agentleFS
TsukiNi22TsukiNi22/skills/skills/docs/report/SKILL.md

report

Skill1 starsChanged 3 days agoMITView on GitHub

Deliver a result (report, audit, review, study, benchmark, summary) as Markdown and/or PDF in the user's report style (measured on the Convertly docs - WeasyPrint, A4, Noto Sans 9 pt, navy (1a3d7c) title with a navy rule under it, navy table heads, light blue callout with navy bar, zebra tables, mono code on grey, footer "title - page / pages"), English by default, converted with scripts/md2pdf.py. Use whenever the user asks for a PDF, a report/benchmark/audit/study, or another skill needs a report output.

102 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use opportunities, quality and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ansvisorSkill

    opportunities

    Finds content gaps, prompts worth tracking, and the off-site sources AI cites instead of the brand.

    Also in 3 projects that use this

  • GoogleSkill

    quality

    Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.

    Also in 3 projects that use this

  • genomewalkerSkill

    resume

    Resume a thread by loading its ~800-token context capsule

    Also in 7 projects that use this

  • tokyubevoxelverseSkill

    checkup

    Give a repository a full health exam — doc rot, dependency staleness, CI decay, git hygiene, dead links, docs contradicting code — and grade it. Use when the user wants to know what quietly rotted, or a prioritized maintenance list.

    Also in 3 projects that use this

  • rajnavakotiSkill

    scan

    Run the AI dashboard scanner and generate the HTML report.

    Also in 5 projects that use this

  • michaelenglandSkill

    import

    This skill should be used when the user wants to import an existing .pptx file into deckwright, bring in a PowerPoint that was created outside this tool, reverse-engineer a presentation for editing, or invoke /deckwright:import. Converts a .pptx into a PptxGenJS generation script so it can be edited and regenerated through the deckwright pipeline.

    Also in 3 projects that use this

The file

Files
SKILL.md

Reports in the user's style (Markdown + PDF)

SKILL_DIR = directory of this file. Requires weasyprint + python3-markdown (installed here) and the Noto fonts. The style is templates/report.css: never restyle unless the user asks. Start from templates/report.md.

1. Ask once (AskUserQuestion, French question, per request)

Format du rendu : Markdown + PDF (Recommandé) · PDF seulement · Markdown seulement. Skip the question when the user already said it. Several reports in the same request share the answer.

2. Language and location

  • English by default (titles, tables, text), another language only when the user asks for it.
  • Location: the one given by the user, otherwise the default of the calling skill (audits: audit/ at the root of the repository, or of the current folder outside a repository); never docs/ unless asked.
  • File name: <YYYY-MM-DD>-<subject>.md / .pdf (ex: audit/2026-10-03-quality.pdf).

3. Convert

python3 SKILL_DIR/scripts/md2pdf.py <report.md> --format both|pdf|md [-o report.pdf] [--footer "Project — subject"] [--lang en]

both keeps the .md next to the .pdf; pdf removes the .md after a successful conversion; md writes no PDF.

4. Structure (from the reference documents)

  1. # Project: subject (one H1, underlined by the navy rule; it is also the footer text unless --footer).
  2. Meta line: **Date**: October 3, 2026 · **Sources**: ... (code paths in backticks).
  3. Callout > **How to read this document** + numbered list of the parts + the assumptions / limits / what is not included.
  4. ## Contents: plain numbered list of the H2.
  5. ## 1. Summary: table | Point | Conclusion |, first column in bold, key numbers in bold.
  6. Numbered parts ## N. Title, sub-parts ### N.M Title, tables for every comparison, numbered findings 1. **Finding.** explanation, short > **Key takeaway**: ... callouts.
  7. ## N. Sources: grouped by **Category**: with bullet links <https://...>, then what is an assumption.

5. Writing

  • Factual, short paragraphs, every number sourced or marked as an assumption, units and dates explicit.
  • Tables rather than prose for anything with several attributes; — for empty cells, n/a when not measurable.
  • Code, paths, commands, identifiers in backticks.
  • Variants: {: .warn} / {: .ok} on the line after a callout (orange / green bar), {: .page} after an H2 to start it on a new page. GitHub callouts (> [!NOTE], [!TIP], [!IMPORTANT], [!WARNING], [!CAUTION]) are rendered too (titled, warning / caution orange, tip green): a README or a protocol-doc Markdown converts as is.

6. Check

  • md2pdf.py fits every table by itself (a width per column from its words, smaller, or a landscape page when it is too wide) and tells on stderr a word past the edge of a page: never a width set by hand, never ignored.
  • Convert a page to an image (pdftoppm -r 60 -png -f 1 -l 2 report.pdf /tmp/p) and look at it: title rule present, no table overflowing, lists rendered as lists, footer present.
  • Give the user the path(s) and the page count (pdfinfo).

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.