{"id":"5684810e-0121-479f-baef-6a1907b537ee","entityType":"agent","slug":"clawhub-dietrichgebert-ponytail-review","name":"ponytail-review","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dietrichgebert-ponytail-review","canonicalPath":"/agent/clawhub-dietrichgebert-ponytail-review","generatedAt":"2026-10-10T06:44:29.347Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T01:00:50.779Z","emptyReason":null},"description":"Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it. Skill: ponytail-review Owner: dietrichgebert Summary: Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:21:31.860Z | auto This release expands the skill from lean/over-engineering review to a full quality review including bugs, tests, security, scale, and perform","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-review","sourceUrl":"https://clawhub.ai/dietrichgebert/ponytail-review","homepage":"https://clawhub.ai/dietrichgebert/skills/ponytail-review","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dietrichgebert/ponytail-review","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dietrichgebert/skills/ponytail-review","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":65,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it. Skill: ponyt"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T01:00:50.779Z","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":"2026-10-10T01:00:50.779Z","emptyReason":null},"stars":null,"forks":null,"downloads":1820,"packageName":null,"latestVersion":"5.1.0","tractionLabel":"1.8K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T01:00:50.779Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T01:00:50.779Z","lastCrawledAt":"2026-10-10T01:00:50.779Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T01:00:50.779Z","lastVerifiedAt":null,"highlights":[{"version":"5.1.0","createdAt":"2026-10-08T16:21:31.860Z","changelog":"This release expands the skill from lean/over-engineering review to a full quality review including bugs, tests, security, scale, and performance. - Broadens scope to review for bugs, security, scalability, missing tests, and slowness, while still flagging unnecessary code. - Adds detailed review process: read diff, follow code flows, check real-world use and expected load. - Outputs findings in clear groups (Must fix, Should fix, Nice to have), with concrete problems and fixes for each. - Makes reporting style simple and actionable, with clear explanations and numbering across all findings. - Updates boundaries: no style/taste issues, only real technical or operational problems. - Removes previous card/summary file (skill-card.md); now SKILL.md gives full details.","fileCount":3,"zipByteSize":3760},{"version":"4.13.0","createdAt":"2026-10-05T18:58:27.270Z","changelog":"- Removed the documentation file skill-card.md. - No changes to core functionality or review guidelines.","fileCount":3,"zipByteSize":2587},{"version":"4.12.0","createdAt":"2026-10-05T03:45:38.042Z","changelog":"- Findings are now numbered for easier referencing and action, e.g., `1. L12-38: ...` - Example output updated to illustrate the new numbering scheme. - Formatting section updated to specify report-wide sequential numbering. - Removed file: skill-card.md.","fileCount":3,"zipByteSize":2744},{"version":"4.11.0","createdAt":"2026-10-04T22:56:33.304Z","changelog":"- Added new tag: reuse (for flagging duplicated helpers/utils within the repo). - Updated examples and tags section in SKILL.md to document the new reuse tag and provide relevant examples. - Removed the file: skill-card.md.","fileCount":3,"zipByteSize":2584},{"version":"4.10.3","createdAt":"2026-10-03T02:37:25.796Z","changelog":"- Removed the skill-card.md file. - No changes to the main skill logic or documentation content.","fileCount":3,"zipByteSize":2451},{"version":"4.10.2","createdAt":"2026-10-03T01:32:44.235Z","changelog":"- Removed the file skill-card.md. - No changes to functionality or documentation in SKILL.md.","fileCount":3,"zipByteSize":2439},{"version":"4.10.1","createdAt":"2026-10-02T15:13:03.202Z","changelog":"- Removed the skill-card.md file. - No changes made to core logic or documentation in SKILL.md.","fileCount":3,"zipByteSize":2511},{"version":"4.9.0","createdAt":"2026-08-07T21:17:04.695Z","changelog":"- Removed the skill-card.md file. - No changes to core functionality or SKILL.md content.","fileCount":3,"zipByteSize":2626}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17beee6vfcnpy9kq5vh15rzzh88rnca:ponytail-review","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-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-review/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-review/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-review/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-review/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T06:44:29.346Z"}},"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-review/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dietrichgebert-ponytail-review/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":"2026-10-10T01:00:50.779Z","emptyReason":null},"readme":"Skill: ponytail-review\n\nOwner: dietrichgebert\n\nSummary: Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it.\n\nTags: latest:5.1.0\n\nVersion history:\n\nv5.1.0 | 2026-10-08T16:21:31.860Z | auto\n\nThis release expands the skill from lean/over-engineering review to a full quality review including bugs, tests, security, scale, and performance.\n\n- Broadens scope to review for bugs, security, scalability, missing tests, and slowness, while still flagging unnecessary code.\n- Adds detailed review process: read diff, follow code flows, check real-world use and expected load.\n- Outputs findings in clear groups (Must fix, Should fix, Nice to have), with concrete problems and fixes for each.\n- Makes reporting style simple and actionable, with clear explanations and numbering across all findings.\n- Updates boundaries: no style/taste issues, only real technical or operational problems.\n- Removes previous card/summary file (skill-card.md); now SKILL.md gives full details.\n\nv4.13.0 | 2026-10-05T18:58:27.270Z | auto\n\n- Removed the documentation file skill-card.md.\n- No changes to core functionality or review guidelines.\n\nv4.12.0 | 2026-10-05T03:45:38.042Z | auto\n\n- Findings are now numbered for easier referencing and action, e.g., `1. L12-38: ...`\n- Example output updated to illustrate the new numbering scheme.\n- Formatting section updated to specify report-wide sequential numbering.\n- Removed file: skill-card.md.\n\nv4.11.0 | 2026-10-04T22:56:33.304Z | auto\n\n- Added new tag: reuse (for flagging duplicated helpers/utils within the repo).\n- Updated examples and tags section in SKILL.md to document the new reuse tag and provide relevant examples.\n- Removed the file: skill-card.md.\n\nv4.10.3 | 2026-10-03T02:37:25.796Z | auto\n\n- Removed the skill-card.md file. \n- No changes to the main skill logic or documentation content.\n\nv4.10.2 | 2026-10-03T01:32:44.235Z | auto\n\n- Removed the file skill-card.md.\n- No changes to functionality or documentation in SKILL.md.\n\nv4.10.1 | 2026-10-02T15:13:03.202Z | auto\n\n- Removed the skill-card.md file.\n- No changes made to core logic or documentation in SKILL.md.\n\nv4.9.0 | 2026-08-07T21:17:04.695Z | auto\n\n- Removed the skill-card.md file.\n- No changes to core functionality or SKILL.md content.\n\nv4.8.4 | 2026-06-29T05:34:45.194Z | auto\n\n- Removed the skill-card.md file.\n- No changes to core functionality or documentation content.\n\nv4.8.3 | 2026-06-24T02:37:28.799Z | auto\n\n- Removed the file: skill-card.md.\n- No changes to the core functionality or documentation in SKILL.md.\n\nv4.8.1 | 2026-06-23T21:02:12.688Z | auto\n\n- Updated skill description for clarity: reviews diffs for over-engineering and highlights what to delete in concise, one-line findings.\n- Standardized output format with tags for deletions, stdlib, native features, YAGNI issues, and line shrinking.\n- Added clear, side-by-side examples contrasting verbose vs. concise findings.\n- Defined boundaries: focus strictly on complexity and over-engineering, excluding correctness, security, and performance.\n- Formalized scoring: report possible net line reduction, or \"Lean already. Ship.\" if nothing to cut.\n\nArchive index:\n\nArchive v5.1.0: 3 files, 3760 bytes\n\nFiles: skill-card.md (1464b), SKILL.md (4976b), _meta.json (134b)\n\nFile v5.1.0:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview a change like the senior developer who will be paged when it breaks.\nOrder of importance: correct, safe, holds under load, tested, fast, lean.\nLean still matters: every extra line must be read, tested and fixed later.\nThis is a report the user asked for, so give it in full.\n\n## 1. Understand first\n\n- Review what the user names: uncommitted or staged changes, a branch, a PR\n  link, or files. Nothing named: the uncommitted changes, or the last commit\n  if there are none.\n- Read the diff, then the code it touches: callers of every changed function,\n  the functions it calls, the tests, the README.\n- Trace the real flow: where data comes in, what is stored, what goes out.\n- A change can break code it does not touch. When a signature, return value\n  or behavior changes, grep every caller.\n- Find the expected load in the repo (README, deploy config): one person\n  running a script, or many users and processes at once. Judge scale against\n  that, and say which load you assumed.\n\n## 2. Look for\n\n1. **Bug:** wrong result, crash, missed edge case (empty, zero, last item,\n   rounding, time zones), a caller broken by the change, a fix applied in one\n   caller while the shared function stays broken.