skill-tuning

@catlog22/skill-tuning

catlog22

1,008

86 forks

Updated 1/18/2026

View on GitHub

Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including context explosion, long-tail forgetting, data flow disruption, and agent coordination failures. Supports Gemini CLI for deep analysis. Triggers on "skill tuning", "tune skill", "skill diagnosis", "optimize skill", "skill debug".

Installation

$skills install @catlog22/skill-tuning

Claude Code

Cursor

Copilot

Codex

Antigravity

Details

Repositorycatlog22/Claude-Code-Workflow

Path.claude/skills/skill-tuning/SKILL.md

Branchmain

Scoped Name@catlog22/skill-tuning

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

skills list

Skill Instructions

name: skill-tuning description: Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including context explosion, long-tail forgetting, data flow disruption, and agent coordination failures. Supports Gemini CLI for deep analysis. Triggers on "skill tuning", "tune skill", "skill diagnosis", "optimize skill", "skill debug". allowed-tools: Task, AskUserQuestion, Read, Write, Bash, Glob, Grep, mcpace-toolsearch_context

Skill Tuning

Universal skill diagnosis and optimization tool that identifies and resolves skill execution problems through iterative multi-agent analysis.

Architecture Overview

┌─────────────────────────────────────────────────────────────────────────────┐
│  Skill Tuning Architecture (Autonomous Mode + Gemini CLI)                    │
├─────────────────────────────────────────────────────────────────────────────┤
│                                                                              │
│  ⚠️ Phase 0: Specification  → 阅读规范 + 理解目标 skill 结构 (强制前置)       │
│              Study                                                           │
│           ↓                                                                  │
│  ┌───────────────────────────────────────────────────────────────────────┐  │
│  │                    Orchestrator (状态驱动决策)                          │  │
│  │  读取诊断状态 → 选择下一步动作 → 执行 → 更新状态 → 循环直到完成         │  │
│  └───────────────────────────────────────────────────────────────────────┘  │
│                              │                                               │
│     ┌────────────┬───────────┼───────────┬────────────┬────────────┐        │
│     ↓            ↓           ↓           ↓            ↓            ↓        │
│  ┌──────┐  ┌──────────┐  ┌─────────┐  ┌────────┐  ┌────────┐  ┌─────────┐  │
│  │ Init │→ │ Analyze  │→ │Diagnose │  │Diagnose│  │Diagnose│  │ Gemini  │  │
│  │      │  │Requiremts│  │ Context │  │ Memory │  │DataFlow│  │Analysis │  │
│  └──────┘  └──────────┘  └─────────┘  └────────┘  └────────┘  └─────────┘  │
│                 │              │           │           │            │        │
│                 │              └───────────┴───────────┴────────────┘        │
│                 ↓                                                            │
│  ┌───────────────────────────────────────────────────────────────────────┐  │
│  │  Requirement Analysis (NEW)                                            │  │
│  │  • Phase 1: 维度拆解 (Gemini CLI) - 单一描述 → 多个关注维度             │  │
│  │  • Phase 2: Spec 匹配 - 每个维度 → taxonomy + strategy                 │  │
│  │  • Phase 3: 覆盖度评估 - 以"有修复策略"为满足标准                       │  │
│  │  • Phase 4: 歧义检测 - 识别多义性描述，必要时请求澄清                   │  │
│  └───────────────────────────────────────────────────────────────────────┘  │
│                              ↓                                               │
│                    ┌──────────────────┐                                      │
│                    │  Apply Fixes +   │                                      │
│                    │  Verify Results  │                                      │
│                    └──────────────────┘                                      │
│                                                                              │
│  ┌───────────────────────────────────────────────────────────────────────┐  │
│  │                    Gemini CLI Integration                              │  │
│  │  根据用户需求动态调用 gemini cli 进行深度分析:                          │  │
│  │  • 需求维度拆解 (requirement decomposition)                             │  │
│  │  • 复杂问题分析 (prompt engineering, architecture review)               │  │
│  │  • 代码模式识别 (pattern matching, anti-pattern detection)              │  │
│  │  • 修复策略生成 (fix generation, refactoring suggestions)               │  │
│  └───────────────────────────────────────────────────────────────────────┘  │
│                                                                              │
└─────────────────────────────────────────────────────────────────────────────┘

Problem Domain

Based on comprehensive analysis, skill-tuning addresses core skill issues and general optimization areas:

Core Skill Issues (自动检测)

Priority	Problem	Root Cause	Solution Strategy
P0	Authoring Principles Violation	中间文件存储, State膨胀, 文件中转	eliminate_intermediate_files, minimize_state, context_passing
P1	Data Flow Disruption	Scattered state, inconsistent formats	state_centralization, schema_enforcement
P2	Agent Coordination	Fragile call chains, merge complexity	error_wrapping, result_validation
P3	Context Explosion	Token accumulation, multi-turn bloat	sliding_window, context_summarization
P4	Long-tail Forgetting	Early constraint loss	constraint_injection, checkpoint_restore
P5	Token Consumption	Verbose prompts, excessive state, redundant I/O	prompt_compression, lazy_loading, output_minimization

