{"id":"8a7a80b2-73bc-4301-ac02-b4ad5c1cea33","entityType":"agent","slug":"clawhub-dietrichgebert-ponytail-audit","name":"ponytail-audit","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dietrichgebert-ponytail-audit","canonicalPath":"/agent/clawhub-dietrichgebert-ponytail-audit","generatedAt":"2026-10-10T08:45:25.042Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T02:17:34.408Z","emptyReason":null},"description":"Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. Skill: ponytail-audit Owner: dietrichgebert Summary: Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:20:51.115Z | auto - Expanded scope: now audits for bugs, security risks, load handling, missing tests, speed, and unnecessary code, not just over-engineering. - Output reorganized: sta","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.8K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17beee6vfcnpy9kq5vh15rzzh88rnca:ponytail-audit","sourceUrl":"https://clawhub.ai/dietrichgebert/ponytail-audit","homepage":"https://clawhub.ai/dietrichgebert/skills/ponytail-audit","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dietrichgebert/ponytail-audit","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dietrichgebert/skills/ponytail-audit","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":65,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. Skill: ponytail-audit Owner: dietric"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T02:17:34.408Z","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":"2026-10-10T02:17:34.408Z","emptyReason":null},"stars":null,"forks":null,"downloads":1780,"packageName":null,"latestVersion":"5.1.0","tractionLabel":"1.8K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T02:17:34.408Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T02:17:34.408Z","lastCrawledAt":"2026-10-10T02:17:34.408Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T02:17:34.408Z","lastVerifiedAt":null,"highlights":[{"version":"5.1.0","createdAt":"2026-10-08T16:20:51.115Z","changelog":"- Expanded scope: now audits for bugs, security risks, load handling, missing tests, speed, and unnecessary code, not just over-engineering. - Output reorganized: starts with a repo summary; findings grouped by priority (must fix, should fix, nice to have); each finding includes what, why, fix, and impact if skipped. - Stronger focus on real-world use: considers expected load, completeness of audit, and requires concrete cases for findings. - More practical: recommends the smallest effective fix; prefers deletion and avoids unnecessary complexity. - Lean audit tags (delete, stdlib, native, reuse, yagni, shrink) now folded into a wider quality review rather than the sole focus. - Removes skill-card.md; documentation now centered in SKILL.md.","fileCount":3,"zipByteSize":4030},{"version":"4.13.0","createdAt":"2026-10-05T18:56:27.153Z","changelog":"- Removed the skill-card.md file for simplified maintenance. - No changes to functionality or documentation content.","fileCount":3,"zipByteSize":2382},{"version":"4.12.0","createdAt":"2026-10-05T03:44:58.072Z","changelog":"ponytrail-audit 4.12.0 changelog - Output findings are now numbered and ranked, making it easier to reference and fix specific issues. - Removed sample file: skill-card.md. - Updated output format in SKILL.md for improved clarity and workflow integration (\"<N>. <tag> <what to cut>. <replacement>. [path]\").","fileCount":3,"zipByteSize":2321},{"version":"4.11.0","createdAt":"2026-10-04T22:55:54.972Z","changelog":"- Added new reuse tag for helpers or patterns already present elsewhere in the repo. - Updated guidance to check for symbol references across the entire codebase before suggesting deletion. - Enhanced Hunt section to include internal helper duplication checks. - Removed skill-card.md file.","fileCount":3,"zipByteSize":2401},{"version":"4.10.3","createdAt":"2026-10-03T02:36:50.583Z","changelog":"- Removed the skill-card.md file. - No changes to core functionality or documentation in SKILL.md. - No new features or breaking changes in this release.","fileCount":3,"zipByteSize":2134},{"version":"4.10.2","createdAt":"2026-10-03T01:32:02.272Z","changelog":"- Removed the skill-card.md file. - No changes made to code or user-facing features.","fileCount":3,"zipByteSize":2265},{"version":"4.10.1","createdAt":"2026-10-02T15:12:24.969Z","changelog":"- Removed the skill-card.md file. - No changes to core functionality or user-facing features.","fileCount":3,"zipByteSize":2170},{"version":"4.9.0","createdAt":"2026-08-07T21:16:04.255Z","changelog":"- Removed skill-card.md file. - No functional changes to the skill logic or documentation.","fileCount":3,"zipByteSize":2418}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17beee6vfcnpy9kq5vh15rzzh88rnca:ponytail-audit","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-dietrichgebert-ponytail-audit/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T08:45:25.041Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-audit/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":"high","updatedAt":"2026-10-10T02:17:34.408Z","emptyReason":null},"readme":"Skill: ponytail-audit\n\nOwner: dietrichgebert\n\nSummary: Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.