agentleFS
cykedevcykedev/vereinsheim/.claude/skills/ingest/SKILL.md

ingest

Skill1 starsChanged 14 days agoApache-2.0View on GitHub

Ingest an external source (a .raw/ file, pasted content, or a URL) into the vault as structured, cited notes. Use when adding reference/domain knowledge — vendor docs, a partner tool's manual, runbooks — that the project should be able to query. Not for the harness's own governance docs (those are authored).

90 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 74 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Capture the raw: Put the original under .raw/ — immutable, never edited.

    line 12

“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “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

/ingest

Turn an external source into structured, linked, cited vault notes (the source type in vault/SCHEMA.md). The rule: extract, never copy (copyright + it goes stale), and every ingested claim cites a source so an answer is always one hop from its provenance.

  1. Capture the raw. Put the original under .raw/ — immutable, never edited. For a URL, fetch it (WebFetch) and save the cleaned markdown there. .raw/ is dot-prefixed, so the loader ignores it.
  2. Read it fully, then discuss the key takeaways with the user (skip if they say "just ingest it").
  3. Create the source note — vault/sources/src-<id>.md from _templates/source.md (title · url · retrieved date · a TL;DR extract). This is the provenance anchor everything cites.
  4. Extract entities into atomic notes. For each significant capability / concept / procedure, create or update an atomic note (subsystem / operation / concept) in the right topic folder, from the matching _templates/. Each carries:
    • a **TL;DR** + an extract (decision-relevant facts, tables over prose — not a doc copy), a curated keywords: line, and aliases;
    • flat typed edges (quoted "[[id]]"): part_of its topic MOC, documented_in: ["[[src-<id>]]"] (cite the source), and where they apply alternative_to (the "what methods exist for X" mesh — author it on both notes), depends_on, relates_to. Heading-TEXT anchors, never slugs.
  5. Dedupe against vault/index.md — update an existing note rather than creating a near-duplicate, and add the new source to its documented_in.
  6. Wire & update — link the new notes into their topic MOC hub; update vault/index.md.
  7. Validate & commit — node .claude/vault-lint.mjs (fix the note it names). No build step; the notes are live. Commit the .raw/ original + the new/updated notes together.

Scale note: ingesting many sources at once is fine — process each fully, then do one cross-reference + index.md pass at the end, and report what was created/updated. If BM25 recall ever weakens on a large ingested corpus, an optional semantic reranker on top of the BM25 search is the escalation, not a rewrite.

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.