changeset-doc-sync
Skill452 starsChanged 23 days agoApache-2.0View on GitHub
Read every doc in www and packages/kitcn/skills/kitcn, sync to active changeset(s), and track with checkmarks.
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 7 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Use this workflow when release docs must match current changeset content.
- Very specific: line 15
Run preflight migration review from /example before docs sync:
- Very specific: line 25
Run autogoal planning first:
- Very specific: line 26
Create or continue one docs/plans/<date>-changeset-doc-sync.md goal plan.
- Very specific: line 27
Use node .agents/skills/autogoal/scripts/create-goal-scratchpad.mjs --template task --title "changeset doc sync" when creating a new plan.
- Distinctive: line 32
Use changed changeset file(s) in the branch.
- Very specific: line 40
Keep /example crosswalk checklist in the goal plan in sync during the run.
- Distinctive: line 42
Read every listed doc and sync:
- Distinctive: line 43
Update docs where migration changes are required.
- Very specific: line 45
If unchanged, still check with note no change needed.
- Distinctive: line 51
No unchecked items remain.
- Distinctive: line 58
Do not summarize file coverage in the goal plan (for example, "56 files scanned").
- Distinctive: line 60
Every processed file must be marked:
- Very specific: line 65
Do not close the run until /example diff, changeset bullets, and updated docs are all cross-referenced.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Changeset Doc Sync
Use this workflow when release docs must match current changeset content.
Mandatory sequence
- Run preflight migration review from
/examplebefore docs sync:git diff --name-only -- examplegit diff --stat -- examplegit diff -- example- Save migration conclusions in the active
docs/plans/<date>-changeset-doc-sync.md. - Mandatory: build a
/examplechange checklist in that goal plan with one checkbox per changed file. - For each changed
/examplefile, record:- impacted doc file(s), or
- explicit
no doc impactjustification.
- Run
autogoalplanning first:- Create or continue one
docs/plans/<date>-changeset-doc-sync.mdgoal plan. - Use
node .agents/skills/autogoal/scripts/create-goal-scratchpad.mjs --template task --title "changeset doc sync"when creating a new plan. - Mandatory: the goal plan must include an exhaustive per-file checklist (every target doc as its own
- [ ]item).
- Create or continue one
- Resolve active changeset target(s):
- List
.changeset/*.mdexcluding.changeset/README.md. - Use changed changeset file(s) in the branch.
- Extract breaking/features/patches and migration snippets.
- List
- Build execution checklists in the goal plan:
- Include every file in:
www/**/*.mdwww/**/*.mdxpackages/kitcn/skills/kitcn/**/*.md
- Keep
/examplecrosswalk checklist in the goal plan in sync during the run.
- Include every file in:
- Read every listed doc and sync:
- Update docs where migration changes are required.
- Mark every file checked once synced.
- If unchanged, still check with note
no change needed. - For each
/examplechanged file, mark the corresponding crosswalk checkbox only after linked docs are verified.
- Completion gates:
/examplecrosswalk in the goal plan has zero unchecked file items.- The goal plan has zero unchecked file items.
- No unchecked items remain.
- The goal plan logs scanned/updated/unchanged totals.
- The goal plan maps key doc edits to concrete changeset bullets.
node .agents/skills/autogoal/scripts/check-complete.mjs docs/plans/<date>-changeset-doc-sync.mdpasses.
Non-negotiable checklist rules
- Do not summarize file coverage in the goal plan (for example, "56 files scanned").
You must list each file explicitly with its own checkbox. - Every processed file must be marked:
updated, orno change needed
- A run is incomplete if even one file remains unchecked in either checklist.
- Any changed
/examplefile without a mapped doc check orno doc impactnote is a hard failure. - Do not close the run until
/examplediff, changeset bullets, and updated docs are all cross-referenced.
Goal plan checklist template (required)
### Phase: Doc Sync Checklist (www)
- [ ] `www/content/docs/a.mdx` — pending
- [ ] `www/content/docs/b.mdx` — pending
### Phase: Doc Sync Checklist (packages/kitcn/skills/kitcn)
- [ ] `packages/kitcn/skills/kitcn/SKILL.md` — pending
- [ ] `packages/kitcn/skills/kitcn/references/setup/index.md` — pending
### Phase: /example-to-doc Crosswalk (required)
- [ ] `example/convex/shared/api.ts` -> `www/content/docs/cli/backend.mdx`, `www/content/docs/react/infer-types.mdx` — pending
- [ ] `example/src/lib/convex/crpc.tsx` -> `www/content/docs/react/index.mdx` — pending
- [ ] `example/src/lib/convex/rsc.tsx` -> `www/content/docs/nextjs/index.mdx`, `www/content/docs/server/server-side-calls.mdx` — pending
- [ ] `example/src/lib/convex/server.ts` -> `www/content/docs/nextjs/index.mdx` — pending
- [ ] `example/convex/functions/http.ts` -> `www/content/docs/server/http.mdx` — pending
- [ ] `example/convex/shared/types-typecheck.ts` -> `www/content/docs/react/infer-types.mdx` — pendingChecklist template
# Doc Sync Checklist
## Changesets
- [x] `.changeset/your-file.md`
## www docs
- [ ] `www/path/to/doc.mdx` — pending
## packages/kitcn/skills/kitcn docs
- [ ] `packages/kitcn/skills/kitcn/SKILL.md` — pending
- [ ] `packages/kitcn/skills/kitcn/references/setup/index.md` — pending
## Synced
- [x] `www/path/to/doc.mdx` — updated for `@convex/api` migration
- [x] `packages/kitcn/skills/kitcn/references/setup/index.md` — no change neededSuggested commands
git diff --name-only -- example
git diff --stat -- example
git diff -- example
find .changeset -maxdepth 1 -type f -name '*.md' ! -name 'README.md' | sort
find www -type f \( -name '*.md' -o -name '*.mdx' \) | sort
{ echo 'packages/kitcn/skills/kitcn/SKILL.md'; find packages/kitcn/skills/kitcn/references -type f -name '*.md' | sort; }In this repository54 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- .agents/skills/autoreview/AGENTS.mdAGENTS.md
- .agents/skills/autoreview/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- 4-ultraciteSkill
- agent-browser-issueSkill
- agent-native-reviewerSkill
- architecture-cleanupSkill
- autoclosureSkill
- autogoalSkill
- autoreviewSkill
- autoSkill
- avoid-feature-creepSkill
- better-auth-best-practicesSkill
- changeset-resolveSkill
- changesetSkill
- component-colocationSkill
- concave-paritySkill
- concaveSkill
- convex-release-auditSkill
- designSkill
- deslopSkill
- diagnosing-bugsSkill
- find-skillsSkill
- grill-with-visionSkill
- hard-cutSkill
- jotai-xSkill
- kitcnSkill
- linear-backlogSkill
- major-taskSkill
- next-dev-loopSkill
- nextjsSkill
- orchestratorSkill
- package-release-auditSkill
- prototypeSkill
- react-querySkill
- research-wikiSkill
- resolve-pr-feedbackSkill
- resolving-merge-conflictsSkill
- scenariosSkill
- shadcn-paritySkill
- sync-convex-authSkill
- sync-visionSkill
- taskSkill
- tddSkill
- testingSkill
- toastSkill
- to-milestoneSkill
- to-prdSkill
- turborepoSkill
- video-transcriptsSkill
- visionSkill
- walkthroughSkill
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.