\n2. **Risk:** security holes (injection, weak randomness, secrets, missing\n   checks on input from users), data loss (errors swallowed, writes in the\n   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 new logic (a branch, a parser, money, security,\n   data writes, a bug fix) with no test that fails when it breaks. One good\n   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, speculative features\n   - reuse: the repo already has this helper (name the path)\n   - stdlib / native: the standard library or platform already does it; a\n     new dependency for a few lines\n   - yagni: abstraction with one implementation, config nobody sets\n   - merge: near-copies that must change together\n   - split: one function doing several unrelated jobs, so it is hard to read\n     or test. Split by job, never by line count, and never into helpers that\n     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- Re-read the lines and confirm: the caller exists, the value can really be\n  empty, the code really is unused.\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 change does:` in two or three sentences.\n\nThen the findings in three groups, 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\".\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: Ship.` or `Verdict: fix 1 and 3 first.`\n- `Lean: -<N> lines possible.` when lean findings exist.\n- `Not checked:` one line, if something mattered and you could not check it.\n\nNothing found: `What this change does:`, then `Looks good. Ship.` and one line\non what you checked.\n\nLists findings, changes no code.\n\nFile v5.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"5.1.0\",\n  \"publishedAt\": 1791476491860\n}\n\nFile v5.1.0:skill-card.md\n\n## Description:\n\nReviews code changes for bugs, security risks, load issues, missing tests, performance problems, and unnecessary complexity, with actionable findings.\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 diff, branch, pull request, or files and receive prioritized, concrete findings without changing code.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Review findings may be incomplete or incorrect.\n\nMitigation: Check the cited code and proposed fixes before acting on the report.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dietrichgebert/skills/ponytail-review)\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown]\n\n**Output Format:** [Markdown report with prioritized findings, fixes, and a verdict]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports findings only; does not change files.]\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, 2587 bytes\n\nFiles: skill-card.md (1472b), SKILL.md (2432b), _meta.json (135b)\n\nFile v4.13.0:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`<N>. L<line>: <tag> <what>. <replacement>.`, or `<N>. <file>:L<line>: ...` for\nmulti-file diffs. Number findings `1.`, `2.`, ... across the whole report, so the\nuser can say \"fix 2 and 5\".\n\nTags:\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\n## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `1. L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `2. L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `3. L18-29: reuse: slugify helper duplicates src/lib/slug.ts slugify. Delete it, import the existing one.`\n\n✅ `4. repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `5. L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `6. L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.13.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.13.0\",\n  \"publishedAt\": 1791226707270\n}\n\nFile v4.13.0:skill-card.md\n\n## Description:\n\nReviews code diffs for over-engineering and suggests deletions or simpler replacements.\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 spot unnecessary complexity in code diffs and identify what to remove or simplify.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: This narrow review can miss correctness, security, and performance issues.\n\nMitigation: Run a separate review for correctness, security, and performance; do not rely on this skill as the sole review pass.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dietrichgebert/skills/ponytail-review)\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Guidance]\n\n**Output Format:** [Numbered, single-line findings with locations and a net-lines estimate, or a brief all-clear]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Review only; does not apply fixes.]\n\n## Skill Version(s):\n\n4.13.0 (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 v4.12.0: 3 files, 2744 bytes\n\nFiles: skill-card.md (1807b), SKILL.md (2432b), _meta.json (135b)\n\nFile v4.12.0:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`<N>. L<line>: <tag> <what>. <replacement>.`, or `<N>. <file>:L<line>: ...` for\nmulti-file diffs. Number findings `1.`, `2.`, ... across the whole report, so the\nuser can say \"fix 2 and 5\".\n\nTags:\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\n## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `1. L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `2. L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `3. L18-29: reuse: slugify helper duplicates src/lib/slug.ts slugify. Delete it, import the existing one.