\n\nTags: latest:5.1.0\n\nVersion history:\n\nv5.1.0 | 2026-10-08T16:20:51.115Z | auto\n\n- Expanded scope: now audits for bugs, security risks, load handling, missing tests, speed, and unnecessary code, not just over-engineering.\n- Output reorganized: starts with a repo summary; findings grouped by priority (must fix, should fix, nice to have); each finding includes what, why, fix, and impact if skipped.\n- Stronger focus on real-world use: considers expected load, completeness of audit, and requires concrete cases for findings.\n- More practical: recommends the smallest effective fix; prefers deletion and avoids unnecessary complexity.\n- Lean audit tags (delete, stdlib, native, reuse, yagni, shrink) now folded into a wider quality review rather than the sole focus.\n- Removes skill-card.md; documentation now centered in SKILL.md.\n\nv4.13.0 | 2026-10-05T18:56:27.153Z | auto\n\n- Removed the skill-card.md file for simplified maintenance.\n- No changes to functionality or documentation content.\n\nv4.12.0 | 2026-10-05T03:44:58.072Z | auto\n\nponytrail-audit 4.12.0 changelog\n\n- Output findings are now numbered and ranked, making it easier to reference and fix specific issues.\n- Removed sample file: skill-card.md.\n- Updated output format in SKILL.md for improved clarity and workflow integration (\"<N>. <tag> <what to cut>. <replacement>. [path]\").\n\nv4.11.0 | 2026-10-04T22:55:54.972Z | auto\n\n- Added new reuse tag for helpers or patterns already present elsewhere in the repo.\n- Updated guidance to check for symbol references across the entire codebase before suggesting deletion.\n- Enhanced Hunt section to include internal helper duplication checks.\n- Removed skill-card.md file.\n\nv4.10.3 | 2026-10-03T02:36:50.583Z | auto\n\n- Removed the skill-card.md file.\n- No changes to core functionality or documentation in SKILL.md.\n- No new features or breaking changes in this release.\n\nv4.10.2 | 2026-10-03T01:32:02.272Z | auto\n\n- Removed the skill-card.md file.  \n- No changes made to code or user-facing features.\n\nv4.10.1 | 2026-10-02T15:12:24.969Z | auto\n\n- Removed the skill-card.md file.\n- No changes to core functionality or user-facing features.\n\nv4.9.0 | 2026-08-07T21:16:04.255Z | auto\n\n- Removed skill-card.md file.\n- No functional changes to the skill logic or documentation.\n\nv4.8.4 | 2026-06-29T05:34:28.188Z | auto\n\n- Removed the skill-card.md file.  \n- No other changes to functionality or documentation.\n\nv4.8.3 | 2026-06-24T02:37:11.217Z | auto\n\n- Removed the skill-card.md file.\n- No changes to functionality or documentation content.\n\nv4.8.1 | 2026-06-23T21:01:46.800Z | auto\n\n- Added a detailed SKILL.md describing ponytail-audit's purpose, tags, methodology, and output format.\n- Clarified that the tool audits entire repos for over-engineering and outputs ranked refactor suggestions.\n- Defined scope boundaries: focused strictly on complexity, not correctness, security, or performance.\n- Provided clear instructions for interpreting output and for reverting to normal mode.\n\nArchive index:\n\nArchive v5.1.0: 3 files, 4030 bytes\n\nFiles: skill-card.md (1705b), SKILL.md (5250b), _meta.json (133b)\n\nFile v5.1.0:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nAudit the whole repo like the senior developer who just inherited it and\nwill be paged when it breaks. Order of importance: correct, safe, holds under\nload, tested, fast, lean. Lean still matters: every extra line must be read,\ntested and fixed later. This is a report the user asked for, so give it in full.\n\n## 1. Map first\n\n- Audit what the user names: a folder, a package, or the whole repo.\n  Nothing named: the whole repo.\n- Read the README, the deploy and build config, the dependency list, the\n  entry points (main, routes, handlers, jobs, CLI commands) and the tests.\n- Find the expected load: one person running a script, or many users and\n  processes at once. Judge scale against that, and say which load you assumed.\n- Trace the main flows end to end: where data comes in, what is stored,\n  what goes out. Read those paths fully: input from users, money, auth,\n  data writes, background jobs, anything shared between processes.\n- Big repo: go deep where a mistake costs the most, not file by file. Say\n  which parts you did not read.\n\n## 2. Look for\n\n1. **Bug:** wrong result, crash, missed edge case (empty, zero, last item,\n   rounding, time zones), callers that disagree with what a function returns,\n   the same rule applied differently in two places.