AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Dejavu Rules

skill-cmg8431-claude-dejavu-dejavu-rules · by cmg8431

Manage dejavu rules manually. Use when user says "add a rule", "remember this", "edit rule", "remove rule", "이거 기억해", "룰 추가해", or wants to manage CLAUDE.md rules through conversation.

↗ Website ↗ Repository
— No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-cmg8431-claude-dejavu-dejavu-rules

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-cmg8431-claude-dejavu-dejavu-rules)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Dejavu Rules? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Manage dejavu Rules

You can help the user manage their claude-dejavu rules through conversation.

Adding Rules

When the user states a preference or rule, use the add_rule MCP tool:

Examples:

  • "이 프로젝트에서는 pnpm만 써" → add_rule("This project uses pnpm, not npm.")
  • "항상 테스트 먼저 돌려" → add_rule("Always run tests before committing.")
  • "Remember to use semantic HTML" → add_rule("Use semantic HTML tags instead of generic divs.")

Or via CLI:

claude-dejavu rules add "This project uses pnpm, not npm."

Editing Rules

When the user wants to modify a rule:

  1. First show current rules using list_rules
  2. Then use edit_rule with the rule ID and new text
claude-dejavu rules edit r-001 "Use pnpm for all package operations, including scripts."

Removing Rules

claude-dejavu rules remove r-001

Reviewing Rules with Feedback

Show the user which rules are working and which aren't:

claude-dejavu rules feedback

This shows:

  • Fire count per rule (how many times it prevented a mistake)
  • Quality grade (A/B/C/D)
  • Dormant rules that might need removal

Guidelines

  • When adding rules, write them as clear, actionable instructions
  • Translate user's natural language into concise rule text
  • If the user speaks Korean/Japanese, still write the rule in English (Claude reads CLAUDE.md in English)
  • After adding/editing, confirm what was done and show the rule ID
  • Suggest reviewing with /dejavu or rules feedback periodically

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Databases