Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Document Plan

ASecurity

Create a baby-step documentation plan (overview + domain deep dives for RAG). Asks doc language before writing. Use when planning repo docs or invoking /document-plan.

6 stars
0 votes
0 copies
0 views
Added 9/25/2026
ai-agentsshellangularrailsgitapidocumentation

Works with

cursorapi

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/25/2026

$npx -y skills add tibursocampos/agent-dev-toolkit --skill document-plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Document Plan?

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

Security grade badge for Document Plan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tibursocampos-document-plan-9f284445/badge)](https://www.skillsdirectory.com/skills/tibursocampos-document-plan-9f284445)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: document-plan
description: Create a baby-step documentation plan (overview + domain deep dives for RAG). Asks doc language before writing. Use when planning repo docs or invoking /document-plan.
---

## STOP - Read before ANY tool call

1. Read `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/rules/guardrails.md`
2. Read `_shared/sdd-artifacts/SESSION.md`; load session-state for `$Cwd`
3. If the relevant gate is not approved: **STOP** - ask user **(pt-BR)** - do **NOT** Write/Shell
4. SDD/develop skills: after **ONE** step/task, **STOP** session - handoff only
5. This skill body is **English**; user-facing prompts may be **(pt-BR)**

### Step -1 - Gate check (report in chat before continuing)

```
Gate check:
[ ] guardrails.mdc read
[ ] SESSION.md read; session-state loaded
[ ] PIPELINE.md read (SDD skills only)
[ ] User confirmed current action (sim)
-> If any unchecked: STOP
```

---

# Skill: document-plan

## Trigger

Invoke when the user asks for: `/document-plan`, `plan repo documentation`, `/document-plan`, or `doc plan`.

Optional argument: path to an existing **reviewed** `docs/overview.md` (or equivalent) to seed the plan.

## Outcome

In the **target workspace** (not `cursor-dev-toolkit` unless that is the repo to document):

- `docs/documentation-plan/plan.md` - baby-step documentation plan with progress tracking
- `docs/overview.md` - high-level repo summary (created or refreshed unless user supplied overview)

Product documentation prose follows the **language the user chooses** (pt-BR or English). File paths stay in English.

## Lazy-load

| When | Path |
|------|------|
| Caveman Mode (if active) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/skills/_shared/caveman/CAVEMAN.md` - **Lite cap** |
| Plan template, domain checklist | `skills/document-plan/reference.md` or `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/skills/document-plan/reference.md` after sync |
| SDD vs RAG plan boundary | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/skills/_shared/sdd-artifacts/STORAGE.md` (read section Read-only discovery - do not conflate paths) |
| Context pressure | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/rules/context-management.mdc` |

## Process

### Step -1b - Caveman Mode (Lite cap)
1. Read `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/sdd/preferences.json` (create `{ "caveman_mode": false, "caveman_level": "full" }` if missing).
2. If `caveman_mode` is false: continue without compression.
3. If true: load `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/skills/_shared/caveman/CAVEMAN.md`; apply **Lite** participation cap + prefs `caveman_level` (Lite skills never escalate); show once: `[Caveman] Modo ativo (respostas compactas, level={effective}). Digite caveman off para desativar.`
4. Honor `caveman on|off|status|lite|full|ultra` (and `stop caveman` / `normal mode`) during the session.
5. Auto-Clarity + never-compress gates/drafts/paths per `CAVEMAN.md`.

### 0. Workspace and stack

1. Confirm **target repository** (consumer app/service - not the toolkit unless explicit).
2. Detect stack with Glob (see `reference.md` section Stack detection). Summarize: languages, frameworks, layout - **do not** assume a fixed corporate stack.
3. Read `AGENTS.md` / `README.md` if present.

**Not SDD:** this skill writes `docs/documentation-plan/plan.md` only - not `PLAN/PLAN_*.md` or `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/sdd/<repo-id>/PLAN/`. Feature PRD/PLAN use `sdd-spec` / `sdd-plan` / `sdd-develop` per `STORAGE.md`.

### 1. Documentation language (blocker)

Before creating or updating any file under `docs/` in the target repo, ask once:

> Documentation language for product `docs/` - **pt-BR** or **English**?

Record the choice in the session and in `docs/documentation-plan/plan.md` header (see template).

### 2. Existing artifacts

| Path | Action |
|------|--------|
| `docs/documentation-plan/plan.md` | If exists: read completed steps; resume or ask to overwrite |
| `docs/overview.md` | Use user-provided path, existing file, or generate from exploration |
| Neither | Create both per `reference.md` |

### 3. Explore and draft overview

Glob/Grep/Read: solution layout, main entry points, bounded contexts, external integrations, test layout. Write or update `docs/overview.md` in the chosen language - concise, RAG-friendly, no invented business domain names.

### 4. Write documentation plan

Create or update `docs/documentation-plan/plan.md` using `reference.md` section Plan template:

- Baby steps per business/technical domain
- Steps for integrations, architecture patterns, and folder conventions
- Progress `0/N`, status per step (**Pending** / **Completed**)
- Each step sized for one `document-implement` session where possible

### 5. Context checkpoint

After finishing overview + plan (or after each major planning chunk if the repo is large), follow `context-management.mdc`: at **>= 40%** context, save `plan.md` and pause; ask whether to continue in a new chat.

### 6. Summarize handoff

Report: paths written, language, step count, first pending step id.

```
/document-implement
```

## Must not

- Embed MES, Athena, or organization-specific product context
- Require external wiki APIs, or fixed .NET/Angular versions without detection
- Create `docs/documentation-plan/` inside **cursor-dev-toolkit** during porting (only in consumer repos at runtime)
- Write `docs/` before the language question is answered
- Default product doc language without asking

## Handoff

| Situation | Next |
|-----------|------|
| Execute next doc step | `/document-implement` |
| Code change needed | `/developer` or SDD `sdd-develop` |
| Commit docs | `/commit` |

Attribution

tibursocampostibursocampos
View sourceSee grades on GitHubMore from tibursocampos →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →