Tooluck logoTooluck
SKILL.md

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

install improve
# install the Citadel pack with the skills CLI
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)

skills/improve/SKILL.md

MITFull file
1# /improve — Autonomous Quality Engine
2
3## Orientation
4
5**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).
6
7**Don't use when:** Refactoring without a rubric (use `/refactor`), one-time code review (use `/review`), or debugging a specific bug (use `/systematic-debugging`).
8
9## Invocation
10
11```
12/improve {target} # Loop until plateau or all axes >= 8.0
13/improve {target} --n=3 # Run exactly N loops then stop
14/improve {target} --axis={name} # Force-attack a specific axis (skips scoring)
15/improve {target} --score-only # Score and report, no attack
16/improve {target} --continue # Resume from campaign state (used by daemon)
17/improve citadel # Targets Citadel itself
18```
19
20`target` is a slug that maps to `.planning/rubrics/{target}.md`.
21If no rubric exists, run Phase 0 first.
22
23## Campaign Mode
24
25When invoked with `--n` or `--continue`, improve operates in **campaign mode** and maintains a campaign file that daemon can attach to.
26
27**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

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

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

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates