agentleFS
Sign inStart free
yogsoth-aiyogsoth-ai/paper-reading/skills/keshav-three-pass/SKILL.md

keshav-three-pass

Skill1 starsChanged 3 months agoApache-2.0View on GitHub

Tactic: Read one paper by Keshav''s three-pass method — a shallow skim, a contribution-grasping full read, then a deep virtual re-implementation. Use when the goal is understanding a paper rather than extracting a fixed schema.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read one paper in three passes of increasing depth.

    line 25
  2. Very specific:

    Call paper-fetch with paper_ref.

    line 31
  3. Very specific:

    Call first-pass-skim with source_path and meta_path.

    line 33
  4. Very specific:

    If read_deeper is false, stop by default.

    line 35
  5. Very specific:

    Call second-pass-grasp with the paths and skim_notes.

    line 37
  6. Distinctive:

    Do not collapse pass 3 into a recap of pass 2.

    line 42

≈ “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

Keshav Three-Pass

Read one paper in three passes of increasing depth. The outputs accumulate as prose rather than fixed fields; use a different tactic when cross-paper alignment matters more than understanding.

Orchestration Pattern

  1. Call paper-fetch with paper_ref. Stop on not_found. Create context/papers/<dir>/keshav-three-pass/ on success.
  2. Call first-pass-skim with source_path and meta_path. Write 01-first-pass-skim.md, recording read_deeper in frontmatter.
  3. If read_deeper is false, stop by default. Continue only on explicit caller override and record gate_overridden: true.
  4. Call second-pass-grasp with the paths and skim_notes; write 02-second-pass-grasp.md.
  5. Call third-pass-deep-read with the paths and grasp_summary; write 03-third-pass-deep-read.md.

Do not collapse pass 3 into a recap of pass 2. It must surface implicit assumptions, virtual re-implementation mismatches, and concrete improvements.

Output Layout

context/papers/<timestamp>-<title-slug>/
  source.md
  source.meta.json
  keshav-three-pass/
    01-first-pass-skim.md
    02-second-pass-grasp.md
    03-third-pass-deep-read.md

Each output carries sop, tactic, and written_at frontmatter. Report the gate outcome, core claim, most consequential implicit assumption, unresolved flags, and all output paths.

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