle-spatial\n4. rotifer arena list --domain sim.particle\n5. Generate comparison report\n```\n\n### Example 3: Build a Quantitative Scenario\n\n```text\nUser: Help me build a quantitative strategy comparison scenario\n\nSkill execution:\n1. Guide user to define domain (e.g. quant.strategy)\n2. Guide creation of two Gene phenotype.json files (Strategy A vs Strategy B)\n3. If compilable source exists, compile to WASM\n4. rotifer arena submit both Genes\n5. Generate scenario comparison report\n```\n\n---\n\n## Checklist Before Running\n\n- Project has a `rotifer.json` (if not, guide `rotifer init`)\n- CLI is installed: `npm i -g @rotifer/playground`, or invoke it as `npx @rotifer/playground`\n- `rotifer doctor` passes — compiling to Native WASM needs esbuild and javy, and\n without them `rotifer compile` fails in a way that reads like a code error\n- ClawHub imports require network connectivity\n\n## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `gene` (dev module) | Route here when users need to create a Gene from scratch |\n| `gene` (migration module) | Route here when the report recommends a fidelity upgrade |\n| `gene` (audit module) | Suggest running when the report shows low security scores |\n\n## Constraints\n\n- **No automatic Cloud publishing**: Comparison evaluation is a local operation; Cloud publishing requires explicit user confirmation\n- **Cross-fidelity comparisons need a disclaimer**: The baseFitness gap between Wrapped and Native comes from the scoring model, not actual capability differences\n- **Reports are Markdown format**: Ready for blogs, community sharing, or GitHub Issues\n\nFile v1.1.0:README.md\n\n# Rotifer Arena\n\n> Objective, quantifiable capability evaluation for AI agents.\n\nOne-click Gene comparison and evaluation powered by [Rotifer Protocol](https://rotifer.dev).\n\n## What It Does\n\nEvaluate any AI capability against the Arena — no setup required:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub\" | Imports, compiles, finds the top opponent, runs Arena battle |\n| \"Compare my two implementations\" | Head-to-head comparison with fitness breakdown |\n| \"Build a quantitative strategy benchmark\" | Scaffolds the scenario, creates Genes, runs evaluation |\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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-arena\",\n \"version\": \"1.1.0\",\n \"publishedAt\": 1786957866121\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:\n\nOne-click Gene comparison and evaluation for Rotifer Protocol: import from ClawHub, local files, or scratch, auto-compile, match opponents, run Arena battles, and generate Markdown reports.\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 compare, benchmark, and evaluate Rotifer Genes or imported ClawHub skills against Arena rankings, fitness scores, security grades, and adoption metrics.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill runs Rotifer CLI commands and may read Gene source or phenotype files during evaluation.\n\nMitigation: Install and invoke it only for intended Rotifer evaluations, review proposed commands before execution, and run it in a workspace appropriate for the Genes or skills being assessed.\n\nRisk: Arena, ClawHub, and adoption-data workflows may require outbound network access.\n\nMitigation: Use it only in environments where ClawHub and Rotifer network interactions are permitted.\n\nRisk: Generated reports can affect technical decisions if metrics are guessed or mixed across sources.\n\nMitigation: Use only metrics produced by concrete Rotifer commands, and leave unavailable values blank with an explanation rather than estimating them.\n\n## Reference(s):\n\n- [Rotifer Arena on ClawHub](https://clawhub.ai/xiaoba-dev/skills/rotifer-arena)\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):** [text, markdown, shell commands, guidance]\n\n**Output Format:** [Markdown reports with command blocks, comparison tables, rankings, and concise guidance]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Writes reports only after the user explicitly asks to save.]\n\n## Skill Version(s):\n\n1.1.0 (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 v1.1.0:clawhub.json\n\n{\n \"name\": \"rotifer-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\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 \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\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, 6386 bytes\n\nFiles: clawhub.json (815b), README.md (1861b), skill-card.md (2747b), SKILL.md (6929b), _meta.json (132b)\n\nFile v1.0.3:SKILL.md\n\n---\nname: rotifer-arena\ndescription: >-\n One-click Gene comparison and evaluation for Rotifer Protocol. Import from ClawHub Skills,\n local files, or build from scratch — automatically compile, match opponents, run Arena\n battles, and generate structured Markdown reports.\n Use when the user mentions \"compare\", \"evaluate\", \"challenge\", \"compete\", \"Arena\",\n \"benchmark\", \"which is better\", \"Gene comparison\", \"Skill comparison\", \"scenario\", \"reference case\".\n---\n\n# Rotifer Arena — Gene Comparison & Evaluation\n\n> One Skill covering Gene/Genome/Agent comparison across all scenarios.\n\n## Prerequisites\n\nThis Skill requires the Rotifer CLI:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nOr use the MCP Server for IDE integration:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\n---\n\n## Overview\n\nThis Skill wraps Rotifer Protocol's core value — **objective, quantifiable capability evaluation** — into a one-click workflow. Users don't need to understand Gene, Arena, or F(g) concepts upfront; the Skill introduces them naturally during execution.\n\n**Cross-platform**: This SKILL.md runs in any AI development environment that supports Skills/Agents.\n\n---\n\n## Workflow\n\n### Phase 1: Identify Evaluation Target\n\nUnderstand user intent through conversation and determine the evaluation mode:\n\n| User signal | Mode | Action |\n|-------------|------|--------|\n| \"Evaluate the X skill from ClawHub\" | **ClawHub migration evaluation** | `rotifer wrap --from-clawhub ` |\n| \"Compare my two implementations\" | **Local comparison** | Confirm both Gene names, skip to Phase 3 |\n| \"I have a Skill I want to test\" | **Skill import evaluation** | `rotifer wrap --from-skill ` |\n| \"Help me build a XX scenario\" | **Scenario scaffolding** | Guide Gene creation (`rotifer init` or manual phenotype) |\n\n**If the user doesn't specify a domain**: auto-read from phenotype.json, or guide the user to choose.\n\n### Phase 2: Compile & Verify\n\n```bash\nrotifer compile \n```\n\nOutput guidance based on fidelity result:\n- **Wrapped**: Verification passed, deterministic evaluation mode\n- **Hybrid/Native**: WASM compilation, real sandbox execution mode (requires NAPI binding)\n\n### Phase 3: Automatic Opponent Matching\n\n**Priority order**:\n\n1. **User-specified**: If the user says \"compare X and Y\", use those directly\n2. **Same-domain local search**: Highest-ranked Gene from `rotifer arena list --domain `\n3. **Same-fidelity preferred**: If target is Wrapped, prefer Wrapped opponents (avoid cross-fidelity blowouts)\n4. **No opponent found**: Inform the user, show current cross-domain Arena rankings for reference\n\n**Opponent selection requires user confirmation** — show candidate F(g) and fidelity.\n\n### Phase 4: Arena Submit & Compare\n\n```bash\nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain \n```\n\nCollect evaluation results for both Genes.\n\n### Phase 5: Generate Evaluation Report\n\n**Output the full report in the conversation** (rendered Markdown).\nAppend at the end: `> Reply \"save\" to write the report to arena-reports/`.\nWhen the user replies \"save\", write to `/arena-reports/--vs-.md`.\n\n**Report format requirements**:\n\n1. **Title = conclusion**: Use scenario name + both Gene names, not a generic title\n2. **Conclusion first**: Immediately below the title, a `>` blockquote with one-sentence summary of winner and key data\n3. **Concise comparison table**: Only decision-relevant metrics (rank, F(g), V(g), Fidelity, success rate, latency, source), bold the winner\n4. **Ranking visualization**: Fixed-width ASCII table showing the full domain ranking, mark new entries with `←`\n5. **Reproduction commands in a standalone bash block**: Pure commands (no comments/output) for easy copy-paste\n6. **No internal references**: No ADR numbers, plan section numbers, or internal version notes\n7. **Minimal metadata**: One line at the bottom with date + CLI version + evaluation mode\n\n**Report structure** (output directly in conversation):\n\n- **Title**: `# Comparison: vs `\n- **Conclusion blockquote**: One sentence — who won, key metric delta, core reason\n- **Comparison table**: Rank, F(g), V(g), Fidelity, Success rate, Latency score, Source\n- **Current ranking**: Full domain leaderboard (ASCII table, `←` marks new entries)\n- **Analysis**: 2–3 paragraphs on fitness gap attribution, security comparison, same-fidelity positioning\n- **Upgrade path**: Table with path / action / expected improvement / effort\n- **Reproduction steps**: 4–5 pure CLI commands\n- **Next steps**: 4 commands with brief descriptions\n- **Footer**: `Generated on YYYY-MM-DD · @rotifer/playground@X.Y.Z · Mode: deterministic estimation`\n\n---\n\n## Scenario Examples\n\n### Example 1: Evaluate a ClawHub Skill's Competitiveness\n\n```text\nUser: Evaluate the web-search skill from ClawHub in the Rotifer ecosystem\n\nSkill execution:\n1. rotifer wrap clawhub-web-search --from-clawhub web-search -d search\n2. rotifer compile clawhub-web-search\n3. Auto-discover same-domain opponent: genesis-web-search (Native, F(g)=0.9470)\n4. rotifer arena submit clawhub-web-search\n5. Generate comparison report\n```\n\n### Example 2: Compare Two Custom Genes\n\n```text\nUser: Compare my particle-brute and particle-spatial — which is better?\n\nSkill execution:\n1. Confirm both Genes exist with phenotype.json\n2. rotifer arena submit particle-brute\n3. rotifer arena submit particle-spatial\n4. rotifer arena list --domain sim.particle\n5. Generate comparison report\n```\n\n### Example 3: Build a Quantitative Scenario\n\n```text\nUser: Help me build a quantitative strategy comparison scenario\n\nSkill execution:\n1. Guide user to define domain (e.g. quant.strategy)\n2. Guide creation of two Gene phenotype.json files (Strategy A vs Strategy B)\n3. If compilable source exists, compile to WASM\n4. rotifer arena submit both Genes\n5. Generate scenario comparison report\n```\n\n---\n\n## Prerequisites\n\n- Project has a `rotifer.json` (if not, guide `rotifer init`)\n- CLI is built (`npm run build` in rotifer-playground)\n- ClawHub imports require network connectivity\n\n## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `gene-dev` | Route here when users need to create a Gene from scratch |\n| `gene-migration` | Route here when the report recommends a fidelity upgrade |\n| `gene-audit` | Suggest running when the report shows low security scores |\n\n## Constraints\n\n- **No automatic Cloud publishing**: Comparison evaluation is a local operation; Cloud publishing requires explicit user confirmation\n- **Cross-fidelity comparisons need a disclaimer**: The baseFitness gap between Wrapped and Native comes from the scoring model, not actual capability differences\n- **Reports are Markdown format**: Ready for blogs, community sharing, or GitHub Issues\n\nFile v1.0.3:README.md\n\n# Rotifer Arena\n\n> Objective, quantifiable capability evaluation for AI agents.\n\nOne-click Gene comparison and evaluation powered by [Rotifer Protocol](https://rotifer.dev).\n\n## What It Does\n\nEvaluate any AI capability against the Arena — no setup required:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub\" | Imports, compiles, finds the top opponent, runs Arena battle |\n| \"Compare my two implementations\" | Head-to-head comparison with fitness breakdown |\n| \"Build a quantitative strategy benchmark\" | Scaffolds the scenario, creates Genes, runs evaluation |\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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-arena\",\n \"version\": \"1.0.3\",\n \"publishedAt\": 1776265986988\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:
\nOne-click Gene comparison and evaluation for Rotifer Protocol that can import from ClawHub Skills, local files, or new scenarios, then compile, match opponents, run Arena battles, and generate structured Markdown reports.
\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 engineers use this skill to compare Rotifer Genes, imported Skills, or custom implementations with Arena scoring, rankings, and reproducible evaluation reports.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill invokes Rotifer CLI or MCP workflows and may submit, import, or evaluate local Skills and Genes.
\nMitigation: Confirm the exact local paths or ClawHub slugs being evaluated before execution, and avoid sensitive code unless the user understands what the Rotifer tooling submits or imports.
\nRisk: Rotifer CLI and MCP packages are external tools executed through npx.
\nMitigation: Treat the Rotifer packages as external code, review the package source or provenance as needed, and run them only in intended Rotifer Gene or Arena workflows.
\nRisk: Cross-fidelity comparisons can reflect scoring-model differences rather than direct capability differences.
\nMitigation: Include the skill's cross-fidelity disclaimer in reports and prefer same-fidelity opponents when comparing Wrapped, Hybrid, or Native Genes.
\n\n\n## Reference(s):
\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](https://github.com/rotifer-protocol/rotifer-playground)
\n- [ClawHub Skill Page](https://clawhub.ai/xiaoba-dev/rotifer-arena)
\n- [Publisher Profile](https://clawhub.ai/user/xiaoba-dev)
\n\n\n## Skill Output:
\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance]
\n**Output Format:** [Markdown reports with tables, fixed-width ranking visualizations, and bash command blocks]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May write saved reports to arena-reports/ after explicit user confirmation.]
\n\n## Skill Version(s):
\n1.0.3 (source: server release metadata and 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-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\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 \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\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, 4908 bytes\n\nFiles: clawhub.json (815b), README.md (1861b), SKILL.md (6653b), _meta.json (132b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: rotifer-arena\ndescription: >-\n One-click Gene comparison and evaluation for Rotifer Protocol. Import from ClawHub Skills,\n local files, or build from scratch — automatically compile, match opponents, run Arena\n battles, and generate structured Markdown reports.\n Use when the user mentions \"compare\", \"evaluate\", \"challenge\", \"compete\", \"Arena\",\n \"benchmark\", \"which is better\", \"Gene comparison\", \"Skill comparison\", \"scenario\", \"reference case\".\n---\n\n# Rotifer Arena — Gene Comparison & Evaluation\n\n> One Skill covering Gene/Genome/Agent comparison across all scenarios.\n\n## Overview\n\nThis Skill wraps Rotifer Protocol's core value — **objective, quantifiable capability evaluation** — into a one-click workflow. Users don't need to understand Gene, Arena, or F(g) concepts upfront; the Skill introduces them naturally during execution.\n\n**Cross-platform**: This SKILL.md runs in any AI development environment that supports Skills/Agents.\n\n---\n\n## Workflow\n\n### Phase 1: Identify Evaluation Target\n\nUnderstand user intent through conversation and determine the evaluation mode:\n\n| User signal | Mode | Action |\n|-------------|------|--------|\n| \"Evaluate the X skill from ClawHub\" | **ClawHub migration evaluation** | `rotifer wrap --from-clawhub ` |\n| \"Compare my two implementations\" | **Local comparison** | Confirm both Gene names, skip to Phase 3 |\n| \"I have a Skill I want to test\" | **Skill import evaluation** | `rotifer wrap --from-skill ` |\n| \"Help me build a XX scenario\" | **Scenario scaffolding** | Guide Gene creation (`rotifer init` or manual phenotype) |\n\n**If the user doesn't specify a domain**: auto-read from phenotype.json, or guide the user to choose.\n\n### Phase 2: Compile & Verify\n\n```bash\nrotifer compile \n```\n\nOutput guidance based on fidelity result:\n- **Wrapped**: Verification passed, deterministic evaluation mode\n- **Hybrid/Native**: WASM compilation, real sandbox execution mode (requires NAPI binding)\n\n### Phase 3: Automatic Opponent Matching\n\n**Priority order**:\n\n1. **User-specified**: If the user says \"compare X and Y\", use those directly\n2. **Same-domain local search**: Highest-ranked Gene from `rotifer arena list --domain `\n3. **Same-fidelity preferred**: If target is Wrapped, prefer Wrapped opponents (avoid cross-fidelity blowouts)\n4. **No opponent found**: Inform the user, show current cross-domain Arena rankings for reference\n\n**Opponent selection requires user confirmation** — show candidate F(g) and fidelity.\n\n### Phase 4: Arena Submit & Compare\n\n```bash\nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain \n```\n\nCollect evaluation results for both Genes.\n\n### Phase 5: Generate Evaluation Report\n\n**Output the full report in the conversation** (rendered Markdown).\nAppend at the end: `> Reply \"save\" to write the report to arena-reports/`.\nWhen the user replies \"save\", write to `/arena-reports/--vs-.md`.\n\n**Report format requirements**:\n\n1. **Title = conclusion**: Use scenario name + both Gene names, not a generic title\n2. **Conclusion first**: Immediately below the title, a `>` blockquote with one-sentence summary of winner and key data\n3. **Concise comparison table**: Only decision-relevant metrics (rank, F(g), V(g), Fidelity, success rate, latency, source), bold the winner\n4. **Ranking visualization**: Fixed-width ASCII table showing the full domain ranking, mark new entries with `←`\n5. **Reproduction commands in a standalone bash block**: Pure commands (no comments/output) for easy copy-paste\n6. **No internal references**: No ADR numbers, plan section numbers, or internal version notes\n7. **Minimal metadata**: One line at the bottom with date + CLI version + evaluation mode\n\n**Report structure** (output directly in conversation):\n\n- **Title**: `# Comparison: vs `\n- **Conclusion blockquote**: One sentence — who won, key metric delta, core reason\n- **Comparison table**: Rank, F(g), V(g), Fidelity, Success rate, Latency score, Source\n- **Current ranking**: Full domain leaderboard (ASCII table, `←` marks new entries)\n- **Analysis**: 2–3 paragraphs on fitness gap attribution, security comparison, same-fidelity positioning\n- **Upgrade path**: Table with path / action / expected improvement / effort\n- **Reproduction steps**: 4–5 pure CLI commands\n- **Next steps**: 4 commands with brief descriptions\n- **Footer**: `Generated on YYYY-MM-DD · @rotifer/playground@X.Y.Z · Mode: deterministic estimation`\n\n---\n\n## Scenario Examples\n\n### Example 1: Evaluate a ClawHub Skill's Competitiveness\n\n```text\nUser: Evaluate the web-search skill from ClawHub in the Rotifer ecosystem\n\nSkill execution:\n1. rotifer wrap clawhub-web-search --from-clawhub web-search -d search\n2. rotifer compile clawhub-web-search\n3. Auto-discover same-domain opponent: genesis-web-search (Native, F(g)=0.9470)\n4. rotifer arena submit clawhub-web-search\n5. Generate comparison report\n```\n\n### Example 2: Compare Two Custom Genes\n\n```text\nUser: Compare my particle-brute and particle-spatial — which is better?\n\nSkill execution:\n1. Confirm both Genes exist with phenotype.json\n2. rotifer arena submit particle-brute\n3. rotifer arena submit particle-spatial\n4. rotifer arena list --domain sim.particle\n5. Generate comparison report\n```\n\n### Example 3: Build a Quantitative Scenario\n\n```text\nUser: Help me build a quantitative strategy comparison scenario\n\nSkill execution:\n1. Guide user to define domain (e.g. quant.strategy)\n2. Guide creation of two Gene phenotype.json files (Strategy A vs Strategy B)\n3. If compilable source exists, compile to WASM\n4. rotifer arena submit both Genes\n5. Generate scenario comparison report\n```\n\n---\n\n## Prerequisites\n\n- Project has a `rotifer.json` (if not, guide `rotifer init`)\n- CLI is built (`npm run build` in rotifer-playground)\n- ClawHub imports require network connectivity\n\n## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `gene-dev` | Route here when users need to create a Gene from scratch |\n| `gene-migration` | Route here when the report recommends a fidelity upgrade |\n| `gene-audit` | Suggest running when the report shows low security scores |\n\n## Constraints\n\n- **No automatic Cloud publishing**: Comparison evaluation is a local operation; Cloud publishing requires explicit user confirmation\n- **Cross-fidelity comparisons need a disclaimer**: The baseFitness gap between Wrapped and Native comes from the scoring model, not actual capability differences\n- **Reports are Markdown format**: Ready for blogs, community sharing, or GitHub Issues\n\nFile v1.0.2:README.md\n\n# Rotifer Arena\n\n> Objective, quantifiable capability evaluation for AI agents.\n\nOne-click Gene comparison and evaluation powered by [Rotifer Protocol](https://rotifer.dev).\n\n## What It Does\n\nEvaluate any AI capability against the Arena — no setup required:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub\" | Imports, compiles, finds the top opponent, runs Arena battle |\n| \"Compare my two implementations\" | Head-to-head comparison with fitness breakdown |\n| \"Build a quantitative strategy benchmark\" | Scaffolds the scenario, creates Genes, runs evaluation |\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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-arena\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1776261766168\n}\n\nFile v1.0.2:clawhub.json\n\n{\n \"name\": \"rotifer-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\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 \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\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, 4905 bytes\n\nFiles: clawhub.json (815b), README.md (1861b), SKILL.md (6641b), _meta.json (132b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: rotifer-arena\ndescription: >-\n One-click Gene comparison and evaluation for Rotifer Protocol. Import from ClawHub Skills,\n local files, or build from scratch — automatically compile, match opponents, run Arena\n battles, and generate structured Markdown reports.\n Use when the user mentions \"compare\", \"evaluate\", \"challenge\", \"compete\", \"Arena\",\n \"benchmark\", \"which is better\", \"Gene comparison\", \"Skill comparison\", \"scenario\", \"reference case\".\n---\n\n# Rotifer Arena — Gene Comparison & Evaluation\n\n> One Skill covering Gene/Genome/Agent comparison across all scenarios.\n\n## Overview\n\nThis Skill wraps Rotifer Protocol's core value — **objective, quantifiable capability evaluation** — into a one-click workflow. Users don't need to understand Gene, Arena, or F(g) concepts upfront; the Skill introduces them naturally during execution.\n\n**Cross-platform**: This SKILL.md runs in any AI development environment that supports Skills/Agents.