[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F31WXC01V3GQP7YPXCEFV4":3,"skill-same:01M7F31WXC01V3GQP7YPXCEFV4":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":12,"updatedAt":33,"install":34,"resources":46},"01M7F31WXC01V3GQP7YPXCEFV4","scaffold",null,"Interactive coach that asks 4-5 questions to determine whether you need an agent, command, skill, hook, or rule, then generates a ready-to-use template. Usage: \u002Fscaffold (no arguments needed, starts the coaching session)","313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","313DEVGRP","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34762848?v=4","01M7F2M535Z5X8XGHYD8TDVAB3","A-RMS by 313DEVGRP","01M7F2M54CR0P3631F4YM0D014",0,"MIT","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fscaffold\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: scaffold\ndescription: \"Interactive coach that asks 4-5 questions to determine whether you need an agent, command, skill, hook, or rule, then generates a ready-to-use template. Usage: \u002Fscaffold (no arguments needed, starts the coaching session)\"\neffort: medium\ndisable-model-invocation: true\n---\n\n# Claude Code scaffold coach\n\nInteractive wizard that identifies the right Claude Code component for your use case and generates a ready-to-use template.\n\n**Usage**: `\u002Fscaffold` (no arguments needed). Start the conversation.\n\n---\n\n## Phase 1: Discovery\n\nOpen with this prompt, then wait for the user's answer before asking anything else:\n\n> What do you want to automate or build? One sentence is enough to start.\n\nOnce you have a rough idea, ask the following questions in order. Skip a question if a previous answer already answers it.\n\n### Q1: Trigger\n\n> How is this triggered?\n>\n> a) I run it myself with a command (e.g. `\u002Fsomething`)\n> b) It should fire automatically when Claude takes an action (writes a file, runs bash, finishes a session...)\n> c) It should apply all the time, every session, without me doing anything\n\n- If **b** → likely a **Hook** (jump to Q_hook)\n- If **c** → likely a **Rule** (jump to Q_rule)\n- If **a** → continue with Q2\n\n### Q2: Domain expertise\n\n> Does this require deep, project-specific expertise?\n> For example: knowing your GraphQL schema, your migration conventions, your internal API patterns, your cost model...\n\n- If **yes, deep expertise** → likely an **Agent** (jump to Q_agent)\n- If **no, more of a checklist or procedure** → continue with Q3\n\n### Q3: Complexity\n\n> How much context and logic does this involve?\n>\n> a) A lot: multiple rules, domain-specific examples, nuanced judgment\n> b) Straightforward: a few steps, a template, some bash\n\n- If **a** → likely a **Skill**\n- If **b** → likely a **Command**\n\n### Q4: Reuse scope\n\n> Who needs this?\n>\n> a) Just me\n> b) My whole team\n> c) It needs to be invokable by other agents automatically\n\n- **c** → strengthens **Agent** (needs a `description:` field that other agents can read)\n- **b** → strengthens **Command** or **Skill** (shared config)\n- **a** → can stay a simple personal **Command**\n\n### Q5: Output type\n\n> What should happen at the end?\n>\n> a) A report or analysis: Claude reads and explains, no files touched\n> b) Code or files generated\n> c) An action taken (commit, push, API call...)\n> d) Claude's behavior changes permanently (always does X, never does Y)\n\n- **a** → read-only Agent (no `Write` or `Bash` in tools)\n- **b\u002Fc** → Agent or Command\u002FSkill with write access\n- **d** → Rule, or Hook if conditional on a specific event\n\n---\n\n## Internal decision tree (do not display, use to reason)\n\n```\nTriggered automatically?\n  ├─ On Claude action (Write, Bash, SessionEnd...) -> Hook\n  └─ Always active, no trigger -> Rule\n\nTriggered manually?\n  ├─ Deep domain expertise required?\n  │   ├─ Yes + invokable by other agents -> Agent\n  │   └─ Yes + manual use only -> Agent or Skill\n  └─ Procedure \u002F checklist, no special expertise?\n      ├─ Complex, lots of project-specific context -> Skill\n      └─ Simple, a few steps -> Command\n\nCommon hybrid cases:\n  - Agent + Command: specialist agent + a shortcut command to invoke it\n  - Rule + Hook: permanent behavior + blocking on a specific action\n  - Skill + Agent: skill that delegates analysis to an agent\n```\n\n---\n\n## Phase 2: Recommendation\n\nAfter the questions, display this structure:\n\n```\n## Diagnosis\n\nYou want to: [one-line summary of the use case]\n\n## Recommendation: [TYPE]\n\n**Why?**\n[2-3 sentences: trigger type, complexity level, reuse scope]\n\n**What it would NOT be, and why:**\n- Not an agent because [short reason]\n- Not a rule because [short reason]\n[adjust based on actual candidates]\n\n**Hybrid case?** [Yes \u002F No]\n[If yes: explain the combination and which file to create first]\n```\n\n---\n\n## Phase 3: Scaffold\n\nAsk: \"Generate the scaffold file?\"\n\nIf yes, produce the template below based on the detected type.\n\n---\n\n### Agent scaffold\n\n```markdown\n---\nname: [kebab-case-name]\ndescription: \"[What this agent does in one sentence. When to invoke it. Example triggers for other agents.]\"\nmodel: sonnet\ntools: Read, Grep, Glob[, Write, Bash (add only if this agent must modify files or run commands)]\n---\n\n# [Agent Name]\n\n[One paragraph: what this agent is for, what it is NOT for, and when to prefer another agent.]\n\n## Context\n\n[Stack, conventions, or domain knowledge this agent needs to be effective.]\n\n## When to invoke\n\n- [Concrete trigger 1]\n- [Concrete trigger 2]\n- [Concrete trigger 3]\n\n## Protocol\n\n### Step 1: Read context\n\n```bash\n# What to read before reasoning\ncat CLAUDE.md 2>\u002Fdev\u002Fnull\n```\n\n### Step 2: Analyze\n\n[What to look for. Patterns to detect. Red flags to surface.]\n\n### Step 3: Output\n\n[Exact output format: use a markdown code block to show the structure.]\n\n## Red flags\n\n| Pattern | Risk |\n|---------|------|\n| [pattern] | [impact] |\n\n## What this agent does NOT do\n\n- [Scope boundary 1]\n- [Scope boundary 2: point to another agent if relevant]\n```\n\n**File**: `.claude\u002Fagents\u002F[name].md`\n\n---\n\n### Command scaffold\n\n```markdown\n---\nname: [name]\ndescription: \"[What this command does in one sentence]\"\nargument-hint: \"[arg] [--flag]\"\n---\n\n# [Command Name]\n\n[Brief description. What problem it solves. When to use it vs alternatives.]\n\n## Arguments\n\n- `[arg]`: [description] (default: [value])\n- `--flag`: [description]\n\n## Usage\n\n```bash\n\u002F[name]              # Basic usage\n\u002F[name] --flag       # With flag\n```\n\n---\n\n## Phase 1: [First phase name]\n\n[What Claude does in this phase.]\n\n```bash\n# Example commands if applicable\n```\n\n## Phase 2: [Second phase name]\n\n[What Claude does.]\n\n## Phase 3: Output\n\n[Output format. Use a markdown block to show the structure.]\n\n$ARGUMENTS\n```\n\n**File**: `.claude\u002Fcommands\u002F[name].md`\n\n---\n\n### Skill scaffold\n\n```markdown\n---\nname: [skill-name]\ndescription: \"[What this skill does. Trigger phrases that activate it. Usage: \u002F[name] [arg]]\"\n---\n\n# [Skill Name]\n\n[What this skill does and when it applies. Distinguish from similar skills.]\n\n## Trigger phrases\n\n- \"[phrase that activates this skill]\"\n- \"[alternative phrasing]\"\n\n## When to use\n\n- [Scenario 1]\n- [Scenario 2]\n\n## Workflow\n\n### 1. [First action]: [brief description]\n\n[Details]\n\n### 2. [Second action]: [brief description]\n\n[Details]\n\n### 3. Deliver output\n\n[Output format]\n\n## Conventions to follow\n\n[Project-specific rules, naming conventions, or patterns this skill must respect.]