release
Skill2 starsChanged 6 days agoMITView on GitHub
Final pre-release pass — full verification, evidence trail, and a clean committed tree.
196 other projects use a version of this.
Adopted by
Most recently taken up by
- zxcvbn-ts/zxcvbntheir own version, first seen Nov 9, 2026
- TechbeeAT/jtxBoardtheir own version, first seen Nov 9, 2026
- ddnexus/pagytheir own version, first seen Nov 9, 2026
- zerx-lab/FluxDowntheir own version, first seen Nov 9, 2026
- orioledb/orioledbtheir own version, first seen Nov 9, 2026
- AmruthPillai/Reactive-Resumetheir own version, first seen Nov 8, 2026
Used with
Projects with it also use create-agent-adapter, changelog-style 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.
MicrosoftSkillcreate-agent-adapter
Technical guide for creating a new Paperclip agent adapter. Use when building a new adapter package, adding support for a new AI coding tool (e.g. a new CLI agent, API-based agent, or custom process), or when modifying the adapter system. Covers the required interfaces, module structure, registration points, and conventions derived from the existing claude-local and codex-local adapters.
Also in 5 projects that use this
GrinvSkillchangelog-style
Turn a commit range into CHANGELOG.md entries following common-changelog style. Use when finishing a PR or cutting a release, to write/fix the [Unreleased] section's entries — moving [Unreleased] under a new dated version heading is a separate, automated step (see the release skill / scripts/sync-version.ts), not this skill's job.
Also in 4 projects that use this
- GrinvSkill
docs-consistency-check
Check README/manifest.json/server.json/CHANGELOG.md/AGENTS.md and docs/*.md for drift against the actual registered tools and source. Use after adding, renaming, or removing a tool, or as part of a live-audit pass.
Also in 4 projects that use this
Microsoft AzureSkillcomponent-release
Prepares a verifiable Agent Landing Zone UI release. Use for release branches, VERSION, changelog entries, tags, release notes, and compatibility evidence; never publish without explicit human approval.
Also in 4 projects that use this
- Microsoft AzureSkill
documentation-consistency
Keeps AI Landing Zone contributor, user, and operator documentation aligned with shipped Bicep behavior. Use for parameters, defaults, outputs, topology, deployment flow, operations, or releases.
Also in 8 projects that use this
rivet-devSkilllaunch-graphics
Generate agentOS marketing/launch graphics (launch & social heroes, code-snippet cards) from the committed generators in docs-internal/graphics. Use when asked to make, update, or render an agentOS launch image, social image, "agentOS Apps" graphic, or technical code-snippet image.
Also in 3 projects that use this
- +3 more from Grinv
Other versions196 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 196
- paperclipai/paperclip★ 112ksame name
- modelcontextprotocol/servers★ 92ksame name
- remotion-dev/remotion★ 72ksame name
- traefik/traefik★ 65ksame name
- usememos/memos★ 64ksame name
- tw93/Pake★ 63ksame name
- AmruthPillai/Reactive-Resume★ 45ksame name
- amruthpillai/reactive-resume★ 45ksame name
- reactive-resume/reactive-resume★ 45ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
186 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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adoptSkill
- commitSkill
- feature-cycleSkill
- parallel-lanesSkill
- reviewSkill
- session-handoffSkill
- update-docsSkill
- verificationSkill
- write-skillSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 186 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Before finishing a feature and reporting it done
- Distinctive: line 12
Before tagging or publishing a release
- Distinctive: line 13
When a change crosses component boundaries
- Very specific: line 17
Run the full chain: npm run check.
- Very specific: line 18
Run npm run check-arch — all architecture rules, including manifest classification.
- Distinctive: line 21
Update the state files (see the session-handoff skill), then commit with a message explaining WHY, not what.
- Distinctive: line 27
Never present a partial result as the whole.
“Common” is measured: kept by at least 6 in 10 of the 186 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
Release
The final pass before a change is considered shippable.
When to Use
- Before finishing a feature and reporting it done
- Before tagging or publishing a release
- When a change crosses component boundaries
Workflow
- Run the full chain:
npm run check. Cross-component changes additionally need Layer 3b (e2e) actually PASSing — a SKIP does not count. - Run
npm run check-arch— all architecture rules, including manifest classification. - Durable evidence: each feature's
verify-featureevidence and trail. Runnpm run vcr(check + check-arch + trail in.harness/trails/) only when no feature was verified, for example after a docs-only change. - Review what changed:
git diff,git status— only intended files, no debug artifacts, no OS files. - Update the state files (see the session-handoff skill), then commit with a message explaining WHY, not what.
- Finish with
npm run clean-checkon the clean tree and recordnpm run session-end.
Rules
- One logical operation per commit — the repo must be consistent after every commit.
- Never present a partial result as the whole; say what was not verified.
- External publication (push, publish, deploy) happens only with explicit authorization.
Quick Reference
npm run check— all layers, output read- e2e PASSed if the change crosses components (SKIP is not enough)
- Evidence trail recorded (by
verify-feature, ornpm run vcrwhen no feature was verified) - Diff reviewed — only intended changes
npm run clean-check— ALL PASS on the clean tree
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.