agentleFS
Sign inStart free
envisioningenvisioning/skills/skills/report/SKILL.md

report

Skill2 starsChanged 51 days agoMITView on GitHub

Write a narrative report from a scan's active signals and frames, shaped by a report type — executive readout, board narrative, watchlist, compliance memo, or a custom type — in house voice, with every claim traceable to a card. Use when the user says "write it up", "executive summary of the scan", "report for leadership", "turn this into a memo", "board slide notes". Stage: make.

93 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use opportunities, export and 10 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

  • soilmassSkill

    export

    Animation export configurations including format selection, resolution, framerate, quality, and optimization settings. Use when rendering animations for web, mobile, video, or social media. Provides tokens for all export parameters across Lottie, GIF, video, and sprite sheet formats.

    Also in 4 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

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 68 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read first: ../../core/voice.md, ../../core/signal-schema.md, ../../core/envisioning.md.

    line 12
  2. Distinctive:

    Lead with change, not with the method: No paragraph about how the scan was done above the fold.

    line 37
  3. Very specific:

    Cite by slug: Every factual claim carries [slug] the first time.

    line 39
  4. Very specific:

    No verified cards → no report.

    line 73
  5. Distinctive:

    Do not invent a recommendation the cards don't support.

    line 74

“Common” is measured: kept by at least 6 in 10 of the 68 edited versions of this file we could read. “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

report

The deliverable. A report is a narrative over verified signals; nothing in it may be untraceable to a card, and nothing verified should be missing without a reason.

Read first: ../../core/voice.md, ../../core/signal-schema.md, ../../core/envisioning.md.

Input

A scan index (or a set of cards) and optionally a frame set. Pick or take a report type:

typereaderlengthshape
readoutCEO / exec team600–900 words3 things that changed · what it means · what to watch
boardboard / non-exec400–600 wordsone narrative, three exhibits, one question for the board
watchliststrategy / foresight teamtable + notesevery verified card, ranked by the playbook's first metric, with tells
complianceGC / compliance600–900 wordsin force · coming · enforcement posture · actions with dates
briefanyone≤ 400 wordsthe one-pager

A custom type needs: reader, length, and the section list; write them into frontmatter.

Procedure

  1. Use only active, grounded cards. verified cards are the spine; pending may appear if labelled as such; rejected cards appear only in a what we ruled out line, which is often the most credible paragraph. Frozen duplicates never appear.
  2. Lead with change, not with the method. No paragraph about how the scan was done above the fold; that goes in a Method footer.
  3. Cite by slug. Every factual claim carries [slug] the first time. Numbers carry their source's note. When connected, slugs render as doors.
  4. Rank by the metrics. The playbook's metrics decide what comes first; don't reorder by narrative convenience.
  5. Write in voice. See voice.md; no hype, name actors, end with a tell or a question.
  6. Gaps are content. The scan index's Coverage gaps becomes a sentence in the report; silence about a thin category reads as confidence you don't have.
  7. Persist to /foresight/reports/<scope>-<type> with category: report (or ./foresight/reports/). Attach the client subject if the scan carried one. message: report · <type>.

Output

---
kind: report
report_type: <type>
title:
scope:
date:
sources: [<scan index>, <frame set>]
cards_cited: <n>
cards_verified_total: <n>
---
<body per the type's shape>

---
*Method:* <playbook>, <n> cards generated, <m> merged, <k> verified, <r> rejected. Cards: <folder or door>.

Refusals

  • No verified cards → no report. Offer ground first.
  • Do not invent a recommendation the cards don't support. A report may end in "we don't know yet; here is what would tell us."

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