Skill Refactor
Analyzes bounded skill evidence, classifies root causes, and recommends a lifecycle lane such as keep, observe, improve through Skill Factory hardening, merge with approval, or retire with approval. Use when a skill is not working, a skill is not triggering correctly, evals or Tessl disagree, repeated failures need debugging, or skill performance issues need evidence-backed repair handoff items.
Install
npx skills add jscraik/Agent-Skills --skill skill-refactorgit clone --depth 1 https://github.com/jscraik/Agent-Skills.git /tmp/Agent-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Agent-Skills/Plugins/skill-factory/skills/data_fetch_analysis/skill-refactor ~/.claude/skills/skill-refactorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Skill Refactor Analyze bounded evidence about skill reliability and turn it into a lifecycle decision or a repair handoff. ## Philosophy Decide from bounded evidence; prefer narrow, reversible lifecycle moves. ## First-Principles Gate - Desired outcome: classify skill reliability evidence and route to keep, observe, improve, capture, merge/fold with approval, or retire with approval without mutating source prematurely. - User-specific constraints: use bounded evidence, preserve approval boundaries, route improvements through Skill Factory hardening, and map eval disagreement to SDK gates. - Rejected copied assumption: a failing skill should immediately be rewritten or retired. - Fundamental constraints: evidence strength controls scope; lifecycle decisions need approval when destructive; weak evidence cannot justify broad canonical changes. - Smallest effective mechanism: produce a lifecycle decision and concrete repair handoff items before edits. - Artifact decision: IMPROVE_EXISTING. - Rejected alternatives: retiring from weak evidence, merging without approval, or patching source before classifying root cause. - Evidence required: evidence anchors, root-cause labels, and repair items with expected SDK gate. - Validation proof: each finding cites one source and one owning gate. - Stop or pivot condition: if evidence is missing or untrusted, ask for bounded evidence instead of recommending a lifecycle move. ## When To Use
Details
- Skill name
skill-refactor- Repository
- jscraik/Agent-Skills
- Path
Plugins/skill-factory/skills/data_fetch_analysis/skill-refactor/SKILL.md- License
- Apache-2.0
- Repo updated
- 16 November 2026
FAQ
What does the Skill Refactor skill do?
Analyzes bounded skill evidence, classifies root causes, and recommends a lifecycle lane such as keep, observe, improve through Skill Factory hardening, merge with approval, or retire with approval. Use when a skill is not working, a skill is not triggering correctly, evals or Tessl disagree, repeated failures need debugging, or skill performance issues need evidence-backed repair handoff items.
How do I install the Skill Refactor skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add jscraik/Agent-Skills --skill skill-refactor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Skill Refactor popular?
It lives in jscraik/Agent-Skills, which has 9 GitHub stars and 4 forks.
Related skills
1password
9jscraik/Agent-Skills
Plan, diagnose, and validate 1Password CLI workflows. Use when tasks need op CLI sign-in, secret references, op run, op inject, item reads, env injection, or service-account secret access.
Agentation
9jscraik/Agent-Skills
Audit, validate, and troubleshoot Agentation integrations in frontend apps. Use when annotations, MCP registration, endpoint sync, webhook delivery, or watch mode readiness are failing.
Agents Md
9jscraik/Agent-Skills
Use when reviewing, creating, shrinking, or refactoring AGENTS.md and directly linked instruction guidance for stale or conflicting rules against current model documentation, scoped routing, deduplication, or progressive disclosure.
Sy Execution Plan
9jscraik/Agent-Skills
Plan how to implement one approved slice, including file targets, validation gates, rollback, and proof lanes. Use when a slice spec is accepted and the user needs the implementation order before code changes.
Skill Refactor
9jscraik/Agent-Skills
Scan Codex session history for skill failures, usage patterns, and coverage gaps. Use when the user wants daily skill-health monitoring or evidence-backed recommendations about installing, improving, merging, or pruning skills.
Talk Farley Vibe Coding Best We Can Do
9jscraik/Agent-Skills
Summarizes, explains, and answers questions about Dave Farley's talk 'Vibe Coding — Is this really the best we can do?', including key arguments, frameworks, and recommendations. Provides verbatim-cited explanations of Farley's three properties of programming languages, audits AI-coding setups against his three-problems framework, drafts BDD-style executable specifications, and outlines his continuous-delivery approach to AI-driven development. Use when the user asks about Dave Farley's talk on vibe coding, agentic programming, AI-generated tests, BDD-style executable specifications, problem-s
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.