conventional-commit
Skill2 starsChanged 8 months agoApache-2.0View on GitHub
Enforces Conventional Commits format for the EndogenAI Workflows repository. USE FOR: composing commit messages (type(scope): description format); reviewing commit message format before push; understanding allowed types (feat/fix/docs/chore/test/refactor/ci/perf) and scopes (scripts/agents/docs/tests/ci/deps/research). DO NOT USE FOR: release versioning decisions (use the Release Manager agent); PR template authoring.
30 other projects use a version of this.
Adopted by
Most recently taken up by
- rlespinasse/agent-skillstheir own version, first seen Nov 8, 2026
- AgnesAI-Labs/agnet-skills-cntheir own version, first seen Nov 1, 2026
- yearzen1/LocalSkillManagertheir own version, first seen Nov 1, 2026
- github/awesome-copilottheir own version, first seen Oct 25, 2026
- typeweaver/skillstheir own version, first seen Oct 20, 2026
- Marvellbrazil/my-agentic-skillstheir own version, first seen Oct 17, 2026
Used with
Projects with it also use shipping-and-launch, doubt-driven-development 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.
LLl0k0laDSkillshipping-and-launch
Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
Also in 3 projects that use this
seikaikyoSkilldoubt-driven-development
對非平凡決策啟動新鮮 context 對抗審查(找碴不背書),在修正還便宜的時候抓出錯誤方向。適用:高風險改動(production、資安敏感邏輯、不可逆操作)、不熟的程式碼、要宣稱「這樣是安全的 / 可行的」之前。機械性操作與一行修改不適用。
Also in 3 projects that use this
LLl0k0laDSkillapi-and-interface-design
Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Also in 3 projects that use this
HK-hubSkillcode-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
Also in 3 projects that use this
guaderramaSkillspec-driven-development
Generate comprehensive specifications for software projects using spec-driven development methodology. Leverages Bright Data MCP tools to research documentation, analyze competitor implementations, gather real-world examples, and enrich specs with architectural insights. Use when user requests specifications, technical plans, project specs, or architecture documentation.
Also in 3 projects that use this
MicrosoftSkillapi-design
Guide for designing and documenting RESTful APIs. Use when asked to design an API, create endpoints, or document an API.
Also in 3 projects that use this
- +1 more from LLl0k0laD
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- github/awesome-copilot★ 41ksame name
- JanDeDobbeleer/oh-my-posh★ 24ksame name
- magicdawn/Bilibili-Gate★ 828same name
- termio-sh/termio★ 787same name
- navikt/copilot★ 61same name
- marc-ing/marc-skills★ 14same name
- rlespinasse/agent-skills★ 13same name
- soujava/agent-skills★ 10same name
- flpbalada/fb-skills★ 8same name
- jjxmonster/skills★ 8same name
20 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 repository27 other files it gives its agents.
- adopt-test-2/AGENTS.mdAGENTS.md
- adopt-test-3/AGENTS.mdAGENTS.md
- adopt-test/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- {{cookiecutter.project_slug}}/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- .github/agents/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-file-authoringSkill
- corpus-sweepSkill
- deep-research-sprintSkill
- delegation-routingSkill
- phase-gate-sequenceSkill
- prompt-archaeologySkill
- pr-review-replySkill
- pr-review-triageSkill
- rate-limit-resilienceSkill
- research-epic-planningSkill
- secondary-research-sprintSkill
- session-managementSkill
- session-retrospectiveSkill
- skill-authoringSkill
- source-cachingSkill
- sprint-planningSkill
- transcript-extractionSkill
- validate-before-commitSkill
- workplan-scaffoldSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 27 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
No period at the end of the description
“Common” is measured: kept by at least 6 in 10 of the 27 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
Conventional Commit
This skill enacts the Algorithms Before Tokens axiom from MANIFESTO.md by encoding commit message conventions as a reusable procedure, eliminating per-session re-prompting overhead. Commit discipline is governed by AGENTS.md § Commit Discipline and CONTRIBUTING.md § Commit Discipline. When this skill and those documents conflict, the primary documents take precedence.
1. Format
<type>(<scope>): <description>
[optional body]
[optional footer(s)]Rules for the first line:
- Imperative mood: "add", "fix", "update" — not "adds", "fixed", "updating"
- Lowercase throughout (type, scope, description)
- No period at the end of the description
- Maximum 72 characters for the first line
- Scope is in parentheses, not brackets
Valid: docs(guides): add session-management skill reference
Invalid: Updated the docs. / DOCS: Updates guides / docs(guides): Added session-management skill reference.
2. Types
| Type | When to use | Example for this repo |
feat | New capability, new agent, new script | feat(agents): add executive-docs agent |
fix | Correction to existing content or code | fix(scripts): handle missing .tmp dir in prune_scratchpad |
docs | Documentation only — no code or script change | docs(guides): clarify encoding checkpoint format |
chore | Tooling, scripts, templates, config — no production logic | chore(scripts): add scaffold_workplan.py for plan generation |
test | New or updated tests | test(scripts): add coverage for validate_synthesis error cases |
refactor | Restructuring without content or behaviour change | refactor(agents): extract session-mgmt handoff to skill |
ci | CI configuration, workflow files, pre-commit hooks | ci: add validate_skill_files check to lint job |
perf | Performance improvement | perf(scripts): cache URL validation results in fetch_source |
Do not use feat for documentation. A new research doc is docs(research), not feat(research). A new guide is docs(guides).
