agentleFS
Sign inStart free
r-irber-irbe/proof-skills/skills/lean-report/SKILL.md

lean-report

Skill3 starsChanged 24 days agoApache-2.0View on GitHub

USE FOR: converting a Lean 4 project blueprint into a publication-grade LaTeX report: blueprint artifact ingestion. DO NOT USE FOR: generating the blueprint itself (@lean-blueprint). TRIGGERS: blueprint to report, generate report, latex pdf.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify prerequisites (Part 12.1 below — blueprint artifacts exist, LaTeX toolchain present).

    line 40
  2. Very specific:

    STOP if \cref references emit "??" after two latexmk passes — the blueprint is out of sync.

    line 52
  3. Distinctive:

    STOP if narration drifts from Lean source (Part 13 final row) — the source changed after narration.

    line 54
  4. Very specific:

    STOP if the figures stage produces empty TikZ outputs — dot2tex is optional but required for dependency graphs.

    line 58

≈ “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

SK-62: Blueprint-to-Report Generator

Convert a Lean 4 project blueprint (extracted LaTeX nodes, dependency graphs, JSON metadata) into a publication-grade LaTeX report with natural language narrative, mathematical exposition, and visual dependency maps.

Routing

  • USE FOR: converting a Lean 4 project blueprint into a publication-grade LaTeX report via the 6-stage INGEST → PLAN → NARRATE → ILLUSTRATE → ASSEMBLE → COMPILE pipeline; ingesting blueprint artifacts (LaTeX nodes, dependency DAG, JSON metadata); generating per-chapter mathematical prose with \leanref cross-references; producing TikZ dependency figures; running latexmk to PDF.
  • DO NOT USE FOR: generating the blueprint itself (delegate to @lean-blueprint); writing one chapter without the pipeline (delegate to

Workflow

  1. Verify prerequisites (Part 12.1 below — blueprint artifacts exist, LaTeX toolchain present).
  2. First-time: run Part 12.2 (INGEST → PLAN → NARRATE → ILLUSTRATE → ASSEMBLE → COMPILE). Each stage's contract is in the handbook (Parts 3–8).
  3. Incremental: run Part 12.3 — re-blueprint, re-ingest, diff, narrate only changed chapters, recompile.
  4. On compilation error consult Part 13 (Troubleshooting) below; on output-artifact question consult Part 14 below.
  5. Handoff to @lean-doc-feedback once the PDF lands so the doc-sync skill can record the new artifact in the repository's tracking matrix.

Recovery & STOP

  • STOP if \cref references emit "??" after two latexmk passes — the blueprint is out of sync; re-run INGEST per Part 12.3.
  • STOP if narration drifts from Lean source (Part 13 final row) — the source changed after narration; re-run NARRATE for affected chapters only.
  • STOP if the figures stage produces empty TikZ outputs — dot2tex is optional but required for dependency graphs; install or fall back to module-map-only figures.

Handoffs

  • Predecessors: agent:gateway (top-level invocation), skill:lean-blueprint (produces the blueprint artifacts this skill consumes), skill:lean-doc-requirements (chapter-scope decisions).
  • Successors: skill:lean-doc-feedback (record the PDF artifact + cross-references), skill:lean-doc-improvement (per-chapter post-narration edits),

Detailed reference

Full encyclopedic reference, decision trees, and lookup tables live in references/lean-report-handbook.md .

See also

  • ../../references/lean-report-handbook.md -- Complete lean-report Handbook
  • ../lean-gateway/SKILL.md -- Top-level skill router

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