\n2. **Risk:** security holes (injection, weak randomness, secrets in code,\n   missing checks on input from users), data loss (errors swallowed, writes\n   in the wrong order, no transaction).\n3. **Scale:** fine for one user, wrong for many: check-then-write races, the\n   same work done by every process, memory or lists that only grow, a query\n   per item, O(n^2) on big input, per-process state that must be shared.\n4. **Missing test:** risky logic (a branch, a parser, money, security, data\n   writes) with no test that fails when it breaks. One good test, not coverage.\n5. **Speed:** big slowdowns are problems. Small wins (work repeated in a hot\n   loop) are suggestions; some software counts every millisecond.\n6. **Lean:** code that should not exist or should be smaller.\n   - delete: dead code, unused options, flags and config, speculative features\n   - reuse: two helpers doing the same thing (keep one, name the path)\n   - stdlib / native: the standard library or platform already does it;\n     a dependency doing what a few lines or the platform can do\n   - yagni: interface with one implementation, factory with one product,\n     wrapper that only passes calls through\n   - merge: near-copies that must change together\n   - split: one function or class doing several unrelated jobs, so it is\n     hard to read or test. Split by job, never by line count, and never into\n     helpers that exist only to make a function shorter.\n\n## 3. Check before you report\n\n- Every finding needs a concrete case: \"this input or situation leads to this\n  wrong result\". No case, no finding.\n- Before calling code unused, grep the whole tree for it, including tests,\n  fixtures, config, and string or dynamic references.\n- A shortcut marked with a `shortcut:` (or older `ponytail:`) comment that names its limit is a\n  decision, not a finding, unless the expected load already crosses it.\n- Propose the smallest fix that works. Prefer fixes that delete code. Never\n  add layers, frameworks or config the problem does not need.\n- No style taste, no \"consider\", no vague worries.\n\n## 4. Output\n\nVery simple English: short sentences, everyday words. Explain a technical\nterm the first time you use it. The reader may never have seen this code.\n\nStart with `What this repo does:` in two or three sentences, and the load\nyou assumed.\n\nThen the findings in three groups, most important first, skip empty groups:\n- **Must fix:** bug, security, data loss, breaks at the expected load.\n- **Should fix:** risky code without a test, real slowness, duplication, a\n  function that mixes jobs, code that should not exist.\n- **Nice to have:** small speed-ups, shorter forms.\n\nNumber findings across all groups, so the user can say \"fix 2 and 5\". At\nmost 20 findings; if you left smaller ones out, say how many.\nEvery finding has all four parts, each one or two short sentences:\n\n2. **Orders land on the wrong day** (`billing/close_day.py:L40-52`)\n   - **What this is:** At midnight this job closes the day and bills all orders of that day.\n   - **Problem:** It takes \"today\" from the server clock, which runs in UTC. An order placed\n     at 00:30 in Berlin is billed on the day before.\n   - **Fix:** Compute the day once in the shop's time zone:\n     `datetime.now(ZoneInfo(\"Europe/Berlin\")).date()`. One line, nothing else changes.\n   - **If we skip it:** Late orders show the wrong date, and accounting fixes them by hand.\n\nEnd with:\n- `Verdict:` one line: healthy, or what to fix first.\n- `Lean: -<N> lines, -<M> dependencies possible.` when lean findings exist.\n- `Not checked:` the parts you did not read or could not run.\n\nNothing found: `What this repo does:`, then `Healthy. Nothing to fix.` and\none line on what you checked.\n\nOne-shot report, changes no code.\n\nFile v5.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"5.1.0\",\n  \"publishedAt\": 1791476451115\n}\n\nFile v5.1.0:skill-card.md\n\n## Description:\n\nQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to review a repository or named folder for concrete bugs, security and data-loss risks, load issues, missing tests, performance problems, and unnecessary code.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The audit requires access to repository contents, which may include sensitive material.\n\nMitigation: Use it only on repositories the agent is authorized to read, and limit the requested scope when appropriate.\n\nRisk: A read-only review can miss problems in code that was not inspected.\n\nMitigation: Check the report's 'Not checked' section and confirm important findings before making changes.\n\n## Reference(s):\n\n- [Skill homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Guidance]\n\n**Output Format:** [Markdown]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Read-only, prioritized audit report with up to 20 numbered findings, concrete cases and suggested fixes; notes what was not checked.]\n\n## Skill Version(s):\n\n5.1.0 (source: ClawHub 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\nArchive v4.13.0: 3 files, 2382 bytes\n\nFiles: skill-card.md (1748b), SKILL.md (1761b), _meta.json (134b)\n\nFile v4.13.0:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `reuse:` equivalent helper, util, or pattern already in this repo. Name the path.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib, helpers duplicating an\nequivalent that already lives in this repo.\nBefore emitting `delete:`, grep the whole tree for the symbol, including tests,\nfixtures and string or dynamic references.\n\n## Output\n\nOne line per finding, numbered and ranked: `<N>. <tag> <what to cut>. <replacement>. [path]`,\nso the user can say \"fix 2 and 5\".\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.13.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.13.0\",\n  \"publishedAt\": 1791226587153\n}\n\nFile v4.13.0:skill-card.md\n\n## Description:\n\nAudits a repository for over-engineering and ranks opportunities to delete, simplify, or replace code with standard-library or native features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this read-only, repo-wide audit to prioritize unnecessary code, dependencies, and abstractions for possible removal or simplification.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A full-repository audit may expose code structure in the agent conversation.\n\nMitigation: Run it only in conversations where sharing repository details is appropriate.\n\nRisk: Simplification suggestions may overlook important uses or lead to unsuitable changes.\n\nMitigation: Review each proposal and check references before making changes; the skill itself does not edit files.\n\n## Reference(s):\n\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Guidance]\n\n**Output Format:** [Numbered, ranked plain-text findings with tags, replacement suggestions, paths, and an estimated net reduction]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Read-only recommendations; no files are changed. Reports 'Lean already. Ship.' if no cuts are found.]\n\n## Skill Version(s):\n\n4.13.0 (source: server-resolved ClawHub release)\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\nArchive v4.12.0: 3 files, 2321 bytes\n\nFiles: skill-card.md (1684b), SKILL.md (1761b), _meta.json (134b)\n\nFile v4.12.0:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `reuse:` equivalent helper, util, or pattern already in this repo. Name the path.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib, helpers duplicating an\nequivalent that already lives in this repo.\nBefore emitting `delete:`, grep the whole tree for the symbol, including tests,\nfixtures and string or dynamic references.\n\n## Output\n\nOne line per finding, numbered and ranked: `<N>. <tag> <what to cut>. <replacement>. [path]`,\nso the user can say \"fix 2 and 5\".\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.12.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.12.0\",\n  \"publishedAt\": 1791171898072\n}\n\nFile v4.12.0:skill-card.md\n\n## Description:\n\nAudits a whole repository for over-engineering and ranks opportunities to delete, simplify, or replace code with standard-library or native features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers use this skill to identify and prioritize repo-wide complexity reductions without modifying files. It produces a read-only list of possible deletions, replacements, and simplifications.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Suggested deletions could remove code used through dynamic references or tests.\n\nMitigation: Review proposed deletions and check references across the repository before applying changes.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dietrichgebert/skills/ponytail-audit)\n- [Skill homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance]\n\n**Output Format:** [Numbered, ranked one-line findings with tags, suggested replacements, and file paths; a final estimate of lines and dependencies removable, or a no-findings message.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Read-only recommendations; no files are changed.]\n\n## Skill Version(s):\n\n4.12.0 (source: ClawHub release evidence)\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\nArchive v4.11.0: 3 files, 2401 bytes\n\nFiles: skill-card.md (1894b), SKILL.md (1708b), _meta.json (134b)\n\nFile v4.11.0:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `reuse:` equivalent helper, util, or pattern already in this repo. Name the path.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib, helpers duplicating an\nequivalent that already lives in this repo.\nBefore emitting `delete:`, grep the whole tree for the symbol, including tests,\nfixtures and string or dynamic references.