agentleFS
Sign inStart free
nitekeepernitekeeper/atelier/skills/ingest/SKILL.md

ingest

Skill0 starsChanged 5 months agoMITView on GitHub

Use when capturing a document, URL, decision, or learned context into the shared Memex wiki for future sessions.

  • Installs packages

88 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

10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 72 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call ingest whenever you have knowledge worth preserving:

    line 11
  2. Very specific:

    Settings recommendation (after pre-flight): if startup_check() returned a settings_rec_offer with eligible=True and non-empty changes, read …

    line 34
  3. Distinctive:

    BEFORE proceeding to the rest of this skill.

    line 37
  4. Distinctive:

    Ask the user (or calling agent): "What do you want to capture?

    line 42
  5. Very specific:

    Before invoking capture, run:

    line 45
  6. Distinctive:

    If the command exits 0: continue to step 2.

    line 49
  7. Very specific:

    Follow Memex capture's approval flow — do not write to the wiki without approval.

    line 53
  8. Very specific:

    Never skip the Memex capture approval gate.

    line 58
  9. Distinctive:

    Never invent or summarize content — capture what was provided, not your interpretation of it.

    line 59
  10. Distinctive:

    If the input is a URL, fetch it first and confirm the content before capturing.

    line 60

“Common” is measured: kept by at least 6 in 10 of the 72 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

Capture knowledge into the shared Memex wiki. Any actor — human or agent — can call this.

When to use

Call ingest whenever you have knowledge worth preserving:

  • A document or file the user has provided
  • A URL with relevant project information
  • Something learned during this session about the codebase
  • A decision made in a meeting
  • Any context that would be expensive to reconstruct later

Pre-flight (always first)

Run from scripts.atelier_entrypoint import startup_check; startup_check().

Branch on the returned action:

  • proceed-local — Memex is not installed. Continue with the rest of this skill's recipe; all writes go to the project-local .ai/atelier.db.
  • proceed-memex — Memex is installed and bootstrapped. Continue; all writes go through Memex.
  • prompt-migration — Memex is installed but this project still has a local DB. Read internal/migrate-local-to-memex/SKILL.md and follow its prompt protocol. After the user answers, restart the pre-flight (startup_check() will now return proceed-memex or proceed-local depending on the user's choice).

Settings recommendation (after pre-flight): if startup_check() returned a settings_rec_offer with eligible=True and non-empty changes, read internal/settings-recommendation/SKILL.md and follow its prompt protocol BEFORE proceeding to the rest of this skill. After the user's choice, continue the original command.

Procedure

  1. Ask the user (or calling agent): "What do you want to capture? Provide the content, file path, or URL."

1b. Verify Memex CLI availability. Before invoking capture, run:

memex --version
  • If the command exits 0: continue to step 2.
  • If the command is not found (command not found / is not recognized): stop. Tell the user: "The memex CLI is not on PATH. Either activate the environment where Memex is installed, or provide a full path to the memex executable. Install: pip install memex." Do not fall back to writing the content elsewhere — session knowledge written outside Memex is invisible to future agents.
  1. Invoke Memex capture with the provided input.
  2. Follow Memex capture's approval flow — do not write to the wiki without approval.
  3. Confirm: "Captured to Memex wiki."

Hard rules

  • Never skip the Memex capture approval gate.
  • Never invent or summarize content — capture what was provided, not your interpretation of it.
  • If the input is a URL, fetch it first and confirm the content before capturing.

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.

Check your setup, free