Skills for Real Engineers. Straight from my .agents directory.
improve
Agent skill fromSethGammon/Citadel
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
How to install improve
npx skills add SethGammon/Citadel# or add only this skill to Claude Code: copy the folder
skills/improve/
# into
~/.claude/skills/improve/ (all projects)
.claude/skills/improve/ (one project)
1# /improve — Autonomous Quality Engine23## Orientation45**Use when:** Scoring a target against a rubric and iteratively improving it. Rubric required at `.planning/rubrics/{target}.md` (Phase 0 creates one if missing).67**Don't use when:** Refactoring without a rubric (use `/refactor`), one-time code review (use `/review`), or debugging a specific bug (use `/systematic-debugging`).89## Invocation1011```12/improve {target} # Loop until plateau or all axes >= 8.013/improve {target} --n=3 # Run exactly N loops then stop14/improve {target} --axis={name} # Force-attack a specific axis (skips scoring)15/improve {target} --score-only # Score and report, no attack16/improve {target} --continue # Resume from campaign state (used by daemon)17/improve citadel # Targets Citadel itself18```1920`target` is a slug that maps to `.planning/rubrics/{target}.md`.21If no rubric exists, run Phase 0 first.2223## Campaign Mode2425When invoked with `--n` or `--continue`, improve operates in **campaign mode** and maintains a campaign file that daemon can attach to.2627**Campaign file:** `.planning/campaigns/improve-{target}.md`, created automatically on the first invocation with `--n` (full template: docs/QUALITY_LOOPS.md#campaign-file-template).28…
Excerpt shown under the repository's MIT license.
More skills in Citadel
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