\n\n## Output\n\nOne line per finding, ranked: `<tag> <what to cut>. <replacement>. [path]`.\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.11.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.11.0\",\n  \"publishedAt\": 1791154554972\n}\n\nFile v4.11.0:skill-card.md\n\n## Description:\n\nAudits an entire repository for over-engineering and ranks opportunities to delete or simplify code or replace it with standard-library or native features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers use this read-only audit to find and prioritize unnecessary complexity across a repository, including dead code, duplicated helpers, and avoidable dependencies.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A whole-repository audit may expose secrets or irrelevant generated and vendor content to the agent.\n\nMitigation: Exclude sensitive, generated, and vendor directories from the material shared for review.\n\nRisk: Simplification suggestions may overlook references or remove behavior that is still needed.\n\nMitigation: Review each proposal and check references throughout the repository before changing code; the skill does not apply edits.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dietrichgebert/skills/ponytail-audit)\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Guidance]\n\n**Output Format:** [Plain-text ranked findings, one per line]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Each finding has a tag, proposed cut, replacement, and path; ends with estimated line and dependency reductions, or a no-findings message. No changes are applied.]\n\n## Skill Version(s):\n\n4.11.0 (source: ClawHub 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\nArchive v4.10.3: 3 files, 2134 bytes\n\nFiles: skill-card.md (1608b), SKILL.md (1434b), _meta.json (134b)\n\nFile v4.10.3:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib.\n\n## Output\n\nOne line per finding, ranked: `<tag> <what to cut>. <replacement>. [path]`.\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.10.3:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.10.3\",\n  \"publishedAt\": 1790995010583\n}\n\nFile v4.10.3:skill-card.md\n\n## Description:\n\nAudit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to identify and rank unnecessary complexity across a repository, including dead code, redundant abstractions, and opportunities to use standard-library or native features.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A complexity-only audit may miss security, correctness, or performance problems.\n\nMitigation: Run separate security, correctness, and performance reviews when those concerns matter.\n\n## Reference(s):\n\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n- [ClawHub skill listing](https://clawhub.ai/dietrichgebert/skills/ponytail-audit)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Guidance]\n\n**Output Format:** [Plain text]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Ranked one-line findings with paths and suggested simplifications, ending with estimated line and dependency reductions; no files are changed.]\n\n## Skill Version(s):\n\n4.10.3 (source: ClawHub 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\nArchive v4.10.2: 3 files, 2265 bytes\n\nFiles: skill-card.md (1935b), SKILL.md (1434b), _meta.json (134b)\n\nFile v4.10.2:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib.\n\n## Output\n\nOne line per finding, ranked: `<tag> <what to cut>. <replacement>. [path]`.\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.10.2:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.10.2\",\n  \"publishedAt\": 1790991122272\n}\n\nFile v4.10.2:skill-card.md\n\n## Description:\n\nAudit the whole repo for over-engineering and rank what to delete, simplify, or replace with standard-library or native features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to review an entire repository for unnecessary complexity and prioritize opportunities to remove code, dependencies, or abstractions. It only lists recommendations and does not edit files.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Repository-wide review exposes source files to the agent beyond a single diff.\n\nMitigation: Use only when repository-wide access is appropriate and limit the agent's access to repositories it is authorized to read.\n\nRisk: Simplification suggestions do not assess correctness, security, or performance.\n\nMitigation: Review recommendations before applying them and use separate correctness and security reviews where needed.\n\n## Reference(s):\n\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n- [ClawHub skill release](https://clawhub.ai/dietrichgebert/skills/ponytail-audit)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Guidance]\n\n**Output Format:** [Ranked, one-line findings with a potential lines-and-dependencies reduction summary, or a brief no-findings message]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Each finding names a simplification category, a proposed replacement, and a file path; no files are modified.]