agentleFS
davidmatousekdavidmatousek/tachi/.claude/skills/tachi-report-assembly/SKILL.md

tachi-report-assembly

Skill95 starsChanged 38 days agoApache-2.0View on GitHub

Domain knowledge for PDF security report assembly — artifact detection patterns with tier selection rules, Typst data variable contract with type specifications and image path resolution, and brand asset handling with logo location and fallback rules. Consumed by the report-assembler agent during report generation.

The file

Files
SKILL.md

tachi-report-assembly

PDF security report assembly domain knowledge extracted from the tachi report-assembler agent. This skill provides the artifact detection tables, Typst template interface contract, and brand asset guidelines that the report-assembler uses to transform pipeline artifacts into a professional PDF security assessment booklet.

Domain Overview

The report assembly pipeline bridges tachi pipeline artifacts (markdown and image files) with a Typst template system to produce a multi-page PDF:

  1. Artifact Detection -- Identify which pipeline outputs are available in the target directory and select the richest data source tier for findings presentation
  2. Data Extraction -- Parse markdown artifacts and extract structured data via deterministic Python script
  3. Typst Data Generation -- Generate a report-data.typ file containing all extracted variables as Typst #let bindings that the template system imports at compile time
  4. Brand Asset Resolution -- Locate logo files with dark variant support and compute relative paths for Typst image inclusion

The Typst template system uses a data injection pattern: main.typ imports report-data.typ and conditionally includes page templates based on artifact availability flags. The agent's responsibility is generating report-data.typ with correct variable names, types, and values.

Loading Table

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

ReferenceFileLoad When
Typst Artifactsreferences/typst-artifacts.mdArtifact detection phase (Step 1) — determining which pipeline outputs exist and selecting data source tier
Typst Template Contractreferences/typst-template-contract.mdData generation phase (Step 2) — generating report-data.typ with correct variable bindings
Brand Asset Guidelinesreferences/brand-asset-guidelines.mdBrand detection phase (Step 2) — locating and resolving logo paths for cover and footer

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.