precommit
Skill2 starsChanged 31 days agoApache-2.0View on GitHub
Quality gate before every commit. Verifies tests are meaningful, instructions are followed, code meets standards, and changes work in the running app. Keywords: commit, push, pre-commit, quality, check, verify, ready, standards, before commit, gate
7 other projects use a version of this.
Adopted by
Most recently taken up by
- mycelium-io/myceliumtheir own version, first seen Nov 1, 2026
- hmj1026/dhpktheir own version, first seen Oct 13, 2026
- dut00/ai-document-intelligence-platformtheir own version, first seen Oct 13, 2026
- sd0xdev/sd0x-dev-flowtheir own version, first seen Oct 8, 2026
- dataplat/dbatoolstheir own version, first seen Oct 8, 2026
- apache/pinottheir own version, first seen Oct 8, 2026
Used with
Projects with it also use merge-prep, repo-intake and 2 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.
sd0xdevSkillmerge-prep
Pre-merge analysis and preparation. Analyzes source branch vs target branch: commit stats, conflict detection, file impact. Analysis-only v1 — outputs report + suggested commands, does not auto-merge. Use when: user says 'merge prep', 'pre-merge', 'merge analysis', or /merge-prep
Also in 3 projects that use this
AuroraBackcountrySkillrepo-intake
Get a picked-up repo ready to work in. Unfamiliar repo: ask intent, map it by reading, write the canonical AGENTS.md, wire the vault, propose a first task. Already-documented repo with no vault space: wire-only — connect it and leave the docs alone. Use when picking up a codebase: "onboard me", "get me set up on this repo", "I cloned/forked this", "map this repo", "wire this into the vault" — or proactively when a repo has no AGENTS.md/CLAUDE.md and real work starts. Check ownership first: on a repo the user doesn't own, intake is vault-first and writes nothing into tracked files. NOT memory refresh (that's memory-checkpoint) or greenfield scaffolding (/scaffold); documented AND wired = nothing to do.
Also in 3 projects that use this
- sd0xdevSkill
issue-analyze
GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict assessment + investigation strategy.
Also in 3 projects that use this
pravinemani5545Skillproject-audit
Use when the user wants a thorough/exhaustive bug audit of a project, codebase, or end-to-end workflow — phrasings like "audit my entire workflow", "find all the bugs", "be extensive, don't miss the most minor bug", pre-go-live hardening, "spawn subagents to find bugs", or when they want the findings actually fixed afterward. Spawns parallel finder agents across many bug dimensions, adversarially verifies every finding to kill false positives, ranks by severity, then fixes in small verified+deployed batches and updates docs. Works on any stack (web app, backend, edge functions, data pipeline, infra).
Also in 3 projects that use this
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- apache/pinot★ 6.2ksame name
- dataplat/dbatools★ 2.9ksame name
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
- mycelium-io/mycelium★ 127same name
- hmj1026/dhpk★ 2same name
- dut00/ai-document-intelligence-platform★ 0same name
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 repository14 other files it gives its agents.
- agent-toolkit-modeSkill
- architectureSkill
- assessSkill
- autopilotSkill
- debug_toolSkill
- evaluateSkill
- exploreSkill
- implementationSkill
- requirementsSkill
- reviewerSkill
- setupSkill
- statusSkill
- updaterSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Test quality — specific assertions, realistic data, would fail if feature deleted.
- Very specific: line 15
Run project test/lint commands from gates.json.
- Very specific: line 17
Write findings to .scratch/precommit_<slug>/findings.json → finalize_report.py precommit ….
- Very specific: line 18
Do not write reports/ directly.
“Common” is measured: kept by at least 6 in 10 of the 6 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
You are a Pre-Commit Gate Agent. Nothing commits until checks pass.
Default path
run_function("gate_status", {"project_dir": ".", "skill": "precommit"})— see missing markers.- Instruction compliance — every user ask addressed + tested.
- Test quality — specific assertions, realistic data, would fail if feature deleted.
- Run project test/lint commands from
gates.json. - Standards + G-IMPL-6 (no easy way out).
- Write findings to
.scratch/precommit_<slug>/findings.json→finalize_report.py precommit …. Exact keys are inget_module("precommit", "workflow")→ "Findings schema" (instructions,rules,readme,tests_meaningful,app_verification,reviewer_gate); finalize exits 2 on any other shape. - Do not write
reports/directly. Do not commit until finalize passes.
Quick mode (<3 files, no new features): steps 1–4 only. Full mode: pull modules.
Pull map
| When | Pull |
| Checklist detail | get_module("precommit", "checks") |
| Full step-by-step + a11y/security/git | get_module("precommit", "workflow") |
| Gate rules | shared/GATE-RULES.md |
| Test patterns | references/test-quality.md |
Block on sloppy tests, unaddressed instructions, or failed suite. Never say "fixed" without verification.
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.