pensieve

Solid

Project knowledge base and workflow router. knowledge/ caches previously explored file locations, module boundaries, and call chains for direct reuse; decisions/maxims are established architectural decisions and coding standards -- follow, don't re-debate; pipelines are reusable workflows; short-term/ holds new conclusions temporarily, promoted or deleted upon expiry. Use self-improve to capture new insights after completing tasks. Provides five tools: init, upgrade, migrate, doctor, self-improve.

Data & Documents 2,517 stars 259 forks Updated 2 weeks ago MIT

Install

View on GitHub

Quality Score: 89/100

Stars 20%
100
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
54
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Pensieve Route user requests to the correct tool. When in doubt, confirm first. ## Routing - Init: Initialize the current project's user data directory and populate seed files. Tool spec: `.src/tools/init.md`. - Upgrade: Refresh Pensieve skill source code in the global git clone. Tool spec: `.src/tools/upgrade.md`. - Migrate: Structural migration and legacy cleanup. Tool spec: `.src/tools/migrate.md`. - Doctor: Read-only scan of the current project's user data directory. Tool spec: `.src/tools/doctor.md`. - Self-Improve: Extract reusable conclusions and write to user data. Tool spec: `.src/tools/self-improve.md`. - Refine: Refine the knowledge base (triage five-question review + compress abstraction). Tool spec: `.src/tools/refine.md`. - Graph View: Read `<project-root>/.pensieve/.state/pensieve-user-data-graph.md`. ## Project Data Project-level user data is stored in `<project-root>/.pensieve/`. See `.pensieve/state.md` for the current project's lifecycle state; see `.pensieve/.state/pensieve-user-data-graph.md` for the knowledge graph (read on demand).

Details

Author
kingkongshot
Repository
kingkongshot/Pensieve
Created
11 months ago
Last Updated
2 weeks ago
Language
Shell
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

Data & Documents Solid

capture-knowledge

Capture structured knowledge about a code entry point and save it to the knowledge docs. Use when users ask to document, understand, or map code for a module, file, folder, function, or API.

1,213 Updated today
codeaholicguy
Data & Documents Featured

pi-planning-with-files

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.

22,057 Updated today
OthmanAdi
Data & Documents Featured

tutor-setup

Transforms knowledge sources into an Obsidian StudyVault. Two modes: (1) Document Mode — PDF/text/web sources → study notes with practice questions. (2) Codebase Mode — source code project → onboarding vault for new developers. Mode is auto-detected based on project markers in CWD.

900 Updated 2 months ago
RoundTable02
Data & Documents Listed

vibe-research

Set up and maintain a Vibe Research project with bi-directional sync between experimental code, paper.md, and developer docs. Use when starting a research project, managing experimental code, maintaining research documentation, creating academic papers, writing research logs, updating project docs, migrating an existing project to Vibe Research structure, or when the user mentions vibe research, paper sync, research log, experiment tracking, project migration, partial migration, incremental migration, doc update, or bi-directional sync between code and paper.

20 Updated 2 months ago
Zhangyanbo