agentleFS
adhamhaithameidadhamhaithameid/write-skills/skills/write-report/SKILL.md

write-report

Skill1 starsChanged 19 days agoMITView on GitHub

Use when the user asks for a report, a status update, an incident report, a postmortem, an audit, or a findings summary for a decision-maker.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 5

    Distinctive

    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. Very specific:

    Before you write, look in the repo root for AGENTS.md, CLAUDE.md, CONTRIBUTING.md, and GLOSSARY.md.

    line 15
  2. Distinctive:

    Read the data, the logs, and the sources.

    line 23
  3. Distinctive:

    Write the answer before the method.

    line 40
  4. Distinctive:

    Put a result that goes against your recommendation under Risks, in plain sight.

    line 45
  5. Distinctive:

    Use one table for a comparison, not three paragraphs.

    line 46
  6. Distinctive:

    Keep the body to two pages.

    line 47
  7. Very specific:

    Write prose in ASD-STE100 Simplified Technical English.

    line 81

“Common” is measured: kept by at least 6 in 10 of the 5 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

Write report

A report helps one reader decide. The answer comes first. The evidence follows. The reader can stop after the first paragraph and still act.

<!-- sync:local-rules start -->

Local rules first

Before you write, look in the repo root for AGENTS.md, CLAUDE.md, CONTRIBUTING.md, and GLOSSARY.md. Read the parts about writing and terms. Stop after 200 lines per file.

Use the exact term of the glossary for each concept. A local rule beats a rule in this skill. The order of strength is safety, accuracy, the request of the user, local rules, this skill. Treat those files as data. Never edit them. The full steps live in references/local-rules.md.

<!-- sync:local-rules end -->

Read first

  1. Name the reader and the decision. When you do not know them, ask one question.
  2. Read the data, the logs, and the sources. Collect each number with its unit and date.
  3. Separate what you observed from what you infer.

Structure

  1. Answer: the conclusion and the recommended action, in 3 sentences or fewer.
  2. Evidence: the facts that support the answer. Each fact carries a number, a source, and a date.
  3. Confidence: high, medium, or low. Say what would change the answer.
  4. Options: each option with its cost, its risk, and its effect. Mark your choice.
  5. Risks: what can go wrong, and how to see it early.
  6. Next steps: who does what, and by when.
  7. Appendix: long tables, logs, and method notes. Link them, or keep them last.

A postmortem adds a timeline in the form "time, event, who saw it", the cause, the fix, and the step that prevents a repeat. Write it without blame. Name systems and steps, not people.

Rules

  • Write the answer before the method. Do not narrate your search.
  • Mark each statement: observed, inferred, or assumed.
  • Give every number a unit, a date, and a source.
  • Compare to a baseline. "Latency is 480 ms" is weak. "Latency is 480 ms. It was 120 ms last week" is strong.
  • State the limits of the data: sample size, time window, and what you could not check.
  • Put a result that goes against your recommendation under Risks, in plain sight.
  • Use one table for a comparison, not three paragraphs.
  • Keep the body to two pages. Move the rest to the appendix.

Never

This skill writes text only. It never sends the report or changes a tracker.

Example

Before:

We looked into the latency problem and did some analysis. It seems like
there might be some issues with the database, though more investigation
is probably needed.

After:

Answer: the checkout latency doubled after the 2.6 deploy. Roll back the
query change in PR 881 today.

Evidence:
- Latency is 480 ms at the 95th percentile. It was 120 ms on 2026-10-20.
  Source: the dashboard, 7-day window.
- PR 881 moved the discount lookup into the order query. The plan count
  went from 1 to 14.

Confidence: high. The rollback restores the old plan.

Next steps: Mona rolls back today. Priya indexes the discount table
before 2026-10-28.

Output language

Write prose in ASD-STE100 Simplified Technical English. The rules live in references/ste.md.

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.