\n\n## Common pitfalls\n\n- [Mistake 1 and how to avoid it]\n- [Mistake 2 and how to avoid it]\n\n$ARGUMENTS\n```\n\n**File**: `.claude\u002Fskills\u002F[name].md`\n\n---\n\n### Hook scaffold\n\n```bash\n#!\u002Fusr\u002Fbin\u002Fenv bash\n# =============================================================================\n# [name].sh: [PreToolUse | PostToolUse | UserPromptSubmit | Stop] Hook\n# =============================================================================\n# [What this hook does in one line]\n# Fires on: [event] matching [tool or pattern]\n#\n# Exit 0 = allow \u002F continue\n# Exit 2 = block with message (PreToolUse only)\n#\n# stdin: JSON payload from Claude Code\n# =============================================================================\n\nset -euo pipefail\n\nINPUT=$(cat)\nTOOL_NAME=$(echo \"$INPUT\" | jq -r '.tool_name \u002F\u002F empty')\n\n# --- Main logic ---\n\n# [Your validation logic here]\n# Example: block writes to protected paths\n# FILE=$(echo \"$INPUT\" | jq -r '.tool_input.file_path \u002F\u002F empty')\n# if [[ \"$FILE\" == *\"\u002Fsecrets\u002F\"* ]]; then\n#   echo \"Blocked: writes to \u002Fsecrets\u002F are not allowed\" >&2\n#   exit 2\n# fi\n\nexit 0\n```\n\n**File**: `.claude\u002Fhooks\u002F[name].sh`\n\nAlso add to `.claude\u002Fsettings.json`:\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Write\",\n        \"hooks\": [{ \"type\": \"command\", \"command\": \".claude\u002Fhooks\u002F[name].sh\" }]\n      }\n    ]\n  }\n}\n```\n\n---\n\n### Rule scaffold\n\n```markdown\n# [Rule Title] (Auto-loaded)\n\n## Directive\n\n[The rule in one imperative sentence.]\n\n## When it applies\n\n[Triggers, file types, or situations where this rule activates.]\n\n## Required behavior\n\n[What Claude must do concretely, be specific.]\n\n## Anti-patterns\n\nDo NOT:\n- [Forbidden example]\n\nDo:\n- [Correct behavior]\n\n---\n\n**Auto-loaded**: This file is loaded automatically at session start.\n```\n\n**File**: `.claude\u002Frules\u002F[name].md`\n\nReference in `CLAUDE.md` if not in an auto-loaded directory.\n\n---\n\n## Quick reference\n\nIf the user is unsure, show this table:\n\n| Type | Trigger | Expertise needed | Complexity | Typical example |\n|------|---------|-----------------|------------|-----------------|\n| **Agent** | Manual or automatic | High, domain-specific | Multi-step analysis | `migration-reviewer`, `dbt-specialist` |\n| **Command** | Manual `\u002Fname` | Low to medium | Simple, a few steps | `\u002Fcommit`, `\u002Fpr`, `\u002Frelease` |\n| **Skill** | Manual `\u002Fname` | Medium to high | Rich workflow, lots of context | `tdd-workflow`, `api-review` |\n| **Hook** | Automatic on event | None (bash logic) | Script | `security-gate.sh`, `format-on-save.sh` |\n| **Rule** | Permanent, every session | None (prose) | Instructions | `no-direct-push.md`, `english-only.md` |\n\n---\n\n## Sources\n\n- Component types overview: [Section 3](..\u002F..\u002F..\u002Fguide\u002Fultimate-guide.md)\n- Agent examples: [agents\u002F](..\u002F..\u002Fagents\u002F)\n- Hook examples: [hooks\u002F](..\u002F..\u002Fhooks\u002F)\n- Skill examples: [skills\u002F](..\u002F..\u002Fskills\u002F)\n","# Claude Code scaffold coach\n\nInteractive wizard that identifies the right Claude Code component for your use case and generates a ready-to-use template.\n\n**Usage**: `\u002Fscaffold` (no arguments needed). Start the conversation.\n\n---\n\n## Phase 1: Discovery\n\nOpen with this prompt, then wait for the user's answer before asking anything else:\n\n> What do you want to automate or build? One sentence is enough to start.\n\nOnce you have a rough idea, ask the following questions in order. Skip a question if a previous answer already answers it.