Tidy Settings
Sort, dedupe, and audit Claude settings.json / settings.local.json at user/project level. Flags risky permissions, broken references, glob-subsumed entries, and cross-file duplicates. Mechanical fixes auto-apply; judgment calls become triage items.
Install
npx skills add flurdy/agent-skills --skill tidy-settingsgit clone --depth 1 https://github.com/flurdy/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/tidy-settings ~/.claude/skills/tidy-settingsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Tidy Settings Occasional housekeeping on your Claude permissions. Settings files accumulate cruft: the same permission added narrowly five times, references to skills/scripts that no longer exist, redundant entries that one user-level rule already covers, and the occasional risky `Bash(curl:*)` you wish you hadn't accepted. This skill cleans the mechanical noise itself and surfaces the judgment-heavy items for your review. ## When to use - Periodically (every few weeks), when settings files feel cluttered. - After a long stretch where you've been clicking "Yes" to permission prompts and want to see what stuck. - Before sharing or committing a project-level `settings.json` — to make sure it's tidy and free of personal/local lines. Complementary to `fewer-permission-prompts` (which adds permissions); this *cleans* them. ## What it does **Auto-applied (mechanical, safe):** - Canonical sort: arrays grouped by tool prefix (`Bash`, `Edit`, `Read`, `Write`, `WebFetch`, `WebSearch`, `Skill`, `Task`, `mcp__*`), alphabetical within group. - Exact dedupe. - Backup files (`.bak`) written alongside each modified file. **Reported for your judgment (never auto-removed):** - **Risk flags** — entries matching known-risky patterns (`Bash(rm:*)`, `Bash(curl:*)`, `WebFetch(*)`, `Read(//...)`, unrestricted Edit/Write, etc.). - **Broken refs** — `Bash(~/path/...)` or `Bash(/abs/path/...)` pointing at missing files; `Skill(name)` for skills not installed.
Details
- Skill name
tidy-settings- Repository
- flurdy/agent-skills
- Path
skills/tidy-settings/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Tidy Settings skill do?
Sort, dedupe, and audit Claude settings.json / settings.local.json at user/project level. Flags risky permissions, broken references, glob-subsumed entries, and cross-file duplicates. Mechanical fixes auto-apply; judgment calls become triage items.
How do I install the Tidy Settings skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add flurdy/agent-skills --skill tidy-settings. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Tidy Settings popular?
It lives in flurdy/agent-skills, which has 9 GitHub stars and 0 forks.
Related skills
Architect
9flurdy/agent-skills
Architecture and implementation planning gate for complex or high-blast-radius work. Produces evidence-backed decisions, reviewable slices, acceptance evidence, and conditional human review ownership without editing code.
Artifact Hygiene
9flurdy/agent-skills
Run a local-only, read-only advisory audit of publishable working-tree files and unpublished branch history with redaction-safe findings.
Backlog Groom
9flurdy/agent-skills
Auto-detects workspace unfinished backlogs across unique stores; otherwise local open beads. Flags thin prose, missing labels, drift, lifecycle and duplicates. Report-only; mutations need approval, destructive ones individually.
Watch Release
9flurdy/agent-skills
Start a recurring release-gatekeeper loop — runs /release-manager on an adaptive cadence (fast when something is in flight, backing off when settled) until end of day. Prompts to push / defer / cancel as services become ready; runs attended.
Prompt Patterns
9flurdy/agent-skills
Find recurring substantial prompts in local Pi and Claude Code history and suggest reusable prompt-template drafts; metadata-first, redacted, bounded and read-only.
Blind Spot
5adelrioj/claude-skills
Use BEFORE starting work on a task to surface the unknown-unknowns you're about to walk into but can't see. Dispatches a fresh-context Claude subagent that hunts what you don't know you don't know about the codebase, the domain, and the decisions ahead, calibrated to your stated experience, then reports ranked, evidence-backed findings and fixes nothing. Triggers on: blind spot pass, blindspot, unknown unknowns, what don't I know, what am I missing, help me prompt better, I know nothing about, teach me my unknowns, before I start, de-risk this task, surface my blind spots.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.