`\n\n✅ `4. repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `5. L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `6. L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.12.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.12.0\",\n  \"publishedAt\": 1791171938042\n}\n\nFile v4.12.0:skill-card.md\n\n## Description:\n\nReviews diffs for unnecessary complexity and suggests what to remove or replace in concise, numbered findings.\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 review code diffs for over-engineering and identify deletions, standard-library replacements, and simpler existing patterns without applying changes.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A complexity-only review may overlook correctness, security, or performance issues.\n\nMitigation: Run a separate review for correctness, security, and performance before accepting changes.\n\nRisk: Conversational text such as 'normal mode' may change or fail to change the intended review style.\n\nMitigation: Use explicit host controls to activate or stop the skill when precise control matters.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dietrichgebert/skills/ponytail-review)\n- [Skill homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown]\n\n**Output Format:** [Numbered, one-line findings with locations and suggested cuts or replacements, followed by a net line-reduction estimate; or a short no-findings verdict]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Review suggestions only; does not edit code.]\n\n## Skill Version(s):\n\n4.12.0 (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 v4.11.0: 3 files, 2584 bytes\n\nFiles: skill-card.md (1636b), SKILL.md (2312b), _meta.json (135b)\n\nFile v4.11.0:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for\nmulti-file diffs.\n\nTags:\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\n## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `L18-29: reuse: slugify helper duplicates src/lib/slug.ts slugify. Delete it, import the existing one.`\n\n✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.11.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.11.0\",\n  \"publishedAt\": 1791154593304\n}\n\nFile v4.11.0:skill-card.md\n\n## Description:\n\nReviews code diffs for unnecessary complexity and suggests concise, deletion-focused changes.\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 find over-engineering in code diffs and receive brief, line-specific suggestions for simplifying or removing it.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A complexity-only review may miss correctness, security, or performance issues.\n\nMitigation: Conduct separate correctness, security, and performance reviews.\n\nRisk: Deletion suggestions could remove useful safeguards.\n\nMitigation: Review suggestions before applying them and retain a basic smoke test or self-check.\n\n## Reference(s):\n\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n- [ClawHub skill release](https://clawhub.ai/dietrichgebert/skills/ponytail-review)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Guidance]\n\n**Output Format:** [Plain text with line-referenced, tagged review findings and a net-lines estimate]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Proposes changes but does not apply them; reports when no simplification is needed.]\n\n## Skill Version(s):\n\n4.11.0 (source: 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 v4.10.3: 3 files, 2451 bytes\n\nFiles: skill-card.md (1517b), SKILL.md (2118b), _meta.json (135b)\n\nFile v4.10.3:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for\nmulti-file diffs.\n\nTags:\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## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.10.3:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.10.3\",\n  \"publishedAt\": 1790995045796\n}\n\nFile v4.10.3:skill-card.md\n\n## Description:\n\nReviews code diffs for unnecessary complexity and suggests concise ways to remove it.\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 code, dependencies, and abstractions they can remove from a diff without applying changes.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A complexity-only review can miss correctness, security, and performance issues.\n\nMitigation: Run a separate general code review for those issues before accepting changes.\n\n## Reference(s):\n\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n- [ClawHub skill listing](https://clawhub.ai/dietrichgebert/skills/ponytail-review)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Code review guidance]\n\n**Output Format:** [Plain text, one line per finding]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Findings identify a location and a simpler replacement, followed by an estimated net line reduction; if nothing needs cutting, reports that the diff is already lean.]