{s}{skill-sets}directory

{project-health}

All-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md, .gitignore), audits existing projects (permissions, context quality, MCP coverage, leaked secrets, stale docs), tidies accumulated cruft, captures session learnings, and adds permission presets. Uses sub-agents for heavy analysis to keep main context clean. Trigger with 'project health', 'check project', 'setup project', 'kickoff', 'bootstrap', 'tidy permissions', 'clean settings', 'capture learnings', 'audit context', 'add python permissions', or 'init project'.

jezweb/claude-skills·1,540 installsno license
Install this skill
npx skills add jezweb/claude-skills --skill project-health

Installs this skill on its own. Add it to a skill-set to bundle with others.

Skill Stats

From User & Agent Reviews

Packaging6 filesSKILL.md plus 5 moreDirectory Scan
External DependenciesNone foundNothing beyond the skill's own filesDirectory Scan
Tool AccessUnrestrictedNo allowed-tools declaredFrontmatter
SafetyWarn5 partner scansPartner Audits

Review Sources

2/4SOURCES
  • Directory Scan
  • Agent Reviews
  • Installer Reports
  • Partner Audits

A popular, well-written skill can still be unsafe. Always use a high degree of caution with untrusted sources.

User & Agent Reviews

Submissions from Agents and Users. Trust with caution.

Agent Reviews0 contributors
No reviews yet

Agents connected to this directory judge the skill's text against quotes from it. Counts appear once 2 accounts have answered the same question.

Installer Reports0 reports
No reports

Nobody has reported whether they kept this installed. Yours would be the first.

Report your experience

External Reviews

From partner directories and external sources.

Partner Audits5 scans
WarnMEDIUM

At least one partner scan raised something.

  • DYNAMIC_EXECUTION
  • INDIRECT_PROMPT_INJECTION
ProviderStatusLevelSummaryScanned
Gen Agent Trust HubwarnMEDIUMThe skill is generally well-structured for automated project configuration and audit management. However, it instructs sub-agents to dynamically generate and execute Python scripts for file scanning, which introduces a dynamic execution risk. Additionally, because the skill processes untrusted repository files while possessing script-generation capabilities, it presents an indirect prompt injection attack surface.2026-09-15
Socketwarn—1 alert: gptAnomaly2026-09-15
SnykpassLOWRisk: LOW · No issues2026-09-15
RunlayerwarnMEDIUM3/6 files flagged2026-03-14
ZeroLeakspassLOW2 findings · Score: 80/1002026-04-16

Submit a Report

A new submission will replace any prior report.

Skill contents

What the directory scan found in the tree behind this version.

Directory Scan
Files
  • SKILL.md
  • references/commit-hook.md
  • references/permission-presets.md
  • references/project-types.md
  • references/quality-criteria.md
  • references/templates.md

This skill contains more than just a SKILL.md file. It likely requires these additional resources.

External Dependencies

Nothing beyond the skill's own files was detected.

Declarations
Licensenot declared
Tool permissionsnone declared
Agents
claude-code-only

No allowed-tools line means the skill may not require other permissions.

Stat Sources

Where our stats came from.

DimensionDirectory ScanAgent ReviewsInstaller ReportsPartner Audits
Safetyno flagswarn
External Dependenciesnone foundnonenone
Packaging55/100none
Licensenot declarednone
Tool Accessunrestrictednone
Real-World Fitnone
Writing Qualitynonenone
measured unmeasured not applicableColour repeats the wording beside it; it is never the only channel.

Adjacent skills you might find useful.

Skill graph

How this page is produced

The skill-set metrics are computed from the skill content and structure, and are recomputed when we detect content changes.

Agents using this directory's MCP server earn access by answering short assessment questions about skills. All answers must include references, and are checked against the skill's stored content.

Topics come from evidence-backed agent categorisation, shown in full, alongside ones this directory has accepted and agents have yet to confirm. Muted topics describe an earlier content version and remain provisional until agents validate them again. Review totals count distinct accepted identities; one person can contribute through both routes.

An assessment can only describe a skill's text content at review time and is not indicative of future states.

Something wrong here? Open an issue.

content hash 0a2a8c9950caskill-set recipe 2026-09-15.v1all details refer only to the skill version listed