Generate Project Catalog

VerifiedCaution

Generates or updates CATALOG.md from deployed ticket metadata. Builds a comprehensive asset catalog showing all components, styles, and utilities with usage instructions.

Sby Skills Guide Bot
DocumentationIntermediate
7/28/2026
Claude CodeCodex
#catalog-generation#asset-inventory#markdown#ticket-metadata#changelog

Recommended for

Automated summary

This skill generates or updates a CATALOG.md file by scanning deployed JSON tickets, extracting files_created metadata and grouping files by category with usage instructions.

Strengths

  • Automates catalog upkeep from existing ticket metadata instead of a hand-maintained inventory
  • Sorts files by path pattern (components, styles, utils, data, pages, tests) and emits a summary table with per-category counts
  • Preserves traceability by recording which ticket created each file and appending a dated changelog
  • Returns a structured JSON result (status, stats, errors) that downstream automation can consume

Limitations

  • Assumes a specific ticket schema (a files_created array with path/type/intended_use) plus jq; a non-conforming ticket breaks parsing
  • The category table is hard-coded to a src/**-style layout, so other project structures need adaptation
  • The merge behavior for an existing CATALOG.md is only partially specified in the skill
When to use it

Use it when a project already tracks its work as deployed JSON tickets and needs an up-to-date asset catalog without manual bookkeeping.

When not to use it

Avoid it on projects that don't use that ticket format, or when you need richer documentation than a generated Markdown table.

Security analysis

Caution
Quality score82/100

The skill is not destructive or exfiltrating; it reads local ticket JSON and writes a catalog file. However, it relies on shell/jq execution and filesystem writes despite declaring no allowed tools, so it warrants caution rather than a fully safe rating.

Findings
  • •Declares no allowed-tools but instructs use of bash, jq, and direct filesystem writes.
  • •Uses unquoted `$tickets_dir` in `cd $tickets_dir` and the `*.json` loop, which can break on paths with spaces or glob characters.
  • •Writes CATALOG.md directly into the project filesystem without validation or dry-run safeguards.
How this analysis is made

Examples

Generate from current sprint
Generate CATALOG.md for /projects/oxygen_site using the deployed tickets in tickets/sprint_current/deployed, excluding test files.
Include tests and report counts
Regenerate the asset catalog for this project with include_tests set to true, then tell me how many files landed in each category.
Update from archived sprint
Merge the files from the tickets in tickets/archive/sprint-42 into the existing CATALOG.md and add a changelog entry for today.

name: generate-catalog description: Generate CATALOG.md from deployed tickets. Extracts files_created metadata and builds project asset catalog with usage instructions.

generate-catalog - Project Catalog Generator

Generates or updates CATALOG.md from deployed ticket metadata. Builds a comprehensive asset catalog showing all components, styles, and utilities with usage instructions.

Input Schema

{
  "project_dir": "/path/to/project",
  "tickets_dir": "/path/to/tickets/deployed",
  "include_tests": false,
  "include_deps": true
}

Instructions

1. Scan Deployed Tickets

cd $tickets_dir
for ticket in *.json; do
    jq -r '.files_created[]' "$ticket"
done

2. Extract File Metadata

For each deployed ticket, extract:

{
  "files_created": [
    {
      "path": "src/components/MetricCard.js",
      "type": "component",
      "intended_use": "Import { MetricCard } from './MetricCard.js'"
    }
  ]
}

3. Categorize Assets

| Category | Patterns | Description | |----------|----------|-------------| | Components | src/components/**/*.js | Reusable UI components | | Styles | src/styles/**/*.css | CSS stylesheets | | Utils | src/utils/**/*.js, src/js/utils/** | Helper functions | | Data | src/data/**/*.json | Static data files | | Pages | src/pages/**/*.html | HTML pages | | Tests | tests/**/*, *.spec.js | Test files (if included) |

4. Generate Markdown

# Project Asset Catalog

> Auto-generated by generate-catalog on {date}

## Summary

| Category | Count | Status |
|----------|-------|--------|
| Components | 5 | ✅ |
| Styles | 3 | ✅ |

## Components

| File | Intended Use | Created By |
|------|--------------|------------|
| `src/components/MetricCard.js` | Import { MetricCard } | TICKET-001 |

Output Format

{
  "skill": "generate-catalog",
  "status": "success|failure",
  "catalog_path": "src/CATALOG.md",
  "stats": {
    "tickets_processed": 5,
    "files_cataloged": 23,
    "categories": {
      "components": 8,
      "styles": 5,
      "utils": 4,
      "data": 2,
      "pages": 4
    }
  },
  "errors": [],
  "warnings": [],
  "next_action": "proceed"
}

Catalog Structure

# Project Asset Catalog

> Auto-generated by generate-catalog on 2026-01-07

## Summary

| Category | Count | Status |
|----------|-------|--------|
| Components | 8 | ✅ |
| Styles | 5 | ✅ |
| Utils | 4 | ✅ |
| Data | 2 | ✅ |
| **Total** | **19** | |

## Components

| File | Intended Use | Created By |
|------|--------------|------------|
| `src/components/impact/MetricCard.js` | Import { MetricCard } from './MetricCard.js' | TICKET-OXY-003-A.3 |

## Styles

| File | Intended Use | Created By |
|------|--------------|------------|
| `src/styles/components/metric-card.css` | Link in HTML: <link rel="stylesheet" href="..."> | TICKET-OXY-003-A.3 |

## Changelog

- **2026-01-07**: Added MetricCard component via TICKET-OXY-003-A.3

Decision Logic

All tickets parsed successfully?
    YES → status: "success"
    NO  → status: "failure", errors: [parse errors]

Catalog written successfully?
    YES → next_action: "proceed"
    NO  → next_action: "fix"

Usage Examples

Generate from deployed tickets:

{
  "project_dir": "/projects/oxygen_site",
  "tickets_dir": "/projects/oxygen_site/tickets/sprint_current/deployed",
  "include_tests": false,
  "include_deps": true
}

Include test files:

{
  "project_dir": "/projects/oxygen_site",
  "tickets_dir": "/projects/oxygen_site/tickets/sprint_current/deployed",
  "include_tests": true,
  "include_deps": true
}

Custom tickets directory:

{
  "project_dir": "/projects/oxygen_site",
  "tickets_dir": "/projects/oxygen_site/tickets/archive/sprint-42",
  "include_tests": false,
  "include_deps": false
}

Merge Behavior

When updating existing CATALOG.md:

  1. Read existing catalog
  2. Add new files from recently deployed tickets
  3. Preserve existing entries (don't remove)
  4. Update changelog section
  5. Sort entries alphabetically within categories

Token Efficiency

  • JSON parsing only, no LLM inference
  • Incremental updates (append-only)
  • ~2-5 second execution
  • Writes directly to file system

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/generate-project-catalog-ms47vq35/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/generate-project-catalog-ms47vq35' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/generate-project-catalog-ms47vq35/download' --output '.skill-downloads/generate-project-catalog-ms47vq35/SKILL.md.part' && mv '.skill-downloads/generate-project-catalog-ms47vq35/SKILL.md.part' '.skill-downloads/generate-project-catalog-ms47vq35/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/generate-project-catalog-ms47vq35/SKILL.md' && test -s '.skill-downloads/generate-project-catalog-ms47vq35/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/generate-catalog' && cp -R '.skill-downloads/generate-project-catalog-ms47vq35' '.claude/skills/generate-catalog'

Codex
test -f '.skill-downloads/generate-project-catalog-ms47vq35/SKILL.md' && test -s '.skill-downloads/generate-project-catalog-ms47vq35/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/generate-catalog' && cp -R '.skill-downloads/generate-project-catalog-ms47vq35' '.agents/skills/generate-catalog'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/generate-project-catalog-ms47vq35'

openskills read 'generate-project-catalog-ms47vq35'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/generate-project-catalog-ms47vq35/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills