agentleFS
Sign inStart free
SkinnnyJaySkinnnyJay/wiki-llm/skills/wiki-research-loop/SKILL.md

wiki-research-loop

Skill0 starsChanged 4 months agoMITView on GitHub

Batch research from research-tasks.json — fetch, ingest, wiki merge. Use when research_loop.enabled for automated passes (e.g. HN front page).

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Do not scrape aggressively.

    line 22
  2. Very specific:

    CLI: Run llm-wiki integrations status and any llm-wiki line from Step 1 of this skill (from the vault root).

    line 34

≈ “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

Research loop (batch tasks)

Not ad-hoc topic research — for a user topic or question, use wiki-research and /llm-wiki:research.

Requires research_loop.enabled: true in llm-wiki/config.json. If false, tell the user to enable it.

  1. Load llm-wiki/research-tasks.json or research-tasks.yaml (or the path in research_loop.tasks_file; YAML needs pip install pyyaml).
  2. For each task with run: true (or user-specified id), respect max_items_per_run and delay_seconds_between_fetches.
  3. Optional batching: llm-wiki research-loop runs hackernews_top and fetch_urls tasks from the JSON/YAML file; then apply wiki-ingest / wiki-maintainer for anything written to raw/.
  4. Or use llm-wiki ingest (e.g. hackernews, url) directly to write into raw/; then apply wiki-ingest / wiki-maintainer.
  5. See references/hn-example.md for Hacker News API usage and ethics (rate limits, ToS).

Do not scrape aggressively; prefer official APIs.

Optional: skills/references/context-persona.md for ingest/tool alignment; persona.name in config (default Gennie).

Done looks like

  • research_loop.enabled: true confirmed (or user told how to enable it).
  • Tasks loaded; delays and max_items_per_run respected; new files under raw/; wiki-ingest / wiki-maintainer applied for batch merge when requested.
  • wiki/log.md updated for the loop run when non-trivial.

Smoke check

  • CLI: Run llm-wiki integrations status and any llm-wiki line from Step 1 of this skill (from the vault root).
  • Prompt: Invoke this skill by name in Claude Code; complete Step 1 only and confirm expected CLI or file output.

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