\n\n### Q1: Trigger\n\n> How is this triggered?\n>\n> a) I run it myself with a command (e.g. `\u002Fsomething`)\n> b) It should fire automatically when Claude takes an action (writes a file, runs bash, finishes a session...)\n> c) It should apply all the time, every session, without me doing anything\n\n- If **b** → likely a **Hook** (jump to Q_hook)\n- If **c** → likely a **Rule** (jump to Q_rule)\n- If **a** → continue with Q2\n\n### Q2: Domain expertise\n\n> Does this require deep, project-specific expertise?\n> For example: knowing your GraphQL schema, your migration conventions, your internal API patterns, your cost model...\n\n- If **yes, deep expertise** → likely an **Agent** (jump to Q_agent)\n- If **no, more of a checklist or procedure** → continue with Q3\n\n### Q3: Complexity\n\n> How much context and logic does this involve?\n>\n> a) A lot: multiple rules, domain-specific examples, nuanced judgment\n> b) Straightforward: a few steps, a template, some bash\n\n- If **a** → likely a **Skill**\n- If **b** → likely a **Command**\n\n### Q4: Reuse scope\n\n> Who needs this?\n>\n> a) Just me\n> b) My whole team\n> c) It needs to be invokable by other agents automatically\n\n- **c** → strengthens **Agent** (needs a `description:` field that other agents can read)\n- **b** → strengthens **Command** or **Skill** (shared config)\n- **a** → can stay a simple personal **Command**\n\n### Q5: Output type\n\n> What should happen at the end?\n>\n> a) A report or analysis: Claude reads and explains, no files touched\n> b) Code or files generated\n> c) An action taken (commit, push, API call...)\n> d) Claude's behavior changes permanently (always does X, never does Y)\n\n- **a** → read-only Agent (no `Write` or `Bash` in tools)\n- **b\u002Fc** → Agent or Command\u002FSkill with write access\n- **d** → Rule, or Hook if conditional on a specific event\n\n---\n\n## Internal decision tree (do not display, use to reason)\n\n```\nTriggered automatically?\n  ├─ On Claude action (Write, Bash, SessionEnd...) -> Hook\n  └─ Always active, no trigger -> Rule\n\nTriggered manually?\n  ├─ Deep domain expertise required?\n  │   ├─ Yes + invokable by other agents -> Agent\n  │   └─ Yes + manual use only -> Agent or Skill\n  └─ Procedure \u002F checklist, no special expertise?\n      ├─ Complex, lots of project-specific context -> Skill\n      └─ Simple, a few steps -> Command\n\nCommon hybrid cases:\n  - Agent + Command: specialist agent + a shortcut command to invoke it\n  - Rule + Hook: permanent behavior + blocking on a specific action\n  - Skill + Agent: skill that delegates analysis to an agent\n```\n\n---\n\n## Phase 2: Recommendation\n\nAfter the questions, display this structure:\n\n```\n## Diagnosis\n\nYou want to: [one-line summary of the use case]\n\n## Recommendation: [TYPE]\n\n**Why?**\n[2-3 sentences: trigger type, complexity level, reuse scope]\n\n**What it would NOT be, and why:**\n- Not an agent because [short reason]\n- Not a rule because [short reason]\n[adjust based on actual candidates]\n\n**Hybrid case?** [Yes \u002F No]\n[If yes: explain the combination and which file to create first]\n```\n\n---\n\n## Phase 3: Scaffold\n\nAsk: \"Generate the scaffold file?\"\n\nIf yes, produce the template below based on the detected type.\n\n---\n\n### Agent scaffold\n\n```markdown\n---\nname: [kebab-case-name]\ndescription: \"[What this agent does in one sentence. When to invoke it. Example triggers for other agents.]\"\nmodel: sonnet\ntools: Read, Grep, Glob[, Write, Bash (add only if this agent must modify files or run commands)]\n---\n\n# [Agent Name]\n\n[One paragraph: what this agent is for, what it is NOT for, and when to prefer another agent.]\n\n## Context\n\n[Stack, conventions, or domain knowledge this agent needs to be effective.]