\n\n## Skill Version(s):\n\n4.10.3 (source: 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 v4.10.2: 3 files, 2439 bytes\n\nFiles: skill-card.md (1494b), SKILL.md (2118b), _meta.json (135b)\n\nFile v4.10.2:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for\nmulti-file diffs.\n\nTags:\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## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.10.2:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.10.2\",\n  \"publishedAt\": 1790991164235\n}\n\nFile v4.10.2:skill-card.md\n\n## Description:\n\nReviews diffs for over-engineering and suggests deletions or simplifications in one line per finding.\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 reviewers use this skill to identify unnecessary complexity in code diffs and suggest what to remove or simplify.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Complexity-only feedback can miss correctness, security, and performance issues.\n\nMitigation: Use a normal code review alongside this skill 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-review)\n\n## Skill Output:\n\n**Output Type(s):** [Text]\n\n**Output Format:** [Plain text with tagged, line-referenced review findings]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Ends with a net line-reduction estimate, or says 'Lean already. Ship.' when there are no findings; does not apply fixes.]\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, 2511 bytes\n\nFiles: skill-card.md (1647b), SKILL.md (2118b), _meta.json (135b)\n\nFile v4.10.1:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for\nmulti-file diffs.\n\nTags:\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## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.10.1:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.10.1\",\n  \"publishedAt\": 1790953983202\n}\n\nFile v4.10.1:skill-card.md\n\n## Description:\n\nReviews code diffs for unnecessary complexity and suggests what to remove or simplify.\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 code reviewers use this skill to find unnecessary dependencies, duplicated standard-library functionality, and speculative abstractions in diffs. It suggests deletions or simpler replacements without changing code.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A complexity-only review can miss security, correctness, or performance issues.\n\nMitigation: Use a separate normal code review for security, correctness, and performance before accepting changes.\n\n## Reference(s):\n\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n- [ClawHub skill release](https://clawhub.ai/dietrichgebert/skills/ponytail-review)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown]\n\n**Output Format:** [Line-numbered, tagged review findings or a short no-findings response]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Findings identify what to cut and its replacement, followed by an estimated net line reduction; the skill does not apply fixes.]\n\n## Skill Version(s):\n\n4.10.1 (source: server-resolved 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, 2626 bytes\n\nFiles: skill-card.md (1898b), SKILL.md (2118b), _meta.json (134b)\n\nFile v4.9.0:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for\nmulti-file diffs.\n\nTags:\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## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.9.0:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.9.0\",\n  \"publishedAt\": 1786137424695\n}\n\nFile v4.9.0:skill-card.md\n\n## Description:\n\nReview a diff for over-engineering and identify what to delete, replace with standard library or native platform features, or simplify.\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 diffs for unnecessary complexity, speculative abstractions, needless dependencies, and hand-rolled functionality that a standard library or platform feature can replace.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may mistake the skill's complexity-focused findings for a complete code review.\n\nMitigation: Run a normal review pass for correctness, security, and performance concerns, which the skill explicitly excludes.\n\nRisk: A terse deletion or simplification recommendation may remove behavior that is still needed by the project.\n\nMitigation: Review each recommendation against product requirements and tests before applying changes.\n\n## Reference(s):\n\n- [Ponytail Homepage](https://github.com/DietrichGebert/ponytail)\n- [ClawHub Skill Page](https://clawhub.ai/dietrichgebert/skills/ponytail-review)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, guidance]\n\n**Output Format:** [Markdown text with one-line findings and a net line-count estimate]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Does not apply fixes; it only lists complexity-reduction findings or reports that the diff is already lean.]