agentleFS
VladTheProgrammerVladTheProgrammer/claude-asimov/.claude/skills/facts-ext/SKILL.md

facts-ext

Skill0 starsChanged 4 months agoMITView on GitHub

Research a topic using web, filesystem, and inference with parallel sub-agents. Usage: /facts-ext {topic} [hints...]

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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. Very specific:

    Use the Agent tool with subagent_type: "ext-fact-finder".

    line 20
  2. Distinctive:

    After the root agent completes, seed both lists from its response:

    line 28
  3. Distinctive:

    Add its COVERED items to covered

    line 29
  4. Distinctive:

    Add its SUGGESTED items to queue

    line 30
  5. Distinctive:

    If the filtered queue is empty, proceed to Phase 3.

    line 37
  6. Distinctive:

    After all agents in this round complete, for each agent:

    line 45
  7. Distinctive:

    Add its SUGGESTED items to queue (replacing the old queue)

    line 47
  8. Distinctive:

    After the loop exits:

    line 52
  9. Very specific:

    Use # {Topic} — Research Facts as the top heading

    line 57
  10. Distinctive:

    No frontmatter, no timestamps, no filler

    line 61
  11. Distinctive:

    Delete all fragment files

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Parse the user's input:

  • First argument is the topic (e.g., Postgres advisory lock semantics, S3 pre-signed URL expiry rules, OAuth device-flow constraints)
  • Any additional arguments are hints — URLs, file paths, or narrowing keywords the agent should start with

Phase 1 — Root research

Spawn an ext-fact-finder agent with:

topic: {topic}
sub_topic: {topic}
hints: {any hints provided, or "none"}

Use the Agent tool with subagent_type: "ext-fact-finder".

Phase 2 — Recursive fan-out

Maintain two lists across rounds:

  • covered — all topics explored so far (accumulated from every agent's COVERED section)
  • queue — sub-topics to explore next

After the root agent completes, seed both lists from its response:

  1. Add its COVERED items to covered
  2. Add its SUGGESTED items to queue

Then loop:

  1. Filter the queue. For each proposed sub-topic, evaluate:
    • Relevance: Is this sub-topic meaningfully related to the original topic {topic}? Drop it if it has drifted to a tangential or generic area.
    • Novelty: Has this topic (or something substantially overlapping) already been covered? Drop it if so.
  2. If the filtered queue is empty, proceed to Phase 3.
  3. Spawn one ext-fact-finder agent per sub-topic in the queue, all in parallel:
    topic: {topic}
    sub_topic: {sub-topic name}
    hints: {hints from the suggestion}
    Use the Agent tool with subagent_type: "ext-fact-finder".
  4. After all agents in this round complete, for each agent:
    • Add its COVERED items to covered
    • Add its SUGGESTED items to queue (replacing the old queue)
  5. Go back to step 1.

Phase 3 — Merge & clean up

After the loop exits:

  1. Glob docs/{topic}/facts-*.md to find all fragment files
  2. Read every fragment
  3. Combine all fragments into docs/{topic}/facts.md:
    • Use # {Topic} — Research Facts as the top heading
    • Organize sections logically (root agent's broad content first, then deeper sub-topic sections)
    • Deduplicate facts that appear in multiple fragments
    • Preserve all source citations
    • No frontmatter, no timestamps, no filler
  4. Delete all fragment files

Tell the user the output is at docs/{topic}/facts.md.

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.