Skills Improve — Development skill for Claude Code
Improve one skill or evaluate the whole library against the quality rubric, then propose a prioritized plan and implement justified, tested changes.
How to install Skills Improve
Installs to ~/.claude/skills/m0st8fa-master-bughunter-skills-improve/SKILL.md
mkdir -p ~/.claude/skills/m0st8fa-master-bughunter-skills-improve && curl -fsSL https://raw.githubusercontent.com/M0st8fa/master-bughunter/HEAD/commands/skills-improve.md -o ~/.claude/skills/m0st8fa-master-bughunter-skills-improve/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Skills Improve does
description: Improve one skill or evaluate the whole library against the quality rubric, then propose a prioritized plan and implement justified, tested changes. Usage: /skills-improve argument-hint: "" allowed-tools: Read, Grep, Glob, WebFetch, WebSearch, Write, Edit, Bash(python3 *)
/skills-improve
Raise quality with evidence, not vibes. `$ARGUMENTS` = a skill name, or `all`.
Workflow
- Inspect the current implementation: `skills/
Alternatives in Development
- Triage PRs — Classify all open PRs by module, review state, scope, and architectural impact — produces a prioritized triage 12.6k ★
- Implement Plan — You are tasked with implementing an approved technical plan from thoughts/shared/plans/ 10k ★
- Flow Parallel — Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates 2.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Askit Build Skill
Create or improve an agentskills.io skill to the Advanced Skill Library Standard. Use to scaffold a new SKILL.
Gsc Analyst
Claude Code skill that turns Google Search Console exports into a prioritized SEO action plan: fitted CTR curv
Rubric Evaluator
Evaluate Claude Code and Codex skill directories with deterministic rubric checks and graded, fixable reports.
Improve Skill
Propose and apply targeted improvements to a specific Claude Code skill (self-improving skills AMEND layer)
Eval Improve
/eval-improve — Evaluate + Directed Improvement
Phoenix Claude Code
Monitor, evaluate, and improve your Claude Code usage with Arize Phoenix
Related Agents
Elite Coder
Implements a kimi-atlas change under the elite mandate — correctness-first, convention-matched, fully tested —
Brainswarm Critic
brainswarm critic role. Steelmans, then attacks, anonymised idea cards with justified critiques (target quote,
Plan Critic
Use WHEN a chosen direction from brainstorming needs to be pressure-tested before planning. Applies multi-lens