agentleFS
kaandgnshkaandgnsh/Claude-Blue/skills/incident-response/incident-report-writing/SKILL.md

incident-report-writing

Skill0 starsChanged 15 days agoMITView on GitHub

Write incident reports for different audiences — executive summary, technical report, regulator/customer notification draft — with consistent facts, confidence language and impact statements. Use when an incident needs a written report for leadership, legal, auditors, customers or regulators.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every technical claim maps to evidence in the case file.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Incident Report Writing

One fact base, several audiences. Write the technical report first; derive the others from it so numbers and dates never disagree.

Audience matrix

AudienceLengthContainsAvoids
Executive / board1 pageWhat happened, business impact, status, decisions needed, cost/riskTool names, IOCs, jargon
TechnicalAs neededTimeline, scope, TTPs (ATT&CK), evidence, root cause, remediation, IOCsSpeculation without labels
Regulator/customer (draft for counsel)Per legalNature of incident, data categories, approximate numbers, measures taken, contact pointUnverified claims, admissions not approved by counsel

Writing rules

  • Lead with the conclusion (BLUF).
  • Dates in UTC with timezone; quantities with confidence ("approximately 4,200 records, confirmed").
  • Consistent confidence words: confirmed / likely / possible / not observed (with telemetry coverage).
  • Distinguish accessed, exfiltrated, and exposed.
  • Every technical claim maps to evidence in the case file.
  • Mark privilege as directed by counsel (e.g., "Privileged & Confidential — prepared at the direction of counsel").

Executive summary template

What happened: <2 sentences>
Impact: <systems, data, customers, operations, $ if known>
Current status: <contained/recovering/monitoring>
Root cause: <one line>
What we're doing: <3 bullets>
Decisions/support needed: <>
Next update: <date>

Technical report outline

  1. Executive summary 2. Scope and methodology 3. Timeline 4. Initial access 5. Attacker actions mapped to ATT&CK 6. Impact (systems/data) 7. Containment, eradication, recovery 8. Root cause & contributing factors 9. Recommendations 10. Appendices: IOCs, queries, evidence inventory

Related skills

forensic-report, after-action, case-documentation, privacy-incident-assessment

References

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.