agentleFS
davidmatousekdavidmatousek/tachi/.claude/skills/tachi-threat-reporting/SKILL.md

tachi-threat-reporting

Skill95 starsChanged 38 days agoApache-2.0View on GitHub

Domain knowledge for narrative threat report generation — executive summary structure, architecture overview patterns, per-category narrative templates, attack tree construction rules with Mermaid syntax, and reference attack tree examples. Consumed by the threat-report agent during report generation.

The file

Files
SKILL.md

tachi-threat-reporting

Narrative threat report domain knowledge extracted from the tachi threat-report agent. This skill provides the templates, construction rules, and reference examples that the threat-report agent uses to transform structured threat model output into comprehensive narrative reports with Mermaid attack trees.

Domain Overview

The threat report agent produces two output types:

  1. threat-report.md -- A 7-section narrative report conforming to schemas/report.yaml containing executive summary, architecture overview, per-category threat analysis, cross-cutting themes, Mermaid attack trees, remediation roadmap, and finding reference appendix
  2. attack-trees/{finding-id}-attack-tree.md -- Standalone Mermaid attack tree files for every Critical and High finding

Report generation applies three bodies of domain knowledge:

  • Narrative Templates -- Structural patterns for each report section: executive summary elements, architecture overview layout, per-category subsection headers, per-finding narrative pattern, progressive depth rules, cross-cutting theme detection criteria, and language conventions
  • Attack Tree Construction -- Rules for building Mermaid flowchart attack trees: tree structure (root/intermediate/leaf), minimum depth requirements, decomposition stopping rules, Mermaid syntax conventions, color styling, node naming, and validation checklist
  • Attack Tree Examples -- Reference implementations demonstrating correct syntax, naming, gate logic, and decomposition depth for Critical and High severity patterns

Loading Table

Reference files are loaded on-demand by the threat-report agent at specific workflow phases using the Read tool.

ReferenceFileLoad When
Narrative Templatesreferences/narrative-templates.mdGenerating Executive Summary (Section 1), Architecture Overview (Section 2), Threat Analysis (Section 3), Cross-Cutting Themes (Section 4), Remediation Roadmap (Section 6)
Attack Tree Constructionreferences/attack-tree-construction.mdConstructing Mermaid attack trees for Critical and High findings (Section 5)
Attack Tree Examplesreferences/attack-tree-examples.mdBefore generating the first attack tree -- load once as reference patterns

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.