3. Scopes
Scopes are lowercase, single-word identifiers describing the affected area of the codebase:
| Scope | Covers |
scripts | Files in scripts/ |
agents | Files in .github/agents/ |
skills | Files in .github/skills/ |
docs | Files in docs/ (guides, research, plans, decisions) |
tests | Files in tests/ |
ci | Files in .github/workflows/, .pre-commit-config.yaml |
deps | pyproject.toml, uv.lock, dependency changes |
research | Research synthesis docs in docs/research/ |
plans | Workplan docs in docs/plans/ |
manifesto | MANIFESTO.md changes |
readme | README.md changes |
guides | Specific use when only docs/guides/ files change |
Scope is optional but strongly encouraged for this repo — it makes git log --oneline readable and enables filtered history queries (e.g., git log --oneline -- scripts/).
4. Multi-Line Body Format
For commits that benefit from explanation (why, not just what), add a body after a blank line:
docs(agents): add session-management skill body section
The session-close procedure previously lacked the issue-comment step.
Added steps 6.2 and 6.3 to encode the gh issue comment + checkbox update
sequence from AGENTS.md § Agent Communication.
Closes #42Body guidelines:
- Separate from the first line with exactly one blank line
- Wrap at 72 characters
- Explain why the change was made, not what (the diff shows what)
- Issue references on their own line at the end
Issue reference formats:
Closes #N— closes the issue when the commit lands on main (via PR merge)Refs #N— references without closingPart of #N— partial progress on a larger issue
5. Breaking Changes
Inline ! suffix
For a breaking change in the first line:
feat(agents)!: rename executive-researcher to research-executiveBREAKING CHANGE footer
For breaking changes with a description:
refactor(scripts): consolidate fetch scripts into single entry point
BREAKING CHANGE: fetch_source.py and fetch_all_sources.py now require
--manifest flag; direct URL argument is removed. Update any scripts
or CI steps that call these with bare URLs.Both methods are valid. Use ! for simple renames/removals; use the footer when a migration note is needed.
6. Examples Representative of This Repo
# New agent added to the fleet
feat(agents): add executive-docs agent for documentation governance
# Bug fix in a script
fix(scripts): correct branch slug calculation for paths with multiple slashes
# Research synthesis doc added
docs(research): add agent-skills-integration synthesis — status: Final
# ADR committed
docs(decisions): add ADR-006 agent skills adoption
# CI gate added
ci: run validate_skill_files.py on PRs touching .github/skills/
# Workplan created at session start
docs(plans): add 2026-03-07-agent-skills-implementation workplan
# Pre-compact safety commit (no scope needed)
chore: pre-compact checkpoint — session state saved to scratchpad
# Dependency update
chore(deps): bump uv.lock after adding mkdocs-material
# Test coverage for a new script
test(scripts): add tests for scaffold_workplan.py happy path and error exits
# Docs-only correction (no functional change)
docs(guides): fix broken link to session-synthesis source stub7. What NOT to Do
| Anti-pattern | Why it fails | Correct alternative |
update docs | Vague — what was updated? No type, no scope | docs(guides): clarify programmatic-first decision table |
WIP or wip: stuff | Not a valid type; not revertable safely | Commit the specific logical unit; use feature branches |
feat: update scripts and docs and agents | Multiple unrelated changes in one commit | Three separate commits, each with its own scope |
Fix #42 | No type, no scope, no description | fix(agents): correct tool restriction for executive-docs (Closes #42) |
docs(guides): Added new section. | Past tense + trailing period | docs(guides): add new section |
chore: checkpoint | Too vague for a non-checkpoint session commit | Use for pre-compact checkpoints only; otherwise be specific |
feat(everything): massive refactor | Scope "everything" is not a real scope | Break into per-scope commits |
| Skipping scope entirely when scope is clear | Makes history unfiltered | Always include scope when the change is clearly localized |
8. Commit Cadence
Per CONTRIBUTING.md § Commit Discipline: commit frequently as you complete each logical unit of work — not one giant commit at the end of a session.
| Unit of work | Commit timing |
| Docs change | Commit immediately after the file is saved |
| Script change | Commit immediately; tests committed in the same or next commit |
| Agent file change | Commit immediately; also update README.md catalog in same commit |
| Workplan created | Commit before Phase 1 executes |
| Pre-compact | Commit all in-flight changes before running /compact |
| Session end | Commit the Session Summary scratchpad content (if extracted to a doc) |
This repo uses rebase and merge only — squash merge is disabled. Every commit message lands on main individually, so every commit message must be valid and meaningful standing alone.
9. Governing Constraint
This skill is governed by AGENTS.md § Commit Discipline and CONTRIBUTING.md § Commit Discipline. The Conventional Commits specification is at conventionalcommits.org.
The encoding inheritance chain is:
MANIFESTO.md → AGENTS.md → agent files → this skill → session behaviour.
A commit message is not decoration — it is the durable record of a logical change. Low-quality messages degrade the endogenic substrate: future sessions cannot reconstruct intent from history, and CI cannot identify regressions by type. Write commit messages as if a future agent will rely on them to understand the codebase.
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.

