Skill of Skills
📄 skillActivePromisingmedium

Pensieve

by kingkongshot

tore your decisions and principles. Claude reads them to make better choices.

Stars

2.5k

Skill Type

🏗️ Code Scaffolding & Templates

Quality Score

119/200

License

MIT

Forks

257

Last Updated

Jun 11, 2026

Discovered

Mar 30, 2026

Validation

Passed

github.com/kingkongshot/Pensieve

Quality Breakdown

119/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
✓Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
○Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Multiple bash scripts in .src/scripts/ that perform system operations (install-hooks.sh, init-project-data.sh, maintain-auto-memory.sh, etc.)
  • Script execution capabilities through run-doctor.sh, run-hook.sh, run-migrate.sh, run-upgrade.sh which could modify project state
  • Git hook installation (install-hooks.sh) enables arbitrary code execution on developer events
  • Auto-memory and project state maintenance scripts that persist configuration changes
  • Multi-agent orchestration capability indicated by .codex/skills/pensieve-sync-to-main/agents/ directory with agent configuration files
  • Tool lifecycle management (init, migrate, upgrade, doctor) that modifies .pensieve/ directory structure and configuration