Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Adr

ASecurity

**Status:** Accepted

16 stars
0 votes
0 copies
0 views
Added 9/20/2026
documentationgoapidocumentation

Works with

api

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add woditschka/agentic-coding-reference --skill adr --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adr?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Adr
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/woditschka-adr/badge)](https://www.skillsdirectory.com/skills/woditschka-adr)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
2026-03-22-skill-based-agent-architecture.md
# The document-writing Skill: Documentation Standards Ship as Runtime, Not Handbook

**Status:** Accepted

## Context

Two problems sat together. First, `doc-review` was a reviewer-named skill living in `stacks/`, yet authoring agents (PRE, system-design-expert, adr-template) referenced it for the writing standards they had to *follow* — authors reaching into the reviewer's rulebook. Second, the writing standards existed twice: as the root handbook `documentation-standards.md` and as the skill's `§ Writing Standards`, kept aligned only by an audit check.

The deeper issue: `documentation-standards.md` was the richer, 520-line artifact — the five-document architecture, ownership boundaries, cross-reference and maintenance rules, worked examples — but it was **root-only handbook, never installed**. A deployed agent only ever saw the thin operational subset. The fuller standard could not raise the bar on agent output because agents never received it.

## Options Considered

1. **Keep the handbook, point authors at the reviewer skill** — status quo wiring; the standard stays uninstalled and the author↔reviewer coupling stays backwards.
2. **Keep the handbook, enrich the skill toward it** — agents get more, but two substantive copies now drift.
3. **Move the full standard into one skill and delete the handbook** — single source, installed everywhere; the handbook stops existing as a separate document.

## Decision

Option 3.

- Rename `doc-review` → **`document-writing`**: one skill, two consumers. Every author **follows** it; the `doc-reviewer` **enforces** it. The `doc-reviewer` agent and its `author` enum are unchanged.
- The skill spans both layers, merged at materialize: `core/.../document-writing/` carries the language-agnostic standard in `documentation-standards.md` (the rules) plus `SKILL.md` (the agent obligations and author validation checklist); `stacks/<stack>/.../document-writing/review-checks.md` carries the stack-specific review checklist (prohibited-pattern rows, path-coherence checks, the review process).
- The root `documentation-standards.md` handbook is deleted; its content moves into the skill — shipped as the skill's own `documentation-standards.md` companion, neutralized for the stack-agnostic core, with `SKILL.md` as the operational entry that follows the same `SKILL.md` + named-companion shape as `tdd-workflow`. Every reference repoints to the committed skill source.
- Ownership detail follows its own rule — one home per fact. Each document's boundary lives in the skill that governs it (`prd-authoring`, `adr-template`); `document-writing` keeps the cross-document **map** and the CLAUDE.md and system-design boundaries that no other skill owns.

## Consequences

**Positive:**
- The full standard ships into every project; agents author against the architecture, ownership, and cross-reference rules they never had before.
- One source for the writing standards — the handbook↔skill duplication is gone.
- Authors and the reviewer read the same rulebook; the backwards coupling is resolved.
- The universal standard de-duplicates across stacks (one core copy, not two).

**Negative:**
- The standard is less prominent as a *human* document — it lives in a skill path, surfaced via README links rather than a top-level handbook.
- The standard is large (~330 lines in `documentation-standards.md`); it loads into agent context whenever the skill is invoked.
- The skill restates concerns the governing skills own; the ownership-as-map split contains the overlap, and the audit guards drift.

## References

- [Project History](../../README.md#project-history) — the what/when timeline
- [`2026-06-12-docs-as-harness-project-api.md`](2026-06-12-docs-as-harness-project-api.md) — listed `documentation-standards.md` among harness-owned handbook docs; this ADR collapses it into the runtime skill
- [`2026-06-03-principles-over-rigid-rules.md`](2026-06-03-principles-over-rigid-rules.md) — its writing-standard reconciliation now points at the skill

Attribution

woditschkawoditschka
View sourceMore from woditschka →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Context Fundamentals

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

179001 votes

release-notes

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), including breaking changes, migrations, and upgrade steps. Use when the user asks for release notes, changelog updates, or a GitHub Release draft.

1301 votes

docs-style-guide

Documentation style guide enforcer by @planetabhi. Applies and reviews the writing style guide when authoring or editing product documentation and tutorials. Use to check prose for voice, tense, word choice, inclusive language, formatting, code block, UI, Markdown, and number/date conventions.

11 votes

Caveman Help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

1023330 votes

How It Works

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

942310 votes
View all in documentation →