\n\n---\n\n## Workflow\n\n### Phase 1: Identify Evaluation Target\n\nUnderstand user intent through conversation and determine the evaluation mode:\n\n| User signal | Mode | Action |\n|-------------|------|--------|\n| \"Evaluate the X skill from ClawHub\" | **ClawHub migration evaluation** | `rotifer wrap --from-clawhub ` |\n| \"Compare my two implementations\" | **Local comparison** | Confirm both Gene names, skip to Phase 3 |\n| \"I have a Skill I want to test\" | **Skill import evaluation** | `rotifer wrap --from-skill ` |\n| \"Help me build a XX scenario\" | **Scenario scaffolding** | Guide Gene creation (`rotifer init` or manual phenotype) |\n\n**If the user doesn't specify a domain**: auto-read from phenotype.json, or guide the user to choose.\n\n### Phase 2: Compile & Verify\n\n```bash\nrotifer compile \n```\n\nOutput guidance based on fidelity result:\n- **Wrapped**: Verification passed, deterministic evaluation mode\n- **Hybrid/Native**: WASM compilation, real sandbox execution mode (requires NAPI binding)\n\n### Phase 3: Automatic Opponent Matching\n\n**Priority order**:\n\n1. **User-specified**: If the user says \"compare X and Y\", use those directly\n2. **Same-domain local search**: Highest-ranked Gene from `rotifer arena list --domain `\n3. **Same-fidelity preferred**: If target is Wrapped, prefer Wrapped opponents (avoid cross-fidelity blowouts)\n4. **No opponent found**: Inform the user, show current cross-domain Arena rankings for reference\n\n**Opponent selection requires user confirmation** — show candidate F(g) and fidelity.\n\n### Phase 4: Arena Submit & Compare\n\n```bash\nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain \n```\n\nCollect evaluation results for both Genes.\n\n### Phase 5: Generate Evaluation Report\n\n**Output the full report in the conversation** (rendered Markdown).\nAppend at the end: `> Reply \"save\" to write the report to arena-reports/`.\nWhen the user replies \"save\", write to `/arena-reports/--vs-.md`.\n\n**Report format requirements**:\n\n1. **Title = conclusion**: Use scenario name + both Gene names, not a generic title\n2. **Conclusion first**: Immediately below the title, a `>` blockquote with one-sentence summary of winner and key data\n3. **Concise comparison table**: Only decision-relevant metrics (rank, F(g), V(g), Fidelity, success rate, latency, source), bold the winner\n4. **Ranking visualization**: Fixed-width ASCII table showing the full domain ranking, mark new entries with `←`\n5. **Reproduction commands in a standalone bash block**: Pure commands (no comments/output) for easy copy-paste\n6. **No internal references**: No ADR numbers, plan section numbers, or internal version notes\n7. **Minimal metadata**: One line at the bottom with date + CLI version + evaluation mode\n\n**Report structure** (output directly in conversation):\n\n- **Title**: `# Comparison: vs `\n- **Conclusion blockquote**: One sentence — who won, key metric delta, core reason\n- **Comparison table**: Rank, F(g), V(g), Fidelity, Success rate, Latency score, Source\n- **Current ranking**: Full domain leaderboard (ASCII table, `←` marks new entries)\n- **Analysis**: 2–3 paragraphs on fitness gap attribution, security comparison, same-fidelity positioning\n- **Upgrade path**: Table with path / action / expected improvement / effort\n- **Reproduction steps**: 4–5 pure CLI commands\n- **Next steps**: 4 commands with brief descriptions\n- **Footer**: `Generated on YYYY-MM-DD · @rotifer/playground@X.Y.Z · Mode: deterministic estimation`\n\n---\n\n## Scenario Examples\n\n### Example 1: Evaluate a ClawHub Skill's Competitiveness\n\n```\nUser: Evaluate the web-search skill from ClawHub in the Rotifer ecosystem\n\nSkill execution:\n1. rotifer wrap clawhub-web-search --from-clawhub web-search -d search\n2. rotifer compile clawhub-web-search\n3. Auto-discover same-domain opponent: genesis-web-search (Native, F(g)=0.9470)\n4. rotifer arena submit clawhub-web-search\n5. Generate comparison report\n```\n\n### Example 2: Compare Two Custom Genes\n\n```\nUser: Compare my particle-brute and particle-spatial — which is better?\n\nSkill execution:\n1. Confirm both Genes exist with phenotype.json\n2. rotifer arena submit particle-brute\n3. rotifer arena submit particle-spatial\n4. rotifer arena list --domain sim.particle\n5. Generate comparison report\n```\n\n### Example 3: Build a Quantitative Scenario\n\n```\nUser: Help me build a quantitative strategy comparison scenario\n\nSkill execution:\n1. Guide user to define domain (e.g. quant.strategy)\n2. Guide creation of two Gene phenotype.json files (Strategy A vs Strategy B)\n3. If compilable source exists, compile to WASM\n4. rotifer arena submit both Genes\n5. Generate scenario comparison report\n```\n\n---\n\n## Prerequisites\n\n- Project has a `rotifer.json` (if not, guide `rotifer init`)\n- CLI is built (`npm run build` in rotifer-playground)\n- ClawHub imports require network connectivity\n\n## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `gene-dev` | Route here when users need to create a Gene from scratch |\n| `gene-migration` | Route here when the report recommends a fidelity upgrade |\n| `gene-audit` | Suggest running when the report shows low security scores |\n\n## Constraints\n\n- **No automatic Cloud publishing**: Comparison evaluation is a local operation; Cloud publishing requires explicit user confirmation\n- **Cross-fidelity comparisons need a disclaimer**: The baseFitness gap between Wrapped and Native comes from the scoring model, not actual capability differences\n- **Reports are Markdown format**: Ready for blogs, community sharing, or GitHub Issues\n\nFile v1.0.1:README.md\n\n# Rotifer Arena\n\n> Objective, quantifiable capability evaluation for AI agents.\n\nOne-click Gene comparison and evaluation powered by [Rotifer Protocol](https://rotifer.dev).\n\n## What It Does\n\nEvaluate any AI capability against the Arena — no setup required:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub\" | Imports, compiles, finds the top opponent, runs Arena battle |\n| \"Compare my two implementations\" | Head-to-head comparison with fitness breakdown |\n| \"Build a quantitative strategy benchmark\" | Scaffolds the scenario, creates Genes, runs evaluation |\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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-arena\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1776261574042\n}\n\nFile v1.0.1:clawhub.json\n\n{\n \"name\": \"rotifer-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\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 \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\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, 5162 bytes\n\nFiles: clawhub.json (815b), README.md (1861b), SKILL.md (6516b), _meta.json (132b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: rotifer-arena\ndescription: >-\n Rotifer 生态入口——一键完成 Gene 对比评估全流程。从 ClawHub Skill、本地 Skill、\n 已有 Gene 或从零创建，自动编排 wrap→compile→arena→报告。\n 当用户提到 \"对比\" \"评估\" \"challenge\" \"竞争\" \"Arena 对抗\" \"跑分\" \"benchmark\"\n \"哪个更好\" \"Gene 对比\" \"Skill 对比\" \"场景案例\" \"参考案例\" 时使用。\n---\n\n# Rotifer Arena — Gene 对比评估\n\n> 一个 Skill 覆盖 Gene/Genome/Agent 全场景对比评估。\n\n## 概述\n\n本 Skill 将 Rotifer Protocol 的核心价值——**客观、可量化的能力评估**——封装为一键工作流。\n用户无需预先理解 Gene、Arena、F(g) 等概念，Skill 在执行过程中自然引入。\n\n**跨平台流通**：本 SKILL.md 可在所有支持 Skill/Agent 的 AI 开发环境中运行。\n\n---\n\n## 工作流\n\n### Phase 1：确定评估目标\n\n通过对话理解用户意图，确定评估模式：\n\n| 用户信号 | 模式 | 动作 |\n|---------|------|------|\n| \"评估一下 ClawHub 上的 X\" | **ClawHub 迁移评估** | `rotifer wrap --from-clawhub ` |\n| \"对比我的两个实现\" | **本地对比** | 确认两个 Gene 名称，跳到 Phase 3 |\n| \"我有个 Skill 想测试竞争力\" | **Skill 导入评估** | `rotifer wrap --from-skill ` |\n| \"帮我构建一个 XX 场景\" | **场景脚手架** | 引导创建 Gene（`rotifer init` 或手动 phenotype） |\n\n**如果用户未指定 domain**：从 phenotype.json 自动读取，或引导用户选择。\n\n### Phase 2：编译与验证\n\n```bash\nrotifer compile \n```\n\n根据 fidelity 结果输出提示：\n- **Wrapped**：验证通过，确定性评估模式\n- **Hybrid/Native**：编译 WASM，真实沙箱执行模式（需 NAPI binding）\n\n### Phase 3：自动对手匹配\n\n**策略优先级**：\n\n1. **用户指定**：如果用户说\"对比 X 和 Y\"，直接使用\n2. **同 domain 本地搜索**：`rotifer arena list --domain ` 中排名最高的 Gene\n3. **同 fidelity 优先**：如果目标是 Wrapped，优先找 Wrapped 对手（避免跨 fidelity 碾压）\n4. **无对手时**：提示用户当前 domain 无竞争者，展示当前 Arena 全域排名供参考\n\n**对手选择需向用户确认**，展示候选对手的 F(g) 和 fidelity。\n\n### Phase 4：Arena 提交与对比\n\n```bash\nrotifer arena submit \nrotifer arena submit # 如果对手未曾提交\nrotifer arena list --domain \n```\n\n收集两个 Gene 的评估结果。\n\n### Phase 5：生成评估报告\n\n**在对话中输出完整报告**（渲染 Markdown）。\n报告末尾附提示：`> 回复\"保存\"将报告写入 arena-reports/ 目录`。\n用户回复\"保存\"时，写入 `/arena-reports/--vs-.md`。\n\n**格式要求**：\n\n1. **标题即结论**：用场景名 + 对比双方命名，不用泛化标题\n2. **结论前置**：标题下紧跟 `>` blockquote 一句话总结胜负和关键数据\n3. **对比表精简**：只保留决策相关指标（排名、F(g)、V(g)、Fidelity、成功率、延迟、来源），粗体标注胜出方\n4. **排名可视化**：用等宽 ASCII 表格展示完整 domain 排名，用 `←` 标注本次迁入\n5. **复现命令单独的 bash 代码块**：纯命令（不含注释/输出），方便独立复制\n6. **去内部引用**：不出现 ADR 编号、plan 章节号、内部版本备注\n7. **元数据极简**：底部一行标注日期 + CLI 版本 + 评估模式\n\n**报告模板**（直接在对话中输出）：\n\n```\n# <场景名> 能力对比： vs \n\n> **结论**：一句话总结——谁赢了、关键数据差距、核心原因。\n\n---\n\n## 对比结果\n\n| | | |\n|--|----------|----------|\n| **排名** | #3 / 4 | #1 / 4 |\n| **适应度 F(g)** | 0.6550 | **0.9470** |\n| **安全评分 V(g)** | **0.8050** | 0.7970 |\n| **Fidelity** | Wrapped | Native |\n| **成功率** | 90.5% | **99.7%** |\n| **延迟评分** | 0.8210 | **0.8690** |\n| **来源** | ClawHub @user | Rotifer 内建 |\n\n## 当前排名： domain\n\n(等宽 ASCII 表格，← 标注本次迁入)\n\n## 分析\n\n（2~3 段：适应度差距归因、安全评分对比、同 fidelity 定位）\n\n## 升级路径\n\n（表格：路径 / 做什么 / 预期提升 / 工作量）\n\n---\n\n## 复现步骤\n\n（4~5 行纯命令，无注释）\n\n## 下一步\n\n（4 行命令 + 简短说明）\n\n---\n\n*生成于 YYYY-MM-DD · @rotifer/playground@X.Y.Z · 评估模式：确定性估计*\n\n> 回复\"保存\"将报告写入 arena-reports/ 目录\n```\n\n---\n\n## 场景示例\n\n### 示例 1：评估 ClawHub Skill 竞争力\n\n```\n用户：评估一下 ClawHub 上的 web-search skill 在 Rotifer 生态里的竞争力\n\nSkill 执行：\n1. rotifer wrap clawhub-web-search --from-clawhub web-search -d search\n2. rotifer compile clawhub-web-search\n3. 自动发现同 domain 对手：genesis-web-search (Native, F(g)=0.9470)\n4. rotifer arena submit clawhub-web-search\n5. 生成对比报告\n```\n\n### 示例 2：对比两个自建 Gene\n\n```\n用户：对比一下我的 particle-brute 和 particle-spatial 哪个更好\n\nSkill 执行：\n1. 确认两个 Gene 都存在且有 phenotype.json\n2. rotifer arena submit particle-brute\n3. rotifer arena submit particle-spatial\n4. rotifer arena list --domain sim.particle\n5. 生成对比报告\n```\n\n### 示例 3：构建量化场景\n\n```\n用户：帮我构建一个量化策略对比的场景案例\n\nSkill 执行：\n1. 引导用户定义 domain（如 quant.strategy）\n2. 引导创建两个 Gene 的 phenotype.json（策略 A vs 策略 B）\n3. 如果有可编译源码，编译为 WASM\n4. rotifer arena submit 两个 Gene\n5. 生成场景对比报告\n```\n\n---\n\n## 前置条件\n\n- 项目已有 `rotifer.json`（如无，引导 `rotifer init`）\n- CLI 已构建（`npm run build` in rotifer-playground）\n- 如需 ClawHub 导入，需网络连接\n\n## 与其他 Skill 的关系\n\n| Skill | 关系 |\n|-------|------|\n| `gene-dev` | 当用户需要从零创建 Gene 时，路由到 gene-dev |\n| `gene-migration` | 当报告建议 fidelity 升级时，路由到 gene-migration |\n| `gene-audit` | 当报告发现安全评分偏低时，建议运行 gene-audit |\n\n## 约束\n\n- **不自动发布到 Cloud**：对比评估是本地操作，Cloud 发布需用户显式确认\n- **跨 fidelity 对比需提醒**：Wrapped vs Native 的 baseFitness 差距源于评分模型，非实际能力差距\n- **报告为 Markdown 格式**：可直接用于博客、社区分享、GitHub Issue\n\nFile v1.0.0:README.md\n\n# Rotifer Arena\n\n> Objective, quantifiable capability evaluation for AI agents.\n\nOne-click Gene comparison and evaluation powered by [Rotifer Protocol](https://rotifer.dev).\n\n## What It Does\n\nEvaluate any AI capability against the Arena — no setup required:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub\" | Imports, compiles, finds the top opponent, runs Arena battle |\n| \"Compare my two implementations\" | Head-to-head comparison with fitness breakdown |\n| \"Build a quantitative strategy benchmark\" | Scaffolds the scenario, creates Genes, runs evaluation |\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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 v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-arena\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1776261185807\n}\n\nFile v1.0.0:clawhub.json\n\n{\n \"name\": \"rotifer-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\n \"version\": \"1.0.0\",\n \"author\": \"rotifer-protocol\",\n \"license\": \"Apache-2.0\",\n \"category\": \"developer-tools\",\n \"tags\": [\n \"rotifer\",\n \"ai-agent\",\n \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\n ],\n \"homepage\": \"https://rotifer.dev\",\n \"repository\": \"https://github.com/rotifer-protocol/rotifer-playground\",\n \"permissions\": [],\n \"screenshots\": [],\n \"demo_video\": null\n}","readmeExcerpt":"Skill: rotifer-arena Owner: xiaoba-dev Summary: Benchmark Rotifer Genes against each other in the Arena — import from ClawHub / local / scratch, compile, match opponents, run Arena evaluation, and produce a Markdown report with F(g) fitness and V(g) security grades. Invoke explicitly to compare or benchmark Rotifer Genes. Do NOT use for general benchmarking, load testing, or comparing anything that is not a Rotifer G","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"npx @rotifer/playground --version"},{"language":"json","snippet":"{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}"},{"language":"bash","snippet":"rotifer compile "},{"language":"bash","snippet":"rotifer vg \nrotifer vg \nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain "},{"language":"bash","snippet":"rotifer arena watch # live; Ctrl+C to stop\nrotifer arena watch all --interval 10000"},{"language":"bash","snippet":"rotifer compare # 2–5 published Genes, by reputation and downloads\nrotifer stats # download history: 7d / 30d / 90d / all time"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: rotifer-arena\ndescription: >-\n Benchmark Rotifer Genes against each other in the Arena — import from ClawHub / local /\n scratch, compile, match opponents, run Arena evaluation, and produce a Markdown report with\n F(g) fitness and V(g) security grades.\n Invoke explicitly to compare or benchmark Rotifer Genes.\n Do NOT use for general benchmarking, load testing, or comparing anything that is not a\n Rotifer Gene or Agent.\n---\n\n# Rotifer Arena — Gene Comparison & Evaluation\n\n> One Skill covering Gene/Genome/Agent comparison across all scenarios.\n\n## Prerequisites\n\nThis Skill requires the Rotifer CLI:\n\n```bash\nnpx @rotifer/playground --version\n```\n\nOr use the MCP Server for IDE integration:\n\n```json\n{\n \"mcpServers\": {\n \"rotifer\": {\n \"command\": \"npx\",\n \"args\": [\"@rotifer/mcp-server\"]\n }\n }\n}\n```\n\n---\n\n## Overview\n\nThis Skill wraps Rotifer Protocol's core value — **objective, quantifiable capability evaluation** — into a one-click workflow. Users don't need to understand Gene, Arena, or F(g) concepts upfront; the Skill introduces them naturally during execution.\n\n**Cross-platform**: This SKILL.md runs in any AI development environment that supports Skills/Agents.\n\n---\n\n## Workflow\n\n### Phase 1: Identify Evaluation Target\n\nUnderstand user intent through conversation and determine the evaluation mode:\n\n| User signal | Mode | Action |\n|-------------|------|--------|\n| \"Evaluate the X skill from ClawHub\" | **ClawHub migration evaluation** | `rotifer wrap --from-clawhub ` |\n| \"Compare my two implementations\" | **Local comparison** | Confirm both Gene names, skip to Phase 3 |\n| \"I have a Skill I want to test\" | **Skill import evaluation** | `rotifer wrap --from-skill ` |\n| \"Help me build a XX scenario\" | **Scenario scaffolding** | Guide Gene creation (`rotifer init` or manual phenotype) |\n\n**If the user doesn't specify a domain**: auto-read from phenotype.json, or guide the user to choose.\n\n### Phase 2: Compile & Verify\n\n```bash\nrotifer compile \n```\n\nOutput guidance based on fidelity result:\n- **Wrapped**: Verification passed, deterministic evaluation mode\n- **Hybrid/Native**: WASM compilation, real sandbox execution mode (requires NAPI binding)\n\n### Phase 3: Automatic Opponent Matching\n\n**Priority order**:\n\n1. **User-specified**: If the user says \"compare X and Y\", use those directly\n2. **Same-domain local search**: Highest-ranked Gene from `rotifer arena list --domain `\n3. **Same-fidelity preferred**: If target is Wrapped, prefer Wrapped opponents (avoid cross-fidelity blowouts)\n4. **No opponent found**: Inform the user, show current cross-domain Arena rankings for reference\n\n**Opponent selection requires user confirmation** — show candidate F(g) and fidelity.