\n\n## Skill Version(s):\n\n4.10.2 (source: ClawHub 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\nArchive v4.10.1: 3 files, 2170 bytes\n\nFiles: skill-card.md (1690b), SKILL.md (1434b), _meta.json (134b)\n\nFile v4.10.1:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib.\n\n## Output\n\nOne line per finding, ranked: `<tag> <what to cut>. <replacement>. [path]`.\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.10.1:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.10.1\",\n  \"publishedAt\": 1790953944969\n}\n\nFile v4.10.1:skill-card.md\n\n## Description:\n\nAudit the whole repo for over-engineering and rank opportunities to delete, simplify, or replace code with standard-library or native features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to review an entire repository for avoidable complexity and receive ranked, read-only simplification suggestions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The audit reads the whole repository, including files beyond a specific change.\n\nMitigation: Use it only on repositories the agent is authorized to read.\n\nRisk: Simplification recommendations may not fit the project's requirements.\n\nMitigation: Review findings before making changes; the skill only lists suggestions and does not edit files.\n\n## Reference(s):\n\n- [Ponytail homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Guidance]\n\n**Output Format:** [Plain-text ranked findings]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [One tagged finding per line with a suggested replacement and path, followed by estimated line and dependency reductions; reports when nothing needs cutting. Does not edit files.]\n\n## Skill Version(s):\n\n4.10.1 (source: ClawHub 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\nArchive v4.9.0: 3 files, 2418 bytes\n\nFiles: skill-card.md (2366b), SKILL.md (1434b), _meta.json (133b)\n\nFile v4.9.0:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib.\n\n## Output\n\nOne line per finding, ranked: `<tag> <what to cut>. <replacement>. [path]`.\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.9.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.9.0\",\n  \"publishedAt\": 1786137364255\n}\n\nFile v4.9.0:skill-card.md\n\n## Description:\n\nAudits an entire repository for over-engineering and returns a ranked list of code, dependencies, and abstractions to delete, simplify, or replace with standard library or native features.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and repository maintainers use this skill to inspect a codebase for unnecessary complexity and receive a prioritized, line-oriented simplification audit. It is intended for broad repository review focused on over-engineering, not correctness, security, or performance assessment.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill directs an agent to inspect the current repository broadly, which may expose sensitive project context to the agent session.\n\nMitigation: Use it only in repositories where broad agent review is acceptable, and review repository access expectations before invoking it.\n\nRisk: Simplification recommendations may remove abstractions or dependencies that still serve unstated product, compatibility, or maintenance needs.\n\nMitigation: Treat findings as proposals and review each suggested deletion or replacement before applying changes.\n\nRisk: The skill explicitly excludes correctness, security, and performance review, so users may miss issues outside over-engineering scope.\n\nMitigation: Route correctness, security, and performance concerns to separate review passes.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dietrichgebert/skills/ponytail-audit)\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [text, guidance]\n\n**Output Format:** [Plain text with ranked, line-oriented audit findings]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Lists findings only and applies no changes; when findings exist, the output ends with a net line and dependency reduction estimate.]\n\n## Skill Version(s):\n\n4.9.0 (source: server release evidence)\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\nArchive v4.8.4: 3 files, 2257 bytes\n\nFiles: skill-card.md (2082b), SKILL.md (1434b), _meta.json (133b)\n\nFile v4.8.4:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib.\n\n## Output\n\nOne line per finding, ranked: `<tag> <what to cut>. <replacement>. [path]`.\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.8.4:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.8.4\",\n  \"publishedAt\": 1782711268188\n}\n\nFile v4.8.4:skill-card.md\n\n## Description: <br>\nAudits an entire repository for over-engineering and returns a ranked list of what to delete, simplify, or replace with standard library or native features. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineers use this skill to inspect a repository for unnecessary abstraction, dead flexibility, hand-rolled standard library behavior, and other simplification opportunities. It reports ranked findings only and does not apply changes. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill needs broad read access to inspect a repository for simplification opportunities. <br>\nMitigation: Use it only in workspaces where repository-wide read access is appropriate, and review the reported findings before acting on them. <br>\nRisk: The skill explicitly excludes correctness, security, and performance review from its scope. <br>\nMitigation: Route correctness bugs, security issues, and performance concerns to a normal review pass instead of relying on this audit. <br>\n\n\n## Reference(s): <br>\n- [Project homepage](https://github.com/DietrichGebert/ponytail) <br>\n- [ClawHub skill page](https://clawhub.ai/dietrichgebert/skills/ponytail-audit) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, guidance] <br>\n**Output Format:** [Markdown text with one ranked finding per line and a final net reduction summary] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Reports simplification findings only; it does not edit files.] <br>\n\n## Skill Version(s): <br>\n4.8.4 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v4.8.3: 3 files, 2276 bytes\n\nFiles: skill-card.md (2096b), SKILL.md (1434b), _meta.json (133b)\n\nFile v4.8.3:SKILL.md\n\n---\nname: ponytail-audit\ndescription: \"Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank\nfindings biggest cut first.\n\n## Tags\n\nSame as ponytail-review:\n\n- `delete:` dead code, unused flexibility, speculative feature. Replacement: nothing.\n- `stdlib:` hand-rolled thing the standard library ships. Name the function.\n- `native:` dependency or code doing what the platform already does. Name the feature.\n- `yagni:` abstraction with one implementation, config nobody sets, layer with one caller.\n- `shrink:` same logic, fewer lines. Show the shorter form.\n\n## Hunt\n\nDeps the stdlib or platform already ships, single-implementation interfaces,\nfactories with one product, wrappers that only delegate, files exporting one\nthing, dead flags and config, hand-rolled stdlib.\n\n## Output\n\nOne line per finding, ranked: `<tag> <what to cut>. <replacement>. [path]`.\nEnd with `net: -<N> lines, -<M> deps possible.` Nothing to cut: `Lean already. Ship.`\n\n## Boundaries\n\nScope: over-engineering and complexity only. Correctness bugs, security holes,\nand performance are explicitly out of scope. Route them to a normal review\npass. Lists findings, applies nothing. One-shot.\n\"stop ponytail-audit\" or \"normal mode\" to revert.\n\nFile v4.8.3:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"4.8.3\",\n  \"publishedAt\": 1782268631217\n}\n\nFile v4.8.3:skill-card.md\n\n## Description: <br>\nAudit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and maintainers use this skill to review a repository for unnecessary complexity and get ranked proposals for what to delete, simplify, or replace with standard library or native platform features. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill produces deletion and simplification proposals that could remove useful abstractions if applied without review. <br>\nMitigation: Treat findings as review input and validate proposed removals with maintainers, tests, and normal code review before changing the repository. <br>\nRisk: Security evidence says installation appears acceptable but notes that users should still review the actual skill contents and permissions before installing. <br>\nMitigation: Inspect the installed skill contents and requested permissions before use, especially in sensitive repositories. <br>\n\n\n## Reference(s): <br>\n- [Ponytail repository](https://github.com/DietrichGebert/ponytail) <br>\n- [ClawHub skill page](https://clawhub.ai/dietrichgebert/skills/ponytail-audit) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance] <br>\n**Output Format:** [Ranked Markdown findings list] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [One finding per line, ending with a net line-count and dependency-reduction estimate when cuts are found.] <br>\n\n## Skill Version(s): <br>\n4.8.3 (source: release evidence) <br>\n\n## Ethical Considerations: <br>\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. <br>","readmeExcerpt":"Skill: ponytail-audit Owner: dietrichgebert Summary: Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:20:51.115Z | auto - Expanded scope: now audits for bugs, security risks, load handling, missing tests, speed, and unnecessary code, not just over-engineering. - Output reorganized: sta","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: ponytail-audit\ndescription: \"Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nAudit the whole repo like the senior developer who just inherited it and\nwill be paged when it breaks. Order of importance: correct, safe, holds under\nload, tested, fast, lean. Lean still matters: every extra line must be read,\ntested and fixed later. This is a report the user asked for, so give it in full.