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

Developer

ASecurity

Smart router for stack skills, or senior fullstack for ad-hoc scripts/HTML/automation. Use for generic development or when invoking /developer.

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

Works with

cursor

Security Analysis

A100/100

Scanned 9/25/2026

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

Installs into .claude/skills of the current project.

Are you the author of Developer?

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

Security grade badge for Developer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tibursocampos-developer-0fc77860/badge)](https://www.skillsdirectory.com/skills/tibursocampos-developer-0fc77860)

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: developer
description: Smart router for stack skills, or senior fullstack for ad-hoc scripts/HTML/automation. Use for generic development or when invoking /developer.
---


## STOP - Read before ANY tool call

1. Read `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/rules/guardrails.mdc`
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
[ ] User confirmed current action (sim)
-> If any unchecked: STOP
```

### Step -1b - Caveman Mode (Full cap)
1. Read `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-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/zcode-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`.

---

## Trigger

Use when user asks for `/developer` or requests generic coding/refactoring tasks without specifying a stack.

## Outcome

Correct stack skill loaded and executed, or ad-hoc implementation in fallback mode with optional handoff to `/commit`.

## Lazy-load (only when needed)

| When | Path (after `scripts/sync-cursor.ps1`) |
|------|----------------------------------------|
| Git / language policy | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/AGENTS.md`, `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/rules/branch-validation.mdc` |
| Developer flow | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/skills/_shared/developer-common/GUIDE.md` |
| Context pressure | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/rules/context-management.mdc` |
| Subagent-first / SPAWN.md | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/skills/_shared/developer-common/subagent-first.md`, `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/skills/_shared/agents/SPAWN.md` |
| Caveman Mode (if active) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/skills/_shared/caveman/CAVEMAN.md` |

Do **not** load `dev_persona` or Antigravity KI artifacts.

## Frontend design routing

Before UI implementation, check project context:

1. If the task is **net-new UI** or a **visual redesign** and `PRODUCT.md` is missing -> recommend `/impeccable init` first (new session).
2. If `docs/DESIGN-BRIEF.md` (or `docs/design/DESIGN-BRIEF.md`) exists -> treat it as acceptance source; delegate to the matching `*-developer` skill **without reinterpreting visual decisions**.
3. One session = design (`impeccable shape`) **or** implementation (`*-developer`), not both.

Premium UI without a brief -> suggest `/impeccable shape` before stack implementation.

## Routing Logic

1. **Inspect the workspace** - identify stack in this order (frameworks before generic Node):

   | Signal | Route to |
   |--------|----------|
   | User asks for **new** Blip plugin scaffold (no existing `blip-ds` project) | `blip-plugin-developer` |
   | `package.json` with `blip-ds` and `iframe-message-proxy` (existing Blip plugin) | `react-developer` (loads `blip-guidelines/`) |
   | `.csproj` with `Microsoft.AspNetCore.Components`, or `_Imports.razor` / `App.razor` | `blazor-developer` |
   | `package.json` with `electron`, `electron-builder`, or `electron-vite` | `electron-developer` |
   | `package.json` with `vue` (and not React/Angular) | `vue-developer` |
   | `package.json` with `react-native` or `expo` | `react-native-developer` |
   | `package.json` with `react` | `react-developer` |
   | `package.json` with `@angular/core` or `angular` | `angular-developer` |
   | `package.json` (Node.js, no framework above) | `javascript-developer` |
   | `.csproj` / `.sln` without Blazor markers | `dotnet-developer` |
   | `pom.xml`, `build.gradle`, `build.gradle.kts`, or `settings.gradle` | `java-developer` |
   | `.py`, `requirements.txt`, `pyproject.toml` | `python-developer` |

2. **Invoke the specialized skill (if match found)**:
   - Silently read the `SKILL.md` of the matched stack under `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/zcode-install-root/skills/`:
     - `blip-plugin-developer`, `blazor-developer`, `electron-developer`, `vue-developer`, `react-native-developer`, `dotnet-developer`, `java-developer`, `react-developer`, `angular-developer`, `javascript-developer`, or `python-developer`
   - Assume the identity and instructions of that skill immediately.
   - Do **not** ask the user for confirmation to switch skills.

3. **Fallback mode (if no match found)**:
   - If no major framework structure is detected (e.g., isolated `.html`, `.sh`, `.bat`, `.ps1` files), **do not delegate**.
   - Assume the task directly using standard, secure engineering practices as a Senior Developer.
   - Proceed to the Execution Process below.

## Execution Process (fallback mode only)

### Subagent-first (before implement)

Stack `*-developer` skills own this policy when routed. In fallback mode: classify complexity → consult capability `subagents` → if medium/complex and `native`: spawn ≤2 children (scoped **paths** + **receipt**); **trivial** stays **in-parent**; if `subagents=none` or Task unavailable → **fallback** **in-parent** (never hard-fail). Load `SPAWN.md` + `subagent-first.md`; do not paste guidelines into child prompts.

### 0. Workspace

Confirm target repo, read `README.md` (if exists), and summarize requested acceptance.

### 1. Micro-plan

Define 2-5 concrete tasks. Checkpoint context usage after each major change per `context-management.mdc`.

### 2. Implement

Write clean, maintainable code following universal best practices for the target language (e.g., HTML, Bash, Python script).

### 3. Tests / Validation

Run local scripts or linting tools to ensure the code executes without syntax errors.

### 4. Handoff

Offer `/commit`. Do not commit automatically.

## Must not

- Paste guideline packs into child prompts (pass scoped **paths** + require **receipt** only)
- Spawn children for **trivial** work (keep **in-parent**)
- Hard-fail when capability `subagents` is `none` or Task is unavailable (use **fallback** **in-parent**)
- Auto-commit or auto-PR
- Leave AI traces in code comments or identifiers (see `ai-stealth.mdc`)
- Delegate when a clear stack match exists

## Handoff

| Situation | Next |
|-----------|------|
| Commit | `/commit` |
| .NET work (explicit) | `/dotnet-developer` |
| Java work (explicit) | `/java-developer` |
| Large scope | `/sdd-spec` -> `sdd-plan` -> `sdd-develop` |
| UI design / brief | `/impeccable` (`shape` / `craft`) |
| New Blip plugin scaffold | `/blip-plugin-developer` |

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', ...

698461 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 →