ai-fication-kit / rules
Cursor rule3 starsChanged 4 months agoApache-2.0View on GitHub
Dry-run the add-feature workflow for a proposed feature — friction report and per-phase readiness score, without writing code.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/add-feature.mdcCursor rule
- .cursor/rules/adversarial-audit.mdcCursor rule
- .cursor/rules/ai-knowledge-layer.mdcCursor rule
- .cursor/rules/check-drift.mdcCursor rule
- .cursor/rules/cold-start.mdcCursor rule
- .cursor/rules/create-feature-catalog.mdcCursor rule
- .cursor/rules/fix-bug.mdcCursor rule
- .cursor/rules/post-cold-start-verification.mdcCursor rule
- .cursor/rules/review-agent-config.mdcCursor rule
- .cursor/rules/review-change.mdcCursor rule
- .cursor/rules/verify-ai-readiness.mdcCursor rule
- add-featureSkill
- cold-startSkill
- deep-testSkill
- fix-bugSkill
- review-changeSkill
- add-featureSkill
- adversarial-auditSkill
- check-docsSkill
- check-driftSkill
- cold-startSkill
- create-feature-catalogSkill
- fix-bugSkill
- implement-specSkill
- perform-feature-add-simulationSkill
- post-cold-start-verificationSkill
- review-agent-configSkill
- review-changeSkill
- verify-ai-readinessSkill
The file
Files
--- description: Dry-run the add-feature workflow for a proposed feature — friction report and per-phase readiness score, without writing code. alwaysApply: false --- <!-- Copyright (c) 2026 Kunal Suri (CEA LIST). All rights reserved. --> Simulate adding the feature the user names — WITHOUT writing a single line of code. This is a pre-flight check of both the plan and the knowledge layer. ## Phases to walk (score each: smooth / friction / blocked) 1. **Locate** — can MODULE_MAP + FEATURE_MAP/CATALOG identify the target modules without crawling? Name them. 2. **Plan** — draft the touch list per layer; note Stability of every file you'd change. Any `frozen` or `?` file ⇒ blocked pending human approval. 3. **Verify** — which suites would prove it works; do they exist and are commands confirmed? 4. **Knowledge update** — which ai/ files would need updating after the change? ## Output A friction report in chat (and, if asked, saved to ai/analysis/audit-reports/): per-phase score with the specific missing knowledge that caused friction, total estimated context cost, and a go / no-go recommendation. Knowledge gaps found here are the cheapest bugs you will ever fix — file each as an audit TODO.
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.