\n\n## 1. Map first\n\n- Audit what the user names: a folder, a package, or the whole repo.\n  Nothing named: the whole repo.\n- Read the README, the deploy and build config, the dependency list, the\n  entry points (main, routes, handlers, jobs, CLI commands) and the tests.\n- Find the expected load: one person running a script, or many users and\n  processes at once. Judge scale against that, and say which load you assumed.\n- Trace the main flows end to end: where data comes in, what is stored,\n  what goes out. Read those paths fully: input from users, money, auth,\n  data writes, background jobs, anything shared between processes.\n- Big repo: go deep where a mistake costs the most, not file by file. Say\n  which parts you did not read.\n\n## 2. Look for\n\n1. **Bug:** wrong result, crash, missed edge case (empty, zero, last item,\n   rounding, time zones), callers that disagree with what a function returns,\n   the same rule applied differently in two places.\n2. **Risk:** security holes (injection, weak randomness, secrets in code,\n   missing checks on input from users), data loss (errors swallowed, writes\n   in the wrong order, no transaction).\n3. **Scale:** fine for one user, wrong for many: check-then-write races, the\n   same work done by every process, memory or lists that only grow, a query\n   per item, O(n^2) on big input, per-process state that must be shared.\n4. **Missing test:** risky logic (a branch, a parser, money, security, data\n   writes) with no test that fails when it breaks. One good test, not coverage.\n5. **Speed:** big slowdowns are problems. Small wins (work repeated in a hot\n   loop) are suggestions; some software counts every millisecond.\n6. **Lean:** code that should not exist or should be smaller.\n   - delete: dead code, unused options, flags and config, speculative features\n   - reuse: two helpers doing the same thing (keep one, name the path)\n   - stdlib / native: the standard library or platform already does it;\n     a dependency doing what a few lines or the platform can do\n   - yagni: interface with one implementation, factory with one product,\n     wrapper that only passes calls through\n   - merge: near-copies that must change together\n   - split: one function or class doing several unrelated jobs, so it is\n     hard to read or test. Split by job, never by line count, and never into\n     helpers that exist only to make a function shorter.\n\n## 3. Check before you report\n\n- Every finding needs a conc"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-audit\",\n  \"version\": \"5.1.0\",\n  \"publishedAt\": 1791476451115\n}"},{"path":"skill-card.md","content":"## Description:\n\nQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dietrichgebert](https://clawhub.ai/user/dietrichgebert)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to review a repository or named folder for concrete bugs, security and data-loss risks, load issues, missing tests, performance problems, and unnecessary code.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The audit requires access to repository contents, which may include sensitive material.\n\nMitigation: Use it only on repositories the agent is authorized to read, and limit the requested scope when appropriate.\n\nRisk: A read-only review can miss problems in code that was not inspected.\n\nMitigation: Check the report's 'Not checked' section and confirm important findings before making changes.\n\n## Reference(s):\n\n- [Skill homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Guidance]\n\n**Output Format:** [Markdown]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Read-only, prioritized audit report with up to 20 numbered findings, concrete cases and suggested fixes; notes what was not checked.]\n\n## Skill Version(s):\n\n5.1.0 (source: ClawHub 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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. Skill: ponytail-audit Owner: dietrichgebert Summary: Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:20:51.115Z | auto - Expanded scope: now audits for bugs, security risks, load handling, missing tests, speed, and unnecessary code, not just over-engineering. - Output reorganized: sta","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1364,"uniquenessScore":51,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T02:17:34.408Z","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":"2026-10-10T02:17:34.408Z","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":"2026-10-10T08:45:25.042Z","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"}]}}}