Menu
Extract observed workflow into a reusable skill
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Create new specialized agent
Audit the intelligence layer for duplication, drift, size, hardcoded paths and framing
Disable IDE adapter and clean up output
Enable IDE adapter for intelligence-sync
Capture session lessons and apply to intelligence/ after approval
Create new skill
| name | intelligence-extract-skill |
| description | Extract observed workflow into a reusable skill |
| argument-hint | <skill-name-hint> [target: skill|rule|agent] |
Use when a workflow that ran during this session should become a reusable artifact — same sequence will be needed again by this user or by someone else using shared intelligence. Starts from observed session behavior instead of design-from-scratch.
intelligence-add-skillintelligence-add-skill — design from scratch / from codebase analysisintelligence-extract-skill — extract from the conversation that just happenedBoth end at the same artifact format. Extract starts from observed behavior, so the steps already exist as real working procedure.
Identify the pattern from session: list the concrete steps the assistant or user-and-assistant performed during the conversation. Include user decisions at each branch and assistant actions.
Generalize: strip session-specific details (file names, dates, specific phrasing), keep the repeatable structure. The artifact should work for the next instance of this task type, not just the one that ran.
Determine artifact type:
intelligence-learn-from-context for single preferences from session)Determine domain prefix (for skill / agent): reuse the existing domain when one fits — list intelligence/skills/ and intelligence/agents/. Derive from repo structure only when no existing domain matches.
Determine naming (for skill): <domain>-<verb>-<noun> with convention verbs — add- (atomic create), create- (orchestrator), update- (modify), run- (execute), review- (read-only analysis).
Check for matching agent: if creating a skill and an agent already covers the domain, link via agent: frontmatter. If no matching agent and one is warranted, call intelligence-add-agent first.
Write the artifact by delegating to the relevant intelligence-add-* skill (intelligence-add-skill / intelligence-add-rule / intelligence-add-agent). The add-* skills carry the authoring conventions — no need to duplicate them here.
Run sync: /intelligence-sync to distribute to all enabled IDE targets.
Follow the Authoring Discipline section in docs/CONVENTIONS.md when writing the artifact body — size budgets (<500 lines for SKILL.md body), imperative form, explain WHY, reserve absolute language for true invariants, lead with positive defaults.
intelligence-add-skill — design new skill from scratchintelligence-learn-from-context — capture a behavioral preference from session (often → rule update)intelligence-review-skills — audit existing artifacts for duplication, staleness, discipline issues