agentsclimarketplace
Sign in

Rabbithole doc exploration

Skill markoblogo/abvx-agent-skills/skills/rabbithole-doc-exploration

Use local Rabbithole for human-in-the-loop exploration of AGENTS.md, SKILL.md, SET plans, repomaps, and long repo docs. Use when the user wants to inspect, question, branch, or review dense agent-facing documents interactively before changing durable docs or workflow contracts.From its SKILL.md

Install
npx -y skills add markoblogo/abvx-agent-skills --skill rabbithole-doc-exploration

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, 535 tokens by cl100k_base, as published. Nobody here has run it

Rabbithole Doc Exploration

Use a local Rabbithole MCP canvas to inspect dense documents with the human before turning findings into durable repo changes.

Use When

  • reviewing AGENTS.md, RUNBOOK.md, docs/ai/repomap.compact.md, or generated repo contracts;
  • reviewing SKILL.md files, skill cards, or workflow packs;
  • reviewing SET planner exports such as orchestrator-bundle.json or rabbithole.seed.md;
  • the user wants to branch into questions from selected text instead of reading a long document linearly.

Inputs

Good starting documents:

  • docs/ai/rabbithole.seed.md
  • AGENTS.md
  • RUNBOOK.md
  • docs/ai/repomap.compact.md
  • .set-plan/orchestrator-bundle.json
  • .set-plan/rabbithole.seed.md
  • skills/<name>/SKILL.md

Workflow

  1. Check availability
    • If Rabbithole MCP tools are available, use open_rabbithole with a title and file path or content.
    • If they are not available, continue as a normal document review and tell the user Rabbithole is optional.
  2. Open the smallest useful seed
    • Prefer docs/ai/rabbithole.seed.md or .set-plan/rabbithole.seed.md when present.
    • Otherwise open the single document the user named.
  3. Answer branches
    • Treat each selected passage as the anchor.
    • Answer with concrete file paths, risks, and proposed doc/code follow-ups.
    • Keep answers branch-sized; do not turn every branch into a full audit.
  4. Promote findings carefully
    • Only write durable repo docs when the finding is stable and broadly useful.
    • Keep Rabbithole notes out of CI contracts unless the repo explicitly stores them.
  5. Close with a compact synthesis
    • List decisions, doc changes made, open questions, and any branch findings that should become tasks.

Guardrails

  • Do not make Rabbithole a required runtime dependency for generated docs, skills, or SET.
  • Do not treat Rabbithole canvas state as source of truth.
  • Do not paste secrets, private profiles, or sensitive local files into Rabbithole unless the user explicitly approves.
  • Prefer seed docs over huge raw files.

Fallback

If Rabbithole is unavailable, read the target document directly and produce the same synthesis without the interactive canvas.

What ships with it: 2 files

1.7 KB alongside SKILL.md

agents/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.