Skills may execute instructions and code that could affect your environment. Marketplace scans reduce risk but do not guarantee safety. Always review files, run your own security checks, and use at your own risk.
promote
Security Scan Summary
Status: Safe
Source: Syntic Skills registry
Automated security scan completed with no high-risk patterns detected. Manual review is still required.
About This Skill
Use when graduating a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement.
Downloadable SKILL.md
Download SKILL.md and place it in your Syntic skills folder. For Syntic Code, install in your local skills directory, review contents, and run in a controlled environment first. Acknowledge the risk notice above to enable the download.
--- name: promote description: Use when graduating a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement. category: Engineering version: 1.0.0 tools: [] --- # Promote β Graduate Learnings to Rules Move a proven pattern from auto-memory into the project's rule system, where it becomes enforced instruction. ## Workflow ### Step 1: Parse the Pattern Extract from user input: - **What**: The concrete fact or pattern - **Why it matters**: Context - **Scope**: Project-specific or global? ### Step 2: Search Auto-Memory Find related entries in MEMORY.md. Show matching entries and confirm they match the user's intent. ### Step 3: Determine Target | Pattern Scope | Target | Example | |---|---|---| | Entire project | `./CLAUDE.md` | "Use pnpm, not npm" | | Specific file types | `.claude/rules/<topic>.md` | "API handlers need validation" | | All projects | `~/.claude/CLAUDE.md` | "Prefer explicit error handling" | ### Step 4: Distill Rule Transform from descriptive note to prescriptive instruction: - One line per rule when possible - Imperative voice: "Use X", "Always Y", "Never Z" - Include the command or example, not just concept - No backstory; just the instruction Example: - Before: "The project uses pnpm workspaces. When I tried npm install it failed." - After: "Package manager: pnpm (not npm). Use `pnpm install`." ### Step 5: Write to Target **For CLAUDE.md:** 1. Read existing CLAUDE.md 2. Find the appropriate section or create one 3. Append the new rule 4. If exceeding 200 lines, suggest `.claude/rules/` instead **For `.claude/rules/`:** 1. Create file if missing 2. Add YAML frontmatter with `paths` if scoped 3. Write rule content ### Step 6: Clean Up Auto-Memory After promoting, remove the original entry from MEMORY.md. Ask user to confirm. ### Step 7: Confirm Completion Verify: rule distilled, written to target, removed from auto-memory, CLAUDE.md/rules updated. ## Promotion Decision Guide ### Promote When: - Pattern appeared 3+ times in auto-memory - Corrected Claude about it multiple times - Any contributor should know it - It prevents recurring mistakes ### Don't Promote When: - One-time debugging note - Session-specific context - Might change soon - Already covered by existing rules ## CLAUDE.md vs .claude/rules/ | Use CLAUDE.md for | Use .claude/rules/ for | |---|---| | Global project rules | File-type-specific patterns | | Build commands | Testing conventions | | Architecture decisions | API design rules | | Team conventions | Framework-specific gotchas |
Bundle Download
Includes SKILL.md and bundled support files where provided. Risk acknowledgement is required.
Install Targets
Syntic App
- 1. Create a dedicated folder for this skill in your local skills library.
- 2. Place SKILL.md into that folder.
- 3. Restart Syntic and invoke this skill on matching tasks.
Syntic Code (CLI)
- 1. Save SKILL.md in your local Syntic Code skills directory.
- 2. Keep related files in the same skill folder.
- 3. Run in a safe environment and validate outputs.
Source
https://github.com/alirezarezvani/claude-skills/blob/main/engineering-team/self-improving-agent/skills/promote/SKILL.md
Open Source LinkRelated Skills
a11y-audit
Use when auditing WCAG 2.2 Level A/AA accessibility, fixing violations in React, Next.js, Vue, Angular...
Engineeringadversarial-reviewer
Use when reviewing recent code changes or a PR before merge and you want a genuinely critical review, not...
Engineeringagent-designer
Use when architecting multi-agent systems, selecting orchestration patterns, or evaluating agent performance.
Engineeringagent-harness
Use when building bounded agentic loops with verified task execution and state machines.