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

Sdd Develop

ASecurity

Execute one PLAN baby step (code in English; PLAN in file language, pt-BR default). One session = one step. Use when implementing a PLAN step or invoking /sdd-develop.

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

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 sdd-develop --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sdd Develop?

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

Security grade badge for Sdd Develop
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tibursocampos-sdd-develop-b2f12384/badge)](https://www.skillsdirectory.com/skills/tibursocampos-sdd-develop-b2f12384)

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: sdd-develop
description: Execute one PLAN baby step (code in English; PLAN in file language, pt-BR default). One session = one step. Use when implementing a PLAN step or invoking /sdd-develop.
---

## 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 **repo** session for `$Cwd`, then after PLAN path is known load **develop** session scoped by PLAN (or PLAN+step) - see `SESSION.md`
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** that develop scope - 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; repo + develop (PLAN-scoped) session loaded
[ ] PIPELINE.md read (SDD skills only)
[ ] User confirmed current action (sim)
-> If any unchecked: STOP
```

---

# Skill: sdd-develop

## Trigger

Invoke when the user asks for: `/sdd-develop`, `implement step`, `execute step`.

## Outcome

One **PLAN step** done: **code and tests in English**; PLAN updated in place. Do not start the next step in the same develop session scope.

**Session scoping:** After the PLAN path is resolved, load/create the develop session file per `SESSION.md` (`sessions/{repo-hash}/plan-{plan-hash}.json`). When spawned as an O3 parallel child on the same PLAN, use `plan-{plan-hash}-step-{N}.json`. Gates `step_confirmed` / `tests_run` apply only to that scoped file - never share one flat repo JSON across parallel children. Repo session still owns `storage_confirmed` / `write_confirmed`.

## Language

| Deliverable | Language |
|-------------|----------|
| Code, tests, comments, XML docs | **English** |
| PLAN progress / notes | **Same as PLAN file** |
| Product `docs/` / README | Ask pt-BR vs English first |

Do not re-ask SDD storage or change artifact language mid-PLAN unless requested.

## Required input

| Input | Rule |
|-------|------|
| PLAN path | Canonical only: `features/NNN-slug/USnn/PLAN/PLAN_NNN_*.md` (or `TSnn`; global under `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/sdd/<repo-id>/features/...`). Root/flat `PLAN/` is **not** valid - do not read/update for execution |
| Step | `Step 1`, `PASSO 1`, etc. |

## Lazy-load (only when needed)

| When | Path |
|------|------|
| Pipeline, missing PLAN dialog | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/skills/_shared/sdd-artifacts/PIPELINE.md` |
| Storage | `STORAGE.md` |
| Caveman Mode (if active) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/install-root/skills/_shared/caveman/CAVEMAN.md` - **Full cap** |
| .NET, Git, context | `dotnet-guidelines/*.md`, `branch-validation.mdc`, `conventional-commits.mdc`, `developer-common/GUIDE.md`, `context-management.mdc` |

## Process

### Step -1b - Caveman Mode (Full 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 **Full** 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`.

### -1. Pipeline and mode

Load `STORAGE.md` and `PIPELINE.md`. Use `STORAGE.md` schema v2 and run the dynamic storage resolution algorithm with parameter `$Workflow = classic`. Resolve `storage_mode` and `path` for the active repository. If this is the first run for the repository, execute storage mode selection and persist it in `manifest.json`.
**Agent mode** is required for code changes and PLAN updates. If the user asks for PRD (`sdd-spec`) or PLAN (`sdd-plan`), route using `PIPELINE.md` section Missing artifacts; do not create PRD/PLAN in this skill.

### 0. Workspace

Target repo. Resolve PLAN:

| Situation | Action |
|-----------|--------|
| Canonical PLAN path given (`features/.../PLAN/` or global `.../features/.../PLAN/`) | `Read` at exact path; update **that** file in place |
| Root/flat `PLAN/` or other non-canonical path | **STOP** - ask user to migrate under `features/.../PLAN/` via `sdd-plan`; do not execute |
| No canonical PLAN path | Glob `features/**/PLAN/PLAN_*.md` only (workspace + global feature root); if not found, use `PIPELINE.md` section `sdd-develop` without PLAN (options 1-3) |
| Path under `features/NNN-slug/` | Optionally load `CONTINUITY.md` / story `STORY.md` for Prior context only - **do not** change multi-step rules |
| User asks "criar PRD/sdd-plan" | Redirect to `sdd-spec` / `sdd-plan`; stop |

Detect stack from PLAN step.

After PLAN path is known: create `{sessions}/{repo-hash}/` if needed; load or create develop session with gates `false` (`SESSION.md` § Develop session - never copy develop gates from the flat repo JSON). If this child was given an explicit step-scoped path (O3 parallel same PLAN), use `plan-{plan-hash}-step-{N}.json`.

### 1. Validate step

Step exists; deps **Concluidos** / **Completed**; summarize objective, files, tests; ask to proceed.

### 2. Git

Feature branch per `branch-validation.mdc`.

### 3-4. Analyze and implement

Glob/Grep/Read scope. Code/tests in English; targeted build/test.

### 5. Commit (optional)

Offer `/commit`; do not auto-commit.

### 6. Update PLAN + checkpoint

`reference.md`: mark step done, progress, next step. Save before context pause (>=40%).

### 7. Report

Files, tests, `N/M` (pt-BR). Handoff: new chat -> `/sdd-develop - <full-plan-path> - Step N+1`.

## Must not

- Portuguese application code; **multiple PLAN steps per develop session scope** (contract unchanged)
- Create PRD/PLAN; skip PLAN save; modify `.gitignore`
- Implement in Plan/Ask without Agent
- Bypass one-step via orchestrator parent implementing code
- Use the flat `{repo-hash}.json` for `step_confirmed` / `tests_run` when a PLAN path is known - always use the PLAN-scoped file (or PLAN+step); create scoped with gates false if missing

## Handoff

| Situation | Next |
|-----------|------|
| Commit | `/commit` |
| Next step | New session -> `/sdd-develop - <full-plan-path> - Step N+1` |
| All steps done | `/code-review` (pass `- single` / `- multi-angle`, or let skill ask) |

Example full path (Classic SDD):

```
/sdd-develop - features/004-export-profile/US01/PLAN/PLAN_004_export_profile.md - Step 2
```

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 →