Not in the top 1,000 by GitHub stars

Totoro-qaq/Cobsidian

Agent-agnostic workflow skill for maintaining Obsidian knowledge bases

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/cobsidian/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

fc88b6e21108 → fc88b6e21108

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → fc88b6e21108

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit fc88b6e21108a4e3f38da110ec3e020a060493fb

13GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 202613

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

cobsidian

When your agent uses it

Use when a user asks to organize, save, compare, review, map, or dissect conversations and source material into an Obsidian vault or Markdown knowledge base, including Chinese requests about 知识库, 笔记, 双链, 学习模式, 项目模式, 复盘模式, 对比模式, 索引模式, 捕获模式, or 拆解模式.

What it loads into context

Frontmatter

98 tokens

Always available to the agent

SKILL.md

2,377 tokens

When the skill is activated

Reference documents

10,799 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Core Principle
  2. Iron Law
  3. Response Language
  4. Vault Resolution
  5. Mode Routing
  6. Host Routing
  7. Knowledge Read
  8. Common Workflow
  9. Write Rules
  10. Red Flags
  11. Helper Scripts
  12. Completion Report

Scripts executed separately

  • mcp_server.py
  • scripts/cobsidian_config.py
  • scripts/dry_run.py
  • scripts/dsh_bridge.py
  • scripts/duplicates.py
  • scripts/find_duplicates.py
  • scripts/knowledge_read.py
  • scripts/note_identity.py
  • scripts/preflight.py
  • scripts/quality_eval.py
  • scripts/retrieval.py
  • scripts/scan_vault.py
  • scripts/suggest_backlinks.py
  • scripts/validate_notes.py
  • scripts/validate_skill.py
  • scripts/write_executor.py

Files

  • SKILL.mdcore11,165 bytes
  • SKILL.mdcore11,165 bytes
  • agents/claude.mddoc1,606 bytes
  • agents/openai.yamlasset364 bytes
  • mcp_server.pyruns12,988 bytes
  • references/backlink-policy.mddoc709 bytes
  • references/hosts/antigravity.mddoc2,289 bytes
  • references/hosts/claude-code.mddoc2,516 bytes
  • references/hosts/codex.mddoc2,683 bytes
  • references/hosts/cursor.mddoc2,254 bytes
  • references/hosts/deepseek-harness.mddoc3,692 bytes
  • references/hosts/github-copilot-cli.mddoc2,309 bytes
  • references/hosts/hermes.mddoc2,279 bytes
  • references/hosts/kimi-code.mddoc2,386 bytes
  • references/hosts/mcp.mddoc2,405 bytes
  • references/hosts/opencode.mddoc2,324 bytes
  • references/hosts/pi.mddoc2,330 bytes
  • references/markdown-style.mddoc565 bytes
  • references/modes/capture.mddoc2,293 bytes
  • references/modes/comparison.mddoc2,294 bytes
  • references/modes/dissection.mddoc5,206 bytes
  • references/modes/index.mddoc2,272 bytes
  • references/modes/learning.mddoc2,340 bytes
  • references/modes/project.mddoc2,386 bytes
  • references/modes/review.mddoc2,303 bytes
  • references/note-types.mddoc2,383 bytes
  • references/preflight.mddoc2,805 bytes
  • scripts/cobsidian_config.pyruns6,877 bytes
  • scripts/dry_run.pyruns12,414 bytes
  • scripts/dsh_bridge.pyruns2,541 bytes
  • scripts/duplicates.pyruns4,267 bytes
  • scripts/find_duplicates.pyruns2,212 bytes
  • scripts/knowledge_read.pyruns6,297 bytes
  • scripts/note_identity.pyruns8,105 bytes
  • scripts/preflight.pyruns6,239 bytes
  • scripts/quality_eval.pyruns9,921 bytes
  • scripts/retrieval.pyruns5,821 bytes
  • scripts/scan_vault.pyruns4,308 bytes
  • scripts/suggest_backlinks.pyruns2,246 bytes
  • scripts/validate_notes.pyruns3,214 bytes
  • scripts/validate_skill.pyruns2,056 bytes
  • scripts/write_executor.pyruns14,453 bytes
Read SKILL.md

# Cobsidian

## Core Principle

Maintain the vault as a linked knowledge system. Do not just generate a standalone Markdown file.

## Iron Law

```text
NEVER WRITE TO THE VAULT WITHOUT SEARCHING EXISTING NOTES FIRST.
```

Dry-run is the default safe path. Skip it only when the user explicitly says to write immediately; the scan and duplicate checks still apply.
View the complete source on GitHub

Skills included

  • cobsidian

Repository facts

License
MIT
Created
Jul 6, 2026
Last pushed
Aug 17, 2026
Forks
4
Open issues
0
Project activity
Slowing

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 1 note
  • skills/cobsidian/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 23 signals by file

skills/cobsidian/mcp_server.py

  • Executable scriptline 1
    Executable file
  • Access to secretsline 299
    [Credential-related source omitted]
  • Access to secretsline 305
    [Credential-related source omitted]
  • Access to secretsline 306
    [Credential-related source omitted]
  • Access to secretsline 320
    [Credential-related source omitted]
  • Access to secretsline 321
    [Credential-related source omitted]
  • Access to secretsline 334
    [Credential-related source omitted]
  • Access to secretsline 335
    [Credential-related source omitted]

skills/cobsidian/scripts/cobsidian_config.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/dry_run.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/dsh_bridge.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/duplicates.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/find_duplicates.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/knowledge_read.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/note_identity.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/preflight.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/quality_eval.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/retrieval.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/scan_vault.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/suggest_backlinks.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/validate_notes.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/validate_skill.py

  • Executable scriptline 1
    Executable file

skills/cobsidian/scripts/write_executor.py

  • Executable scriptline 1
    Executable file

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 23 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/cobsidian/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/cobsidian/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/cobsidian/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/cobsidian/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/cobsidian/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/cobsidian/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.