From pensieve
Routes intents to tools managing project knowledge base: init setups, upgrade/migrate handle changes, doctor checks health, self-improve archives findings, loop runs workflows.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pensieve:pensieveThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Route user requests to the correct tool. When uncertain, confirm first.
decisions/README.mdknowledge/README.mdknowledge/taste-review/content.mdmaxims/README.mdpipelines/README.mdreferences/directory-layout.mdreferences/shared-rules.mdreferences/tool-boundaries.mdtools/core/doctor_engine.pytools/core/pensieve_core.pytools/core/schema.jsontools/doctor/_doctor.mdtools/doctor/migrations/README.mdtools/doctor/scripts/check-frontmatter.shtools/doctor/scripts/run-doctor.shtools/doctor/scripts/scan-structure.shtools/init/_init.mdtools/loop/DESIGN.template.mdtools/loop/README.mdtools/loop/REQUIREMENTS.template.mdRoute user requests to the correct tool. When uncertain, confirm first.
init | Version uncertainty → upgrade | Migration/residue uncertainty → migrate<USER_DATA_ROOT>/knowledge/ first, then use self-improve to write findingsself-improve | Complex task needing decomposition → loopupgrade; migration/residue cleanup goes through migrate.decision/pipeline must have at least one [[...]] link.Full rules in
references/shared-rules.md
Before executing any tool, read its ### Use when section to confirm applicability. For tool boundaries and redirect rules, see references/tool-boundaries.md.
| Intent | Tool spec (read first) | Trigger words |
|---|---|---|
| Initialize | <SYSTEM_SKILL_ROOT>/tools/init/_init.md | init, initialize |
| Version update | <SYSTEM_SKILL_ROOT>/tools/upgrade/_upgrade.md | upgrade, version |
| Structure migration | <SYSTEM_SKILL_ROOT>/tools/migrate/_migrate.md | migrate, migration, clean old paths |
| Health check | <SYSTEM_SKILL_ROOT>/tools/doctor/_doctor.md | doctor, check, format check |
| Archive experience | <SYSTEM_SKILL_ROOT>/tools/self-improve/_self-improve.md | self-improve, archive, reflect |
| Iterative execution | <SYSTEM_SKILL_ROOT>/tools/loop/_loop.md | loop, iterative execution, execute pipeline |
<SYSTEM_SKILL_ROOT> is injected by the SessionStart hook; user data path is fixed at <project>/.claude/skills/pensieve/.
npx claudepluginhub mamajiaa/pensieve-claude-plugin --plugin pensieveManages SSOT, project memory, and cross-tool memory search. Handles decisions.md, patterns.md, SSOT promotion, migration, merging, and sync. Use to save learnings or search past decisions.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.