Automated summary
Synthesizes raw session data into structured Obsidian-compatible markdown notes with automatic frontmatter, tags, and links.
Strengths
- Automates creation of project and session notes
- Smart tag generation based on code and commit analysis
- Bidirectional linking for seamless navigation
Limitations
- Depends on quality and completeness of harvested data
- May require manual adjustments after generation
- Rigid structure may not fit all note-taking styles
Use this skill when you need to maintain a structured and interconnected knowledge base from development sessions.
Avoid it if you prefer free-form note-taking without a fixed schema or if input data is inconsistent.
Security analysis
SafeThe skill only uses safe tools (Read, Write, Grep, Glob) to read cached data and write markdown notes to a specified directory. No shell execution, network access, or data exfiltration risks are present. The Python script mentioned is not automatically executed; the agent would implement the synthesis using its own capabilities.
No concerns found
How this analysis is madeExamples
Synthesize notes from today's session for the ATLAS-main project.Create project notes for ATLAS-main.Forge knowledge from all cached harvest data.name: knowledge-forge description: | Synthesizes harvested session data and project analysis into structured Obsidian-compatible markdown notes with proper frontmatter, tags, and links.
Triggers: "synthesize notes", "create project notes", "forge knowledge", "/forge" version: 1.0.0 author: Claude Code allowed-tools:
- Read
- Write
- Grep
- Glob
Knowledge Forge
Transforms raw harvested data into beautiful, interconnected Obsidian notes.
What It Creates
Session Notes (Daily Rollups)
---
date: 2026-01-19
project: ATLAS-main
type: session-log
tags: [devlog, atlas, python, api]
commits: 5
lines_changed: "+234/-45"
---
# Session Log: ATLAS-main
## Summary
Implemented chat API endpoints and added comprehensive test coverage.
## Commits
- `abc1234` feat(api): add chat endpoint
- `def5678` test: add API client tests
- `ghi9012` fix: handle timeout errors
## Files Changed
| File | Changes |
|------|---------|
| src/api/client.py | +45/-12 |
| tests/test_api.py | +120/-0 |
## Decisions Made
- Used httpx for async HTTP support
- Implemented exponential backoff for retries
## Related
- [[ATLAS-main/_index]]
- [[2026-01-18]] (previous session)
Project Index Notes
---
project: ATLAS-main
type: project-index
created: 2025-10-15
last_updated: 2026-01-19
status: active
tags: [project, atlas, python, ai]
---
# ATLAS-main
> AI-powered knowledge management and agent orchestration platform.
## Quick Stats
| Metric | Value |
|--------|-------|
| Total Lines | 45,230 |
| Languages | Python, TypeScript, YAML |
| Commits | 847 |
| Contributors | 3 |
## Tech Stack
- **Backend**: FastAPI, LangChain
- **Frontend**: Next.js, Tailwind
- **Database**: PostgreSQL, Qdrant
- **Infrastructure**: Docker, Vercel
## Recent Activity
![[sessions/2026-01-19]]
![[sessions/2026-01-18]]
## Architecture
![[architecture]]
## Changelog
![[changelog]]
Architecture Notes
Auto-generated from codebase analysis:
---
project: ATLAS-main
type: architecture
generated: 2026-01-19
---
# Architecture: ATLAS-main
## Directory Structure
ATLAS-main/ ├── src/ │ ├── api/ # FastAPI endpoints │ ├── agents/ # LangChain agents │ ├── models/ # Pydantic models │ └── utils/ # Shared utilities ├── dashboard/ # Next.js frontend ├── tests/ # Test suite └── docs/ # Documentation
## Key Components
...
Tag Generation
Automatically generates tags based on:
- Tech stack detected
- File types modified
- Commit message keywords
- Project category
Example tag extraction:
content = "Implemented FastAPI endpoint for chat"
# Generates: [api, fastapi, chat, backend]
Link Generation
Creates bidirectional links:
[[project/_index]]- Project home[[sessions/YYYY-MM-DD]]- Daily sessions[[Developer-Log/YYYY-MM-DD]]- Cross-project daily[[project/architecture]]- Architecture docs[[project/changelog]]- Changelog
Usage
# Synthesize from cached harvest data
python synthesize.py --input ~/.cache/devlog/ATLAS_20260119.json
# Synthesize all pending cache files
python synthesize.py --all
# Preview without writing
python synthesize.py --dry-run --input data.json
Output Locations
Notes are written to Vaultage:
~/Documents/Vaultage/
├── 01_Projects/
│ └── {project}/
│ ├── _index.md
│ ├── sessions/
│ │ └── YYYY-MM-DD.md
│ ├── architecture.md
│ └── changelog.md
└── 06_Metadata/
└── Developer-Log/
└── YYYY-MM-DD.md
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/knowledge-forge-mmh8qqf5/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/knowledge-forge-mmh8qqf5' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/knowledge-forge-mmh8qqf5/download' --output '.skill-downloads/knowledge-forge-mmh8qqf5/SKILL.md.part' && mv '.skill-downloads/knowledge-forge-mmh8qqf5/SKILL.md.part' '.skill-downloads/knowledge-forge-mmh8qqf5/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/knowledge-forge-mmh8qqf5/SKILL.md' && test -s '.skill-downloads/knowledge-forge-mmh8qqf5/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/knowledge-forge' && cp -R '.skill-downloads/knowledge-forge-mmh8qqf5' '.claude/skills/knowledge-forge'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/knowledge-forge-mmh8qqf5'openskills read 'knowledge-forge-mmh8qqf5'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/knowledge-forge-mmh8qqf5/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.