agentleFS
aaaa-zhenaaaa-zhen/claude-home-agent/.agents/skills/media-library/SKILL.md

media-library

Skill11 starsChanged 51 days agoMITView on GitHub

Find, recall, inspect, or resend the user's previous WeChat images, videos, voice messages, screenshots, files, and generated media from the local media vault.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. sneakers-the-rat/muse-skills★ 25same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user refers to prior media: "刚才那张图", "之前的视频", "找一下截图", "把原图发我", "这张图再发一遍", "上次那个文件".

    line 8
  2. Distinctive:

    Search first, do not scan every media directory manually.

    line 18
  3. Distinctive:

    Prefer the newest matching record unless the user gives a date, topic, caption, or other clue.

    line 23
  4. Very specific:

    If the user wants the original media sent back, reply with [send_file:/absolute/path].

    line 24
  5. Distinctive:

    If the user wants analysis, inspect the file directly when needed, then answer concisely.

    line 25
  6. Distinctive:

    If multiple records may match, ask one short clarification instead of guessing.

    line 26
  7. Distinctive:

    Do not expose the media index implementation unless the user asks how it works.

    line 30
  8. Distinctive:

    Never reveal unrelated media filenames or paths when the user asks for one specific item.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Media Library

Use this skill when the user refers to prior media: "刚才那张图", "之前的视频", "找一下截图", "把原图发我", "这张图再发一遍", "上次那个文件".

Sources

  • New media index: media/index.jsonl
  • Legacy media index, only when the user explicitly asks for old/imported media: /Users/zhen/.openclaw/openclaw-weixin/media-archive/index.jsonl
  • Media vault docs: media/README.md

Procedure

  1. Search first, do not scan every media directory manually.
    • Recent images: node scripts/media-search.mjs --type image --limit 10
    • Recent videos: node scripts/media-search.mjs --type video --limit 10
    • Keyword search: node scripts/media-search.mjs --q "keyword" --limit 10
    • Legacy search, only if explicitly requested: add --include-legacy
  2. Prefer the newest matching record unless the user gives a date, topic, caption, or other clue.
  3. If the user wants the original media sent back, reply with [send_file:/absolute/path].
  4. If the user wants analysis, inspect the file directly when needed, then answer concisely.
  5. If multiple records may match, ask one short clarification instead of guessing.

Notes

  • Do not expose the media index implementation unless the user asks how it works.
  • Never reveal unrelated media filenames or paths when the user asks for one specific item.

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.