ponytail-review
Skill5 starsChanged 48 days agoApache-2.0View on GitHub
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.
84 other projects use a version of this, 52 of them edited.
Adopted by
Most recently taken up by
- Floppa2003/skillstheir own version, first seen Nov 16, 2026
- jjsizemore/jjskillsedited, first seen Nov 16, 2026
- mvsimao/agent-skillstheir own version, first seen Nov 16, 2026
- AlexanderTar/swarmrunedited, first seen Nov 16, 2026
- FAHTHIZ/oasistheir own version, first seen Nov 16, 2026
- Yassimba/loomtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use caveman-explore, caveman-discover and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JuliusBrusseeSkillcaveman-explore
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
Also in 5 projects that use this
JuliusBrusseeSkillcaveman-discover
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
Also in 3 projects that use this
ryu111Skillmigration
Migration planning expertise. Use when replacing tools/frameworks, upgrading versions, migrating databases, or planning transitions. Contains strategies, compatibility analysis methods, and rollback planning.
Also in 5 projects that use this
huangzidaSkillcaveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
Also in 7 projects that use this
huangzidaSkillcaveman-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Also in 9 projects that use this
jaydubya818Skillthermo-nuclear-code-quality-review
Use when the user requests an intentionally strict maintainability review.
Also in 5 projects that use this
- +4 more from JuliusBrussee
- +2 more from huangzida
Other versions84 projects use a version of this.
Word for word · 0
None found.
Edited · 52
- kortix-ai/CompanyOS★ 21k99% same
- kortix-ai/suna★ 21k99% same
- marmelab/atomic-crm★ 1.4k96% same
- mezotv/notra★ 25699% same
- usenotra/notra★ 25699% same
- jacred-fdb/jacred★ 14099% same
- Wenaixi/dsh-ponytail★ 4699% same
- KenSuh/open-agent-harness★ 3399% same
- sampleXbro/agentsmesh★ 2799% same
- mirkobozzetto/espresso★ 2576% same
42 more not listed
Wrote their own version · 32
- DietrichGebert/ponytail★ 182ksame name
- Cygnux-Labs/Tracekit★ 726same name
- engasnm111/lnwjud★ 209same name
- Djarvur/go-ultimate★ 31same name
- Yassimba/loom★ 13same name
- ZerroDevs/AgentsHub-Desktop★ 9same name
- shaderera/shaderera★ 7same name
- ZerroDevs/AgentsHub★ 6same name
- FAHTHIZ/oasis★ 4same name
- Jay-1409/skills★ 2same name
22 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- rules/AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/graphify.mdcCursor rule
- llms.txtllms.txt
- chilean-administrative-legalSkill
- chilean-case-intakeSkill
- chilean-contract-legalSkill
- chilean-contradictorio-goldfishSkill
- chilean-corporate-legalSkill
- chilean-docket-watcherSkill
- chilean-doctrine-ingestionSkill
- chilean-dogmatic-graphifySkill
- chilean-dossier-assemblySkill
- chilean-employment-legalSkill
- chilean-energy-legalSkill
- chilean-environmental-legalSkill
- chilean-forensic-evidenceSkill
- chilean-legal-clinicSkill
- chilean-litigation-legalSkill
- chilean-notebooklm-groundingSkill
- chilean-privacy-ipSkill
- chilean-probity-investigationSkill
- chilean-real-estate-cbrSkill
- chilean-socratic-bar-examSkill
- chilean-workspace-legal-flowSkill
- ponytail-auditSkill
- ponytail-debtSkill
- ponytail-gainSkill
- ponytail-helpSkill
- ponytailSkill
- graphifySkill
The file
We split this skill into the rules it gives an agent
2 rules. 1 is common, 0 are distinctive, and 1 is very specific to this project.
1
Common
Most of the 80 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 59
If there is nothing to cut, say Lean already.
- Common: line 67
Does not apply the fixes, only lists them.
“Common” is measured: kept by at least 6 in 10 of the 80 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review diffs for unnecessary complexity. One line per finding: location, what to cut, what replaces it. The diff's best outcome is getting shorter.
Format
L<line>: <tag> <what>. <replacement>., or <file>:L<line>: ... for
multi-file diffs.
Tags:
delete:dead code, unused flexibility, speculative feature. Replacement: nothing.stdlib:hand-rolled thing the standard library ships. Name the function.native:dependency or code doing what the platform already does. Name the feature.yagni:abstraction with one implementation, config nobody sets, layer with one caller.shrink:same logic, fewer lines. Show the shorter form.
📎 Citas y formato de entrega
- Documentos (informe en derecho, análisis, memorándum, escrito, minuta, dossier): se entregan en Word (.docx), no en PDF, para que se puedan modificar; las citas van a pie de página, numeradas, con fuente · identificador · enlace.
- Conversación: la respuesta va primero y las citas van al final, después del texto.
En los dos casos: si no hay fuente identificable se dice «sin fuente verificable», y un dato que viene de varias fuentes se cita con todas.
Examples
❌ "This EmailValidator class might be more complex than necessary, have you considered whether all these validation rules are needed at this stage?"
✅ L12-38: stdlib: 27-line validator class. "@" in email, 1 line, real validation is the confirmation mail.
✅ L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.
✅ repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.
✅ L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.
✅ L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.
Scoring
End with the only metric that matters: net: -<N> lines possible.
If there is nothing to cut, say Lean already. Ship. and stop.
Boundaries
Scope: over-engineering and complexity only. Correctness bugs, security holes,
and performance are explicitly out of scope. Route them to a normal review
pass, not this one. A single smoke test or assert-based
self-check is the ponytail minimum, not bloat, never flag it for deletion.
Does not apply the fixes, only lists them.
"stop ponytail-review" or "normal mode": revert to verbose review style.
🎨 Presentación y Lenguaje Claro (Legal Design)
Overlay de docs/legal_design.md para este repositorio (por eso va en español: es el idioma de trabajo de Open Legal Chile). Esta skill es de código, no de derecho: hereda las reglas de presentación, no las jurídicas.
- Quién lee: quien revisa el diff, que puede no ser experto en este módulo.
- Lenguaje claro: todo término técnico o sigla va con su equivalencia simple entre paréntesis la primera vez —
yagni (no construyas lo que todavía no se necesita). - Salida (estructura): una línea por hallazgo (
L<line>: <tag> <what>. <replacement>.) cerrando connet: -<N> lines possible. - Citas: si la salida toca materia jurídica, se cita en el Formato de Citación Obligatorio de
AGENTS.md§2 ([BCN - Ley N° 21.643, Art. 2]); si es código, archivo y línea. - Compuerta: ⚖️ Compuerta de Revisión Jurídica aplica solo si la salida de esta skill termina en un producto jurídico (escrito, memo, comunicación a contraparte). Una skill que simplifica código no produce asesoría jurídica ni la sustituye.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

