cro-agent-skills / templates
CLAUDE.md0 starsChanged 22 days agoMITView on GitHub
Open only what the task needs. +local: also read the slot's .local.md. unwritten: create it from the code when first needed. Verbatim sources: docs/ref/.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.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
- project-startSkill
- 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
Files
<Project>
<One line: what it is.> Type: <App|WordPress|Shopify theme|Content> · Client: <name|the agency> · Repo: <private|client-shared|public|none>
Hard rules
<!-- Project-specific only; violation = data loss, leak, outage, client breach or money. ≤12 bullets. Never repeat global rules. No deploy line (global gate covers it). Soft rules go to docs/06-AGENTS.md. --><rule>
Stack
- <framework + version> ·
<DB>·<auth>· <host / process>
Commands
- Dev
<cmd>· Build<cmd>· Test<cmd>· Lint<cmd>
Docs map
Open only what the task needs. +local: also read the slot's .local.md. unwritten: create it from the code when first needed. Verbatim sources: docs/ref/.
| Need | Read |
| Goals, approved scope, client asks | docs/01-PRD.md |
| UI, tokens, components | docs/02-DESIGN.md |
| Structure, modules, decisions | docs/03-ARCHITECTURE.md |
| Schema, migrations, seeds | docs/04-DATABASE.md |
| Routes, endpoints, webhooks | docs/05-API.md |
| Autonomy, workflows, project skills | docs/06-AGENTS.md |
| Client, URLs, environments, access pointers | docs/07-README.md |
| Phase, task queue, blockers | docs/08-IMPLEMENTATION.md |
| Local setup, env var names | docs/09-SETUP.md |
| Feature specs, how features are built | docs/10-FEATURES.md |
| Auth, roles, security | docs/11-AUTH-SECURITY.md |
| MCP / AI tooling for this project | docs/12-MCP.md |
| Third-party services, tracking IDs | docs/13-INTEGRATIONS.md |
| Tests, QA checklists | docs/14-TESTING-QA.md |
| Gotchas, known issues | docs/15-DEBUGGING.md |
| Deploy, release, rollback | docs/16-DEPLOYMENT.md |
| What shipped when | docs/17-CHANGELOG.md |
<!-- Keep only rows for slots that apply to the type (see the standard §4). Mark missing files `unwritten`, files with a .local.md `+local`. -->N/A: <slots that cannot apply, or delete this line>
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.