\n\n## Skill Version(s):\n\n4.9.0 (source: evidence.release.version)\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, 2557 bytes\n\nFiles: skill-card.md (1816b), SKILL.md (2118b), _meta.json (134b)\n\nFile v4.8.4:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for\nmulti-file diffs.\n\nTags:\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## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.8.4:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.8.4\",\n  \"publishedAt\": 1782711285194\n}\n\nFile v4.8.4:skill-card.md\n\n## Description: <br>\nReview a diff for over-engineering and identify deletions, standard-library replacements, native platform features, speculative abstractions, and shorter equivalents. <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 use this skill during code review to find unnecessary complexity in diffs and get terse suggestions for what to remove or simplify. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill intentionally gives terse deletion and simplification suggestions that may miss correctness, security, or performance concerns. <br>\nMitigation: Use it as a complexity-focused pass and run a normal review for bugs, security, and performance before relying on the results. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/dietrichgebert/skills/ponytail-review) <br>\n- [Project homepage](https://github.com/DietrichGebert/ponytail) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, Guidance] <br>\n**Output Format:** [Markdown or plain text review findings, one line per finding] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Ends with a net lines possible summary when findings exist; says Lean already. Ship. when there is nothing to cut.] <br>\n\n## Skill Version(s): <br>\n4.8.4 (source: server 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>\n\nArchive v4.8.3: 3 files, 2764 bytes\n\nFiles: skill-card.md (2352b), SKILL.md (2118b), _meta.json (134b)\n\nFile v4.8.3:SKILL.md\n\n---\nname: ponytail-review\ndescription: \"Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview diffs for unnecessary complexity. One line per finding: location, what\nto cut, what replaces it. The diff's best outcome is getting shorter.\n\n## Format\n\n`L<line>: <tag> <what>. <replacement>.`, or `<file>:L<line>: ...` for\nmulti-file diffs.\n\nTags:\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## Examples\n\n❌ \"This EmailValidator class might be more complex than necessary, have you\nconsidered whether all these validation rules are needed at this stage?\"\n\n✅ `L12-38: stdlib: 27-line validator class. \"@\" in email, 1 line, real validation is the confirmation mail.`\n\n✅ `L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.`\n\n✅ `repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.`\n\n✅ `L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.`\n\n✅ `L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.`\n\n## Scoring\n\nEnd with the only metric that matters: `net: -<N> lines possible.`\n\nIf there is nothing to cut, say `Lean already. Ship.` and stop.\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, not this one. A single smoke test or `assert`-based\nself-check is the ponytail minimum, not bloat, never flag it for deletion.\nDoes not apply the fixes, only lists them.\n\"stop ponytail-review\" or \"normal mode\": revert to verbose review style.\n\nFile v4.8.3:_meta.json\n\n{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"4.8.3\",\n  \"publishedAt\": 1782268648799\n}\n\nFile v4.8.3:skill-card.md\n\n## Description: <br>\nReview a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding. <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 run a terse review pass over code diffs and identify unnecessary complexity to delete or simplify. It focuses on over-engineering signals such as needless dependencies, speculative abstractions, hand-rolled standard library behavior, and line-count reduction opportunities. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill is intentionally scoped to over-engineering and complexity, so it may miss correctness, security, performance, or maintainability issues outside that narrow review pass. <br>\nMitigation: Use a normal review alongside this skill for bugs, security, performance, and broader maintainability concerns. <br>\nRisk: The skill produces deletion and simplification recommendations but does not apply fixes. <br>\nMitigation: Review each recommendation before editing code, and validate accepted changes with the project test or smoke-test workflow. <br>\n\n\n## Reference(s): <br>\n- [Ponytail Review on ClawHub](https://clawhub.ai/dietrichgebert/skills/ponytail-review) <br>\n- [dietrichgebert ClawHub profile](https://clawhub.ai/user/dietrichgebert) <br>\n- [Ponytail homepage](https://github.com/DietrichGebert/ponytail) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Analysis, Markdown, Guidance] <br>\n**Output Format:** [Concise Markdown text with one finding per line and a final net line-count estimate] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Does not apply fixes; reports findings only. If there is nothing to cut, it returns a brief lean-code message.] <br>\n\n## Skill Version(s): <br>\n4.8.3 (source: server-resolved 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>","readmeExcerpt":"Skill: ponytail-review Owner: dietrichgebert Summary: Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:21:31.860Z | auto This release expands the skill from lean/over-engineering review to a full quality review including bugs, tests, security, scale, and perform","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: ponytail-review\ndescription: \"Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it.\"\nhomepage: https://github.com/DietrichGebert/ponytail\nlicense: MIT\n---\n\nReview a change like the senior developer who will be paged when it breaks.\nOrder of importance: correct, safe, holds under load, tested, fast, lean.\nLean still matters: every extra line must be read, tested and fixed later.\nThis is a report the user asked for, so give it in full.\n\n## 1. Understand first\n\n- Review what the user names: uncommitted or staged changes, a branch, a PR\n  link, or files. Nothing named: the uncommitted changes, or the last commit\n  if there are none.\n- Read the diff, then the code it touches: callers of every changed function,\n  the functions it calls, the tests, the README.\n- Trace the real flow: where data comes in, what is stored, what goes out.\n- A change can break code it does not touch. When a signature, return value\n  or behavior changes, grep every caller.\n- Find the expected load in the repo (README, deploy config): one person\n  running a script, or many users and processes at once. Judge scale against\n  that, and say which load you assumed.\n\n## 2. Look for\n\n1. **Bug:** wrong result, crash, missed edge case (empty, zero, last item,\n   rounding, time zones), a caller broken by the change, a fix applied in one\n   caller while the shared function stays broken.\n2. **Risk:** security holes (injection, weak randomness, secrets, missing\n   checks on input from users), data loss (errors swallowed, writes in the\n   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 new logic (a branch, a parser, money, security,\n   data writes, a bug fix) with no test that fails when it breaks. One good\n   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, speculative features\n   - reuse: the repo already has this helper (name the path)\n   - stdlib / native: the standard library or platform already does it; a\n     new dependency for a few lines\n   - yagni: abstraction with one implementation, config nobody sets\n   - merge: near-copies that must change together\n   - split: one function doing several unrelated jobs, so it is hard to read\n     or test. Split by job, never by line count, and never into helpers that\n     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- Re-read the lines and confirm: the caller ex"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn75jhs1s4186aj57w94eykzm188rxj8\",\n  \"slug\": \"ponytail-review\",\n  \"version\": \"5.1.0\",\n  \"publishedAt\": 1791476491860\n}"},{"path":"skill-card.md","content":"## Description:\n\nReviews code changes for bugs, security risks, load issues, missing tests, performance problems, and unnecessary complexity, with actionable findings.\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 diff, branch, pull request, or files and receive prioritized, concrete findings without changing code.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Review findings may be incomplete or incorrect.\n\nMitigation: Check the cited code and proposed fixes before acting on the report.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dietrichgebert/skills/ponytail-review)\n- [Project homepage](https://github.com/DietrichGebert/ponytail)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown]\n\n**Output Format:** [Markdown report with prioritized findings, fixes, and a verdict]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports findings only; does not change files.]\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 review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it. Skill: ponytail-review Owner: dietrichgebert Summary: Quality review of a diff: bugs, security, real load, missing tests, speed, and what to delete. Each finding says what goes wrong and how to fix it. Tags: latest:5.1.0 Version history: v5.1.0 | 2026-10-08T16:21:31.860Z | auto This release expands the skill from lean/over-engineering review to a full quality review including bugs, tests, security, scale, and perform","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1304,"uniquenessScore":51,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T01:00:50.779Z","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":"2026-10-10T01:00:50.779Z","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":"2026-10-10T06:44:29.347Z","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"}]}}}