agentleFS
Fable-ForgeFable-Forge/fableforge-agent-skills/skills/obsidian-article-writeback/SKILL.md

obsidian-article-writeback

Skill1 starsChanged 53 days agoMITView on GitHub

Use when turning project guidance, design notes, agent discussions, recent Codex work, or external article summaries into shareable Chinese Obsidian Knowledge articles, especially when the user asks to write into Knowledge, curate publishable topics, avoid duplicate topics, de-brand project material, or manage internal/draft/published article layers.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use this for repo devlogs, implementation docs, or spoiler-heavy lore with little reusable method value.

    line 21
  2. Very specific:

    Use the user-provided vault path when given.

    line 26
  3. Distinctive:

    Read only the source material needed to extract the method.

    line 27
  4. Distinctive:

    If curating topics, list existing Knowledge titles first to avoid duplicates.

    line 28
  5. Distinctive:

    Keep the repeatable decision, workflow, principle, checklist, or anti-pattern.

    line 31
  6. Distinctive:

    Remove project-only lore, transient implementation trivia, and assistant-process framing.

    line 32
  7. Very specific:

    Default Chinese structure: 问题 -> 原因 -> 结论 -> 推荐流程 -> 常见错误 -> 最简原则.

    line 36
  8. Distinctive:

    Write Markdown into the target Knowledge vault only when the user asked for writeback.

    line 42
  9. Distinctive:

    Check language, headings, duplicate topic risk, banned project names, and any requested de-branding.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Obsidian Article Writeback

Overview

Turn reusable project or research insight into a practical Chinese Knowledge article. The default local target is <your-vault>/Knowledge.

When To Use

Use this for:

  • selecting which recent work is worth writing into Knowledge
  • writing or rewriting a shareable Knowledge article
  • converting project-specific experience into de-branded method writing
  • separating internal originals, pending-publication drafts, published notes, and article ledger entries

Do not use this for repo devlogs, implementation docs, or spoiler-heavy lore with little reusable method value.

Workflow

  1. Confirm source and target.
    • Use the user-provided vault path when given; otherwise default to <your-vault>/Knowledge.
    • Read only the source material needed to extract the method.
    • If curating topics, list existing Knowledge titles first to avoid duplicates.
  2. Extract the portable method.
    • Keep the repeatable decision, workflow, principle, checklist, or anti-pattern.
    • Remove project-only lore, transient implementation trivia, and assistant-process framing.
    • Preserve concrete operational nouns only when they teach the method.
  3. Shape the article.
    • Default Chinese structure: 问题 -> 原因 -> 结论 -> 推荐流程 -> 常见错误 -> 最简原则.
    • For publishing batches, maintain separate internal, pending-publication, and published layers.
    • Mark published articles with publish date and a no-duplicate-publication note when that convention exists.
    • For CTA, choose by article type: follow for series positioning, save for checklists/templates, comment for debate.
  4. Write and verify.
    • Write Markdown into the target Knowledge vault only when the user asked for writeback.
    • Re-read the saved file.
    • Check language, headings, duplicate topic risk, banned project names, and any requested de-branding.
    • Report exact paths and what was verified.

Output Contract

For curation, report candidate titles, duplication status, reuse value, and recommended order. For writeback, report created/updated paths, source material used, verification performed, and any content deliberately left internal.

Common Mistakes

  • Writing a project postmortem instead of a reusable article.
  • Skipping the existing-title check and duplicating an old Knowledge note.
  • Leaving project names in public copy after the user asked for de-branding.
  • Treating a chat-only draft as done when the request was to write into the vault.
  • Using the same CTA on every article instead of matching the article's job.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.