Auto Doc Index

Auto-generate document index tables (ADR, RFC, Pitfall, etc.) from file frontmatter. In real-world testing, hand-maintained indexes had a 62% error rate — ti...

Security Scan

The skill's code, instructions, and requirements are coherent with its stated purpose: it scans doc files, parses frontmatter with regex, and replaces a marked section in README.md with an auto-generated table — there is no unrelated credential access, network exfiltration, or surprising install behavior.

Purpose & Capability

Name and description (auto-generate index tables from frontmatter) match the included template script and SKILL.md. The script only reads markdown files in a project doc tree and writes README.md index sections; no unrelated services, credentials, or binaries are requested.

Instruction Scope

SKILL.md instructs copying the included TypeScript template and running it to regenerate index sections between <!-- INDEX:START --> and <!-- INDEX:END --> markers. The runtime instructions and the script are consistent: they only read files under the doc/adr and doc/pitfall directories and write the README.md files in those directories. Note: the script uses regex-based parsing (no YAML lib) by design and uses a DOC_ROOT of join(__dirname, '..', 'doc'), so consumers must place the script or adjust paths appropriately. There is no instruction to read unrelated files, environment variables, or send data externally.

Install Mechanism

This is instruction-only (no install spec). The template is included as source code (TypeScript). There are no external downloads or install steps in the skill itself. Practical usage advice in README suggests running via `npx tsx`, which will pull a runtime from npm at execution time — not part of a packaged install but something users should be aware of.

Credentials

The skill declares no required environment variables or credentials and the script does not read any environment variables or config paths. The level of access requested (filesystem read of doc files and write to README.md in the targeted directories) is proportionate to the stated purpose.

Persistence & Privilege

always is false and the skill does not request permanent system presence or modify other skills or global agent settings. The default ability for the agent to invoke the skill autonomously is not problematic here and is typical for skills.

Assessment

This skill appears to do what it says: generate index tables from per-file frontmatter and inject them between explicit markers in README.md. Before using it: (1) back up your README.md (or run in a branch/CI) so you can inspect diffs the first time it runs, (2) add the required <!-- INDEX:START/END --> markers in the intended README, (3) ensure the script's DOC_ROOT matches where your docs live (the template expects ../doc relative to the script), (4) be aware the parser is regex-based — it may mis-handle unusual frontmatter formats — review generated output for correctness, and (5) running with `npx tsx` will fetch a runtime from npm at execution time, so if you prefer no network fetch, compile/transpile the script or run with an existing local Node toolchain. If you need broader guarantees (e.g., CI-only execution), integrate the generator into CI or pre-commit hooks and require reviewers to inspect the generated changes.

Auto Doc Index — Derived Indexes from Frontmatter

Replaces hand-maintained index tables in README.md with auto-generated tables derived from structured frontmatter in individual doc files.

Why This Matters — Real Evidence

In a real project with 13 ADR files, comparing hand-maintained index vs auto-generated index revealed 8 discrepancies (62% error rate):

Issue Type	Example	Count
Title truncated	"activate none" vs actual "activate none by default"	2
Status fabricated	Index said "Decided" but file said "Accepted"	3
Date invented	Index showed "2026-01-28" but file had no Date field	1
Metadata lost	"(revised 2026-01-28)" stripped from status	1
Case "normalized"	decided silently changed to Decided	4

These aren't hypothetical risks — they were already present and invisible in a well-maintained project. Hand-editing creates a false sense of correctness while the index silently diverges from its source files.

When to Use

• Setting up a new documentation directory (ADR, RFC, Pitfall, Design Doc, etc.)
• Adding a new document to an existing indexed directory
• Onboarding a project that has hand-maintained doc indexes showing signs of drift
• Resolving recurring merge conflicts in shared README.md index tables
• Migrating from hand-maintained indexes to auto-generated ones

Boundaries

• This skill generates index tables only — it does not create or modify the content of individual documents.
• The generator script replaces content only between <!-- INDEX:START --> and <!-- INDEX:END --> markers. All other README.md content is preserved verbatim.
• Do NOT use this for indexes that require editorial curation (e.g., "recommended reading order"). Auto-generation is for factual, exhaustive catalogs.
• Do NOT introduce YAML frontmatter parsing libraries — the regex-based approach is intentional to keep the script zero-dependency.
• This skill targets file-system-based documentation. It does not apply to wiki-style or database-backed doc systems.

Problem

A hand-maintained index in README.md is shared mutable state — every new document requires editing the same file, same table, often the same diff hunk. In multi-agent or multi-contributor workflows this creates:

• Silent data loss: titles get shortened, statuses get "corrected"
• Merge conflicts: semantically independent changes collide in the same hunk
• Stale indexes: contributors forget to update, nobody notices
• Normalization illusion: edits look "cleaner" but diverge from source

Solution

Each document is self-describing via frontmatter. A generator script scans the directory, parses frontmatter, and injects the index table between <!-- INDEX:START --> / <!-- INDEX:END --> markers in README.md.

Write ops become N:N (each file independent). Index becomes a stateless pure function.

Setup Steps

1. Define frontmatter convention

Choose a frontmatter format for your doc type. Two common patterns:

Pattern A — Inline metadata (ADR/RFC style):

# ADR-001: Title Here

Status: Decided
Date: 2026-01-28

## Context
...

Pattern B — Bold-field metadata (Pitfall/Postmortem style):

# PIT-001: Title Here

**Date:** 2026-01-28
**Area:** engine
**Severity:** high
**Status:** resolved

2. Add markers to README.md

Wrap the existing index table (or create a placeholder) with markers:

## Index

<!-- INDEX:START -->
| ADR | Title | Status | Date |
|-----|-------|--------|------|
<!-- INDEX:END -->

## Other Sections (preserved)
...

Content outside markers is never touched by the generator.

3. Create the generator script

Copy template/generate-doc-index.ts from this skill's template directory, or generate a new one following the pattern below.

Core architecture (zero external dependencies):

// 1. Scan directory for matching files (e.g. /^\d{3}-.*\.md$/)
// 2. Parse frontmatter from each file (regex-based, no YAML lib needed)
// 3. Sort entries by ID/number
// 4. Generate markdown table string
// 5. Inject between <!-- INDEX:START --> and <!-- INDEX:END --> markers

See template/generate-doc-index.ts for a working implementation that handles both Pattern A and Pattern B.

4. Run the generator

npx tsx scripts/generate-doc-index.ts all

5. Update documentation governance

Add to your project's AGENTS.md or CONTRIBUTING.md:

Rule: Never hand-edit the index table between <!-- INDEX:START/END --> markers. To add a new document, create the .md file with proper frontmatter, then run the generator.

Workflow Comparison

OLD: Write doc → Hand-edit README.md index → Conflict risk
NEW: Write doc → Run generator → Idempotent rebuild, zero conflicts

Adding a New Doc Type

To support a new document category (e.g. RFCs, Design Docs):

1. Define the frontmatter convention
2. Add a parser function (regex for title, status, date, etc.)
3. Add a table generator function (column layout)
4. Add <!-- INDEX:START/END --> markers to the README.md
5. Register in the script's main() dispatcher

Anti-patterns

• Do NOT use YAML frontmatter libraries — regex is sufficient and avoids deps.
• Do NOT generate the entire README.md — only the index section. Preserve manually-written intro, templates, and notes via the marker pattern.
• Do NOT require contributors to run the generator before committing. Run it in CI or as a pre-commit hook for enforcement.

Checklist

- [ ] Frontmatter convention defined for each doc type
- [ ] README.md has <!-- INDEX:START --> and <!-- INDEX:END --> markers
- [ ] Generator script created and tested
- [ ] Documentation governance updated (AGENTS.md / CONTRIBUTING.md)
- [ ] (Optional) Pre-commit hook or CI step added