project-start
Skill0 starsChanged 22 days agoMITView on GitHub
Start, resume or switch to a named project using minimum required context when the user says work on, resume, continue, open, switch to or check a project.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- taljeon/plzdotheir own version, first seen Nov 1, 2026
- grace-method/grace-plugintheir own version, first seen Oct 25, 2026
- razbakov/skillstheir own version, first seen Oct 17, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- taljeon/plzdo★ 9same name
- razbakov/skills★ 5same name
- grace-method/grace-plugin★ 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 repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/setup-project-context/templates/CLAUDE.mdCLAUDE.md
- backend-architectureSkill
- build-review-loopSkill
- capability-intakeSkill
- competitor-market-analysisSkill
- context-auditSkill
- data-analysis-insightsSkill
- data-privacy-securitySkill
- dev-agentsSkill
- dev-patternsSkill
- frontend-system-designSkill
- idea-validatorSkill
- intellectual-property-licensingSkill
- international-legal-researchSkill
- legal-document-drafterSkill
- llm-councilSkill
- make-slidesSkill
- password-authentication-securitySkill
- privacy-data-protection-lawSkill
- project-estimation-planningSkill
- rea-researchSkill
- requirements-business-analystSkill
- secrets-credential-managerSkill
- seo-tech-stackSkill
- setup-project-contextSkill
- shopify-ui-auditSkill
- site-incidentSkill
- sop-process-builderSkill
- task-dispatchSkill
- technical-feasibilitySkill
- tech-research-intelligenceSkill
- update-mdSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
27 rules. 0 are common, 6 are distinctive, and 21 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
21
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
If yes, do not read the global project index.
- Very specific: line 19
If no, read only the matching entry from ~/.claude/project-index.md.
- Very specific: line 20
Use ~/.claude/context.md only as fallback when the project cannot be resolved from the lightweight index.
- Very specific: line 28
Always read the project index: <project>/CLAUDE.md, or <project>/.claude/CLAUDE.md where the docs are local-only (git repo with a remote).
- Very specific: line 34
Never go looking for a slot marked unwritten.
- Very specific: line 36
If there is no Docs map (legacy project), read selectively and offer setup-project-context migrate once:
- Very specific: line 37
Read <project>/rule.md only when permanent unique project rules affect the task.
- Very specific: line 38
Read <project>/docs/task.md only when continuing current work or checking active implementation.
- Very specific: line 39
Read <project>/docs/pending.md only when selecting next work or reviewing blockers.
- Very specific: line 40
Read <project>/docs/scope.md only when validating whether work is included.
- Very specific: line 41
Read <project>/docs/proposal.md only when checking commercial commitments or original timelines.
- Very specific: line 42
Read <project>/docs/completed-vs-scope.md only for delivery status, handover or scope-completion checks.
- Very specific: line 43
Read <project>/docs/changelog.md only for confirmed change history or release reporting.
- Very specific: line 44
Read <project>/docs/deploy.md only for push, release, deployment, rollback, tagging or production work.
- Very specific: line 45
Read <project>/context.md only when prior technical state is required.
- Very specific: line 46
Read <project>/DESIGN.md only for UI, layout, component or responsive work.
- Very specific: line 47
Read <project>/memory.md only for recurring issues or known gotchas.
- Very specific: line 48
Read <project>/spec.md only for architecture, API, schema, authentication, permissions, calculations, security or core workflows.
- Very specific: line 50
Check .claude/rules/ only for rules matching the affected work area.
- Very specific: line 52
Check .claude/skills/ only when a unique project workflow is required.
- Distinctive: line 57
Do not invoke implementation capabilities during project start unless the same request clearly requires specialised work.
- Very specific: line 58
When capability selection is required after project resolution, use task-dispatch.
- Distinctive: line 62
Do not read files only because they exist.
- Distinctive: line 63
Do not load unrelated project folders.
- Distinctive: line 64
Do not load full registry information when the requested project is already identified.
- Very specific: line 65
Do not read spec.md for ordinary copy, styling or layout work.
- Distinctive: line 66
Do not read infrastructure or deployment files unless those actions are requested.
“Common” is measured: kept by at least 6 in 10 of the 3 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
Start or Resume Project Work
Requested project or task: $ARGUMENTS
Objective
Resolve the requested project and load only the documentation required to begin the current task.
Process
- Determine whether the current working directory is already the requested project.
- If yes, do not read the global project index.
- If no, read only the matching entry from
~/.claude/project-index.md. - Use
~/.claude/context.mdonly as fallback when the project cannot be resolved from the lightweight index.
- Resolve only necessary information:
- Project name.
- Local project path.
- Platform or short stack summary.
- Environment, hosting or deployment information only when the task requires it.
Always read the project index:
<project>/CLAUDE.md, or<project>/.claude/CLAUDE.mdwhere the docs are local-only (git repo with a remote). If it has a## Docs map(v2 project), read only the mapped slots the task needs, plus the slot's.local.mdwhere the map says+local:- resume / next work →
docs/08-IMPLEMENTATION.md(+.local.md§Checkpoint) - UI, layout, components →
02· structure, refactor →03· schema →04· endpoints, webhooks →05 - agent workflow, project skills →
06· URLs, access, client →07· local setup →09· feature work →10(+01for scope) - auth, permissions, security →
11· MCP tooling →12· third-party services →13· tests, QA →14 - bug, recurring issue →
15· push, release, deploy, rollback →16· change history →17 - Never go looking for a slot marked
unwritten; create it from the code only when the task needs it (standard:~/.claude/references/project-docs-standard.md).
If there is no Docs map (legacy project), read selectively and offer
setup-project-context migrateonce:- Read
<project>/rule.mdonly when permanent unique project rules affect the task. - Read
<project>/docs/task.mdonly when continuing current work or checking active implementation. - Read
<project>/docs/pending.mdonly when selecting next work or reviewing blockers. - Read
<project>/docs/scope.mdonly when validating whether work is included. - Read
<project>/docs/proposal.mdonly when checking commercial commitments or original timelines. - Read
<project>/docs/completed-vs-scope.mdonly for delivery status, handover or scope-completion checks. - Read
<project>/docs/changelog.mdonly for confirmed change history or release reporting. - Read
<project>/docs/deploy.mdonly for push, release, deployment, rollback, tagging or production work. - Read
<project>/context.mdonly when prior technical state is required. - Read
<project>/DESIGN.mdonly for UI, layout, component or responsive work. - Read
<project>/memory.mdonly for recurring issues or known gotchas. - Read
<project>/spec.mdonly for architecture, API, schema, authentication, permissions, calculations, security or core workflows.
- resume / next work →
- Check
.claude/rules/only for rules matching the affected work area. - Check
.claude/skills/only when a unique project workflow is required.
Capability Rule
- Project resolution does not require a specialist agent, MCP or plugin.
- Do not invoke implementation capabilities during project start unless the same request clearly requires specialised work.
- When capability selection is required after project resolution, use
task-dispatch.
Token Rules
- Do not read files only because they exist.
- Do not load unrelated project folders.
- Do not load full registry information when the requested project is already identified.
- Do not read
spec.mdfor ordinary copy, styling or layout work. - Do not read infrastructure or deployment files unless those actions are requested.
Initial Response After Resolution
State only:
Project resolved: <project-name>
Docs: v2 | legacy
Context loaded: <files actually read>
Task focus: <requested task or next confirmed task>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.

