skill-developer

Name: skill-developer
Author: Dokhacgiakhoa

AI Community v4.1.0-fractal

Repo stars 437
Author repo antigravity-ide

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.jso…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Purpose”, “When to Use This Skill”, “System Overview”, “🧠 Knowledge Modules (Fractal Skills)”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name skill-developer directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Purpose / When to Use This Skill / System Overview” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / env-read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: AI
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 92 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @Dokhacgiakhoa · v4.1.0-fractal · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Plug-and-play
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Env read
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview skill-developer-dokhacgiakhoa.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Skill Developer Guide

## Purpose

Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best practices including the 500-line rule and progressive disclosure pattern.

## When to Use This Skill

Automatically activates when you mention:
- Creating or adding skills
- Modifying skill triggers or rules
- Understanding how skill activation works
- Debugging skill activation issues
- Working with skill-rules.json
- Hook system mechanics
- Claude Code best practices
- Progressive disclosure
- YAML frontmatter
- 500-line rule

---

## System Overview

## 🧠 Knowledge Modules (Fractal Skills)

### 1. [Two-Hook Architecture](./sub-skills/two-hook-architecture.md)
### 2. [Configuration File](./sub-skills/configuration-file.md)
### 3. [1. Guardrail Skills](./sub-skills/1-guardrail-skills.md)
### 4. [2. Domain Skills](./sub-skills/2-domain-skills.md)
### 5. [Step 1: Create Skill File](./sub-skills/step-1-create-skill-file.md)
### 6. [Step 2: Add to skill-rules.json](./sub-skills/step-2-add-to-skill-rulesjson.md)
### 7. [Step 3: Test Triggers](./sub-skills/step-3-test-triggers.md)
### 8. [Step 4: Refine Patterns](./sub-skills/step-4-refine-patterns.md)
### 9. [Step 5: Follow Anthropic Best Practices](./sub-skills/step-5-follow-anthropic-best-practices.md)
### 10. [BLOCK (Critical Guardrails)](./sub-skills/block-critical-guardrails.md)
### 11. [SUGGEST (Recommended)](./sub-skills/suggest-recommended.md)
### 12. [WARN (Optional)](./sub-skills/warn-optional.md)
### 13. [1. Session Tracking](./sub-skills/1-session-tracking.md)
### 14. [2. File Markers](./sub-skills/2-file-markers.md)
### 15. [3. Environment Variables](./sub-skills/3-environment-variables.md)

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Purpose → When to Use This Skill → System Overview → 🧠 Knowledge Modules (Fractal Skills) → 1. [Two-Hook Architecture](./sub-skills/two-hook-architecture.md) → 2. [Configuration File](./sub-skills/configuration-file.md)
terms    -> no emphasized key terms
files/cmd -> skill-rules.js · ./sub-skills/two-hook-architecture.md · ./sub-skills/configuration-file.md · ./sub-skills/1-guardrail-skills.md · ./sub-skills/2-domain-skills.md · ./sub-skills/step-1-create-skill-file.md · ./sub-skills/step-2-add-to-skill-rulesjson.md · ./sub-skills/step-3-test-triggers.md
body sha256 -> e27b4ece600a

skill-developer

Decide Fit First

Design Intent

How To Use It

Boundaries And Review

Skill Developer Guide

Purpose

When to Use This Skill

System Overview

🧠 Knowledge Modules (Fractal Skills)

1. Two-Hook Architecture

2. Configuration File

3. 1. Guardrail Skills

4. 2. Domain Skills

5. Step 1: Create Skill File

6. Step 2: Add to skill-rules.json

7. Step 3: Test Triggers

8. Step 4: Refine Patterns

9. Step 5: Follow Anthropic Best Practices

10. BLOCK (Critical Guardrails)

11. SUGGEST (Recommended)

12. WARN (Optional)

13. 1. Session Tracking

14. 2. File Markers

15. 3. Environment Variables

16. TRIGGER_TYPES.md(TRIGGER_TYPES.md)

17. SKILL_RULES_REFERENCE.md(SKILL_RULES_REFERENCE.md)

18. HOOK_MECHANISMS.md(HOOK_MECHANISMS.md)

19. TROUBLESHOOTING.md(TROUBLESHOOTING.md)

20. PATTERNS_LIBRARY.md(PATTERNS_LIBRARY.md)

21. ADVANCED.md(ADVANCED.md)

22. Create New Skill (5 Steps)

23. Trigger Types

24. Enforcement

25. Skip Conditions

26. Anthropic Best Practices

27. Troubleshoot

Discussion