\n\n### Phase 4: Arena Submit & Compare\n\n```bash\nrotifer vg \nrotifer vg \nrotifer arena submit \nrotifer arena submit \nrotifer arena list --domain \n```\n\n`rotifer vg` is wher"},{"path":"README.md","content":"# Rotifer Arena\n\n> Objective, quantifiable evaluation of Rotifer Genes.\n\nHead-to-head Gene comparison in the Arena of [Rotifer Protocol](https://rotifer.dev).\n\n**Not for general benchmarking.** Everything here operates on Rotifer Genes and\nthe Rotifer CLI — it does not evaluate arbitrary AI capabilities, load-test\nservices, or compare things that are not Genes. A ClawHub Skill can be evaluated\nonly by first importing it *as* a Gene, which is a step you approve.\n\n## What It Does\n\nCompare Rotifer Genes and produce a report you can act on:\n\n| Say this | It does this |\n|----------|-------------|\n| \"Evaluate the web-search skill from ClawHub as a Rotifer Gene\" | Imports it as a Gene, compiles, finds the top opponent in its domain, runs the Arena evaluation |\n| \"Compare my two Rotifer Genes\" | Head-to-head F(g) comparison with fitness breakdown |\n| \"Build a Rotifer Gene benchmark for this domain\" | Scaffolds the scenario, creates the Genes, runs evaluation |\n\n**Setup it does need**: a Rotifer workspace (`rotifer.json`), the CLI\n(`npm i -g @rotifer/playground`), and — for Native Genes — the TS→WASM toolchain\nthat `rotifer doctor` checks.\n\nEvery evaluation produces a structured Markdown report with:\n- **F(g)** fitness scores and ranking\n- **V(g)** security assessment\n- Fidelity comparison (Native vs Hybrid vs Wrapped)\n- Upgrade path recommendations\n\n## Quick Start\n\n```\nCompare my particle-brute and particle-spatial Genes\n```\n\nThe Skill handles the rest: confirms both Genes exist, submits to Arena, and generates a comparison report.\n\n## Workflow\n\n1. **Identify target** — understand what to evaluate\n2. **Compile & verify** — `rotifer compile` the Gene\n3. **Match opponent** — auto-find the strongest competitor in the same domain\n4. **Arena submit** — run the evaluation\n5. **Generate report** — structured Markdown with scores, rankings, and next steps\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** | Compiled Gene artifacts in the project, and — only when you reply \"save\" — an evaluation report under `arena-reports/`. Nothing outside the project. |\n| **Sends** | Arena submissions and registry queries to the public Rotifer API. Your Gene's source is not uploaded unless you run `rotifer publish` yourself. |\n\nFull detail in [SKILL.md](SKILL.md).\n\n## Related Skills\n\n- [rotifer-guide](https://clawhub.ai/skills/rotifer-guide) — Learn Rotifer from scratch\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 Protoco"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7ec5m4jmk1h4jyzfrxaesjk9838ykv\",\n \"slug\": \"rotifer-arena\",\n \"version\": \"1.2.1\",\n \"publishedAt\": 1786978469504\n}"},{"path":"skill-card.md","content":"## Description:\n\nRotifer Arena helps developers compare Rotifer Genes by importing or selecting Genes, compiling them, matching opponents, running Arena evaluation, and producing a Markdown report with fitness and security grades.\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 benchmark and compare Rotifer Genes or imported ClawHub Skills as Genes, then review a concise Markdown report with Arena fitness, security grading, rankings, and upgrade guidance.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The workflow runs Rotifer npm packages that are not pinned to exact versions, which can change behavior or supply-chain exposure between runs.\n\nMitigation: Pin exact @rotifer/playground and @rotifer/mcp-server versions where possible, avoid global installation when practical, and review proposed commands before execution.\n\nRisk: Rotifer evaluations may read project Genes, Agent definitions, and workspace files while running local CLI commands and public Arena or registry queries.\n\nMitigation: Run evaluations in a low-privilege project or sandbox when the workspace contains sensitive code or credentials, and publish only after explicit user approval.\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- [ClawHub Skill Page](https://clawhub.ai/xiaoba-dev/skills/rotifer-arena)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown report with comparison tables, ranking summaries, analysis, upgrade guidance, and bash command blocks.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports are shown in the conversation first and are written to arena-reports/ only when the user explicitly asks to save them.]\n\n## Skill Version(s):\n\n1.2.1 (source: server release evidence 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-arena\",\n \"display_name\": \"Rotifer Arena\",\n \"description\": \"One-click Gene comparison and evaluation. Import from ClawHub Skills, local files, or build from scratch — automatically compile, match opponents, run Arena battles, and generate a full Markdown report with fitness scores.\",\n \"tagline\": \"Objective, quantifiable capability evaluation for AI agents\",\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 \"arena\",\n \"benchmark\",\n \"evaluation\",\n \"comparison\",\n \"gene\",\n \"fitness\"\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":1810,"uniquenessScore":41,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:13:23.315Z","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":"2026-10-11T22:13:23.315Z","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":"2026-10-12T13:11:33.090Z","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"}]}}}