General Optimization Areas (按需分析 via Gemini CLI)

Category	Issues	Gemini Analysis Scope
Prompt Engineering	模糊指令, 输出格式不一致, 幻觉风险	提示词优化, 结构化输出设计
Architecture	阶段划分不合理, 依赖混乱, 扩展性差	架构审查, 模块化建议
Performance	执行慢, Token消耗高, 重复计算	性能分析, 缓存策略
Error Handling	错误恢复不当, 无降级策略, 日志不足	容错设计, 可观测性增强
Output Quality	输出不稳定, 格式漂移, 质量波动	质量门控, 验证机制
User Experience	交互不流畅, 反馈不清晰, 进度不可见	UX优化, 进度追踪

Key Design Principles

Problem-First Diagnosis: Systematic identification before any fix attempt
Data-Driven Analysis: Record execution traces, token counts, state snapshots
Iterative Refinement: Multiple tuning rounds until quality gates pass
Non-Destructive: All changes are reversible with backup checkpoints
Agent Coordination: Use specialized sub-agents for each diagnosis type
Gemini CLI On-Demand: Deep analysis via CLI for complex/custom issues

Gemini CLI Integration

根据用户需求动态调用 Gemini CLI 进行深度分析。

Trigger Conditions

Condition	Action	CLI Mode
用户描述复杂问题	调用 Gemini 分析问题根因	`analysis`
自动诊断发现 critical 问题	请求深度分析确认	`analysis`
用户请求架构审查	执行架构分析	`analysis`
需要生成修复代码	生成修复提案	`write`
标准策略不适用	请求定制化策略	`analysis`

CLI Command Template

ccw cli -p "
PURPOSE: ${purpose}
TASK: ${task_steps}
MODE: ${mode}
CONTEXT: @${skill_path}/**/*
EXPECTED: ${expected_output}
RULES: $(cat ~/.claude/workflows/cli-templates/protocols/${mode}-protocol.md) | ${constraints}
" --tool gemini --mode ${mode} --cd ${skill_path}

Analysis Types

1. Problem Root Cause Analysis

ccw cli -p "
PURPOSE: Identify root cause of skill execution issue: ${user_issue_description}
TASK: • Analyze skill structure and phase flow • Identify anti-patterns • Trace data flow issues
MODE: analysis
CONTEXT: @**/*.md
EXPECTED: JSON with { root_causes: [], patterns_found: [], recommendations: [] }
RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) | Focus on execution flow
" --tool gemini --mode analysis

2. Architecture Review

ccw cli -p "
PURPOSE: Review skill architecture for scalability and maintainability
TASK: • Evaluate phase decomposition • Check state management patterns • Assess agent coordination
MODE: analysis
CONTEXT: @**/*.md
EXPECTED: Architecture assessment with improvement recommendations
RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) | Focus on modularity
" --tool gemini --mode analysis

3. Fix Strategy Generation

ccw cli -p "
PURPOSE: Generate fix strategy for issue: ${issue_id} - ${issue_description}
TASK: • Analyze issue context • Design fix approach • Generate implementation plan
MODE: analysis
CONTEXT: @**/*.md
EXPECTED: JSON with { strategy: string, changes: [], verification_steps: [] }
RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md) | Minimal invasive changes
" --tool gemini --mode analysis

Mandatory Prerequisites

CRITICAL: Read these documents before executing any action.

Core Specs (Required)

Document	Purpose	Priority
specs/skill-authoring-principles.md	首要准则：简洁高效、去除存储、上下文流转	P0
specs/problem-taxonomy.md	Problem classification and detection patterns	P0
specs/tuning-strategies.md	Fix strategies for each problem type	P0
specs/dimension-mapping.md	Dimension to Spec mapping rules	P0
specs/quality-gates.md	Quality thresholds and verification criteria	P1

Templates (Reference)

Document	Purpose
templates/diagnosis-report.md	Diagnosis report structure
templates/fix-proposal.md	Fix proposal format