\n\n## When to invoke\n\n- [Concrete trigger 1]\n- [Concrete trigger 2]\n- [Concrete trigger 3]\n\n## Protocol\n\n### Step 1: Read context\n\n```bash\n# What to read before reasoning\ncat CLAUDE.md 2>\u002Fdev\u002Fnull\n```\n\n### Step 2: Analyze\n\n[What to look for. Patterns to detect. Red flags to surface.]\n\n### Step 3: Output\n\n[Exact output format: use a markdown code block to show the structure.]\n\n## Red flags\n\n| Pattern | Risk |\n|---------|------|\n| [pattern] | [impact] |\n\n## What this agent does NOT do\n\n- [Scope boundary 1]\n- [Scope boundary 2: point to another agent if relevant]\n```\n\n**File**: `.claude\u002Fagents\u002F[name].md`\n\n---\n\n### Command scaffold\n\n```markdown\n---\nname: [name]\ndescription: \"[What this command does in one sentence]\"\nargument-hint: \"[arg] [--flag]\"\n---\n\n# [Command Name]\n\n[Brief description. What problem it solves. When to use it vs alternatives.]\n\n## Arguments\n\n- `[arg]`: [description] (default: [value])\n- `--flag`: [description]\n\n## Usage\n\n```bash\n\u002F[name]              # Basic usage\n\u002F[name] --flag       # With flag\n```\n\n---\n\n## Phase 1: [First phase name]\n\n[What Claude does in this phase.]\n\n```bash\n# Example commands if applicable\n```\n\n## Phase 2: [Second phase name]\n\n[What Claude does.]\n\n## Phase 3: Output\n\n[Output format. Use a markdown block to show the structure.]\n\n$ARGUMENTS\n```\n\n**File**: `.claude\u002Fcommands\u002F[name].md`\n\n---\n\n### Skill scaffold\n\n```markdown\n---\nname: [skill-name]\ndescription: \"[What this skill does. Trigger phrases that activate it. Usage: \u002F[name] [arg]]\"\n---\n\n# [Skill Name]\n\n[What this skill does and when it applies. Distinguish from similar skills.]\n\n## Trigger phrases\n\n- \"[phrase that activates this skill]\"\n- \"[alternative phrasing]\"\n\n## When to use\n\n- [Scenario 1]\n- [Scenario 2]\n\n## Workflow\n\n### 1. [First action]: [brief description]\n\n[Details]\n\n### 2. [Second action]: [brief description]\n\n[Details]\n\n### 3. Deliver output\n\n[Output format]\n\n## Conventions to follow\n\n[Project-specific rules, naming conventions, or patterns this skill must respect.]\n\n## Common pitfalls\n\n- [Mistake 1 and how to avoid it]\n- [Mistake 2 and how to avoid it]\n\n$ARGUMENTS\n```\n\n**File**: `.claude\u002Fskills\u002F[name].md`\n\n---\n\n### Hook scaffold\n\n```bash\n#!\u002Fusr\u002Fbin\u002Fenv bash\n# =============================================================================\n# [name].sh: [PreToolUse | PostToolUse | UserPromptSubmit | Stop] Hook\n# =============================================================================\n# [What this hook does in one line]\n# Fires on: [event] matching [tool or pattern]\n#\n# Exit 0 = allow \u002F continue\n# Exit 2 = block with message (PreToolUse only)\n#\n# stdin: JSON payload from Claude Code\n# =============================================================================\n\nset -euo pipefail\n\nINPUT=$(cat)\nTOOL_NAME=$(echo \"$INPUT\" | jq -r '.tool_name \u002F\u002F empty')\n\n# --- Main logic ---\n\n# [Your validation logic here]\n# Example: block writes to protected paths\n# FILE=$(echo \"$INPUT\" | jq -r '.tool_input.file_path \u002F\u002F empty')\n# if [[ \"$FILE\" == *\"\u002Fsecrets\u002F\"* ]]; then\n#   echo \"Blocked: writes to \u002Fsecrets\u002F are not allowed\" >&2\n#   exit 2\n# fi\n\nexit 0\n```\n\n**File**: `.claude\u002Fhooks\u002F[name].sh`\n\nAlso add to `.claude\u002Fsettings.json`:\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Write\",\n        \"hooks\": [{ \"type\": \"command\", \"command\": \".claude\u002Fhooks\u002F[name].sh\" }]\n      }\n    ]\n  }\n}\n```\n\n---\n\n### Rule scaffold\n\n```markdown\n# [Rule Title] (Auto-loaded)\n\n## Directive\n\n[The rule in one imperative sentence.]