Execution Flow

┌─────────────────────────────────────────────────────────────────────────────┐
│  Phase 0: Specification Study (强制前置 - 禁止跳过)                           │
│  → Read: specs/problem-taxonomy.md (问题分类)                                │
│  → Read: specs/tuning-strategies.md (调优策略)                               │
│  → Read: specs/dimension-mapping.md (维度映射规则)                           │
│  → Read: Target skill's SKILL.md and phases/*.md                            │
│  → Output: 内化规范，理解目标 skill 结构                                      │
├─────────────────────────────────────────────────────────────────────────────┤
│  action-init: Initialize Tuning Session                                      │
│  → Create work directory: .workflow/.scratchpad/skill-tuning-{timestamp}    │
│  → Initialize state.json with target skill info                             │
│  → Create backup of target skill files                                       │
├─────────────────────────────────────────────────────────────────────────────┤
│  action-analyze-requirements: Requirement Analysis                           │
│  → Phase 1: 维度拆解 (Gemini CLI) - 单一描述 → 多个关注维度                   │
│  → Phase 2: Spec 匹配 - 每个维度 → taxonomy + strategy                       │
│  → Phase 3: 覆盖度评估 - 以"有修复策略"为满足标准                             │
│  → Phase 4: 歧义检测 - 识别多义性描述，必要时请求澄清                         │
│  → Output: state.json (requirement_analysis field)                           │
├─────────────────────────────────────────────────────────────────────────────┤
│  action-diagnose-*: Diagnosis Actions (context/memory/dataflow/agent/docs/   │
│                      token_consumption)                                      │
│  → Execute pattern-based detection for each category                         │
│  → Output: state.json (diagnosis.{category} field)                           │
├─────────────────────────────────────────────────────────────────────────────┤
│  action-generate-report: Consolidated Report                                 │
│  → Generate markdown summary from state.diagnosis                            │
│  → Prioritize issues by severity                                             │
│  → Output: state.json (final_report field)                                   │
├─────────────────────────────────────────────────────────────────────────────┤
│  action-propose-fixes: Fix Proposal Generation                               │
│  → Generate fix strategies for each issue                                    │
│  → Create implementation plan                                                │
│  → Output: state.json (proposed_fixes field)                                 │
├─────────────────────────────────────────────────────────────────────────────┤
│  action-apply-fix: Apply Selected Fix                                        │
│  → User selects fix to apply                                                 │
│  → Execute fix with backup                                                   │
│  → Update state with fix result                                              │
├─────────────────────────────────────────────────────────────────────────────┤
│  action-verify: Verification                                                 │
│  → Re-run affected diagnosis                                                 │
│  → Check quality gates                                                       │
│  → Update iteration count                                                    │
├─────────────────────────────────────────────────────────────────────────────┤
│  action-complete: Finalization                                               │
│  → Set status='completed'                                                    │
│  → Final report already in state.json (final_report field)                   │
│  → Output: state.json (final)                                                │
└─────────────────────────────────────────────────────────────────────────────┘

Directory Setup

const timestamp = new Date().toISOString().slice(0,19).replace(/[-:T]/g, '');
const workDir = `.workflow/.scratchpad/skill-tuning-${timestamp}`;

// Simplified: Only backups dir needed, diagnosis results go into state.json
Bash(`mkdir -p "${workDir}/backups"`);

Output Structure

.workflow/.scratchpad/skill-tuning-{timestamp}/
├── state.json                      # Single source of truth (all results consolidated)
│   ├── diagnosis.*                 # All diagnosis results embedded
│   ├── issues[]                    # Found issues
│   ├── proposed_fixes[]            # Fix proposals
│   └── final_report                # Markdown summary (on completion)
└── backups/
    └── {skill-name}-backup/        # Original skill files backup

Token Optimization: All outputs consolidated into state.json. No separate diagnosis files or report files.

State Schema

详细状态结构定义请参阅 phases/state-schema.md。

核心状态字段：

status: 工作流状态 (pending/running/completed/failed)
target_skill: 目标 skill 信息
diagnosis: 各维度诊断结果
issues: 发现的问题列表
proposed_fixes: 建议的修复方案

Reference Documents

Document	Purpose
phases/orchestrator.md	Orchestrator decision logic
phases/state-schema.md	State structure definition
phases/actions/action-init.md	Initialize tuning session
phases/actions/action-analyze-requirements.md	Requirement analysis (NEW)
phases/actions/action-diagnose-context.md	Context explosion diagnosis
phases/actions/action-diagnose-memory.md	Long-tail forgetting diagnosis
phases/actions/action-diagnose-dataflow.md	Data flow diagnosis
phases/actions/action-diagnose-agent.md	Agent coordination diagnosis
phases/actions/action-diagnose-docs.md	Documentation structure diagnosis
phases/actions/action-diagnose-token-consumption.md	Token consumption diagnosis
phases/actions/action-generate-report.md	Report generation
phases/actions/action-propose-fixes.md	Fix proposal
phases/actions/action-apply-fix.md	Fix application
phases/actions/action-verify.md	Verification
phases/actions/action-complete.md	Finalization
specs/problem-taxonomy.md	Problem classification
specs/tuning-strategies.md	Fix strategies
specs/dimension-mapping.md	Dimension to Spec mapping (NEW)
specs/quality-gates.md	Quality criteria

More by catlog22

View all

Prompt Enhancer

1,008

Transform vague prompts into actionable specs using intelligent analysis and session memory. Use when user input contains -e or --enhance flag.

ccw

1,008

Stateless workflow orchestrator. Auto-selects optimal workflow based on task intent. Triggers "ccw", "workflow".

1,008

Generate software copyright design specification documents compliant with China Copyright Protection Center (CPCC) standards. Creates complete design documents with Mermaid diagrams based on source code analysis. Use for software copyright registration, generating design specification, creating CPCC-compliant documents, or documenting software for intellectual property protection. Triggers on "软件著作权", "设计说明书", "版权登记", "CPCC", "软著申请".

issue-manage

1,008

Interactive issue management with menu-driven CRUD operations. Use when managing issues, viewing issue status, editing issue fields, performing bulk operations, or viewing issue history. Triggers on "manage issue", "list issues", "edit issue", "delete issue", "bulk update", "issue dashboard", "issue history", "completed issues".