\n\n## When it applies\n\n[Triggers, file types, or situations where this rule activates.]\n\n## Required behavior\n\n[What Claude must do concretely, be specific.]\n\n## Anti-patterns\n\nDo NOT:\n- [Forbidden example]\n\nDo:\n- [Correct behavior]\n\n---\n\n**Auto-loaded**: This file is loaded automatically at session start.\n```\n\n**File**: `.claude\u002Frules\u002F[name].md`\n\nReference in `CLAUDE.md` if not in an auto-loaded directory.\n\n---\n\n## Quick reference\n\nIf the user is unsure, show this table:\n\n| Type | Trigger | Expertise needed | Complexity | Typical example |\n|------|---------|-----------------|------------|-----------------|\n| **Agent** | Manual or automatic | High, domain-specific | Multi-step analysis | `migration-reviewer`, `dbt-specialist` |\n| **Command** | Manual `\u002Fname` | Low to medium | Simple, a few steps | `\u002Fcommit`, `\u002Fpr`, `\u002Frelease` |\n| **Skill** | Manual `\u002Fname` | Medium to high | Rich workflow, lots of context | `tdd-workflow`, `api-review` |\n| **Hook** | Automatic on event | None (bash logic) | Script | `security-gate.sh`, `format-on-save.sh` |\n| **Rule** | Permanent, every session | None (prose) | Instructions | `no-direct-push.md`, `english-only.md` |\n\n---\n\n## Sources\n\n- Component types overview: [Section 3](..\u002F..\u002F..\u002Fguide\u002Fultimate-guide.md)\n- Agent examples: [agents\u002F](..\u002F..\u002Fagents\u002F)\n- Hook examples: [hooks\u002F](..\u002F..\u002Fhooks\u002F)\n- Skill examples: [skills\u002F](..\u002F..\u002Fskills\u002F)\n",{"name":5,"effort":24,"description":7,"disable-model-invocation":25},"medium",true,"main","f2cc95bc769ca4c3a398965b767dfb41cdf8d698","reference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fscaffold",2,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","https:\u002F\u002Fgithub.com\u002F313DEVGRP","https:\u002F\u002Fwww.a-rms.net","2026-10-18 12:48:10",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":25},[36,39,42],{"tool":37,"command":38},"npx","npx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill scaffold",{"tool":40,"command":41},"bunx","bunx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill scaffold",{"tool":43,"command":44},"pnpm","pnpm dlx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill scaffold","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fscaffold\u002FSKILL.md",[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7F343WNVHZWWYJDD77QEJ7J","voice-refine","Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvoice-refine\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7F3417SNXASFTDA1B2X4XYZ","validate-changes","Evaluate staged changes using LLM-as-a-Judge before committing","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvalidate-changes\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7F33YN9QK88H2B81PVHMNG1","update-threat-db","Delegate threat-intelligence research and updates to AgentSec, then validate the guide and landing mirrors.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fupdate-threat-db\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7F33SXQ57G2FVFK094T4584","token-audit","Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when hitting rate limits, experiencing early context compression, or after adding significant config files.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftoken-audit\u002Fskill.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7F33NAWXFPHW59CF52EAGGK","talk-stage6-revision","Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-6-revision\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7F33G9V96HVZKAGZ84J4EBR","talk-stage5-script","Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-5-script\u002FSKILL.md",[],[]]