skill-tuning

Name: skill-tuning
Author: catlog22

Data Community

Repo stars 2,029
Author updated Live
Author repo Claude-Code-Workflow

Fluxly profile Facts only: domain, agents, trust score, runtime, permissions and network

Domain: Data
Compatible agents: Claude Code
Cursor
Cline
Codex
Windsurf
Gemini CLI

+20
Trust score: 88 / 100 · community maintained
Author / version / license: @catlog22 · no license declared
Token usage: Lean
Setup complexity: Guided setup
External API key: Not required
Operating systems: Unspecified (assume cross-platform)
Runtime requirements: No special requirements
Permissions: Read-only
Write / modify
Shell exec
Network behavior: Local-only
Install commands: 26 variants

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-tuning.preview

---
name: skill-tuning
description: Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including…
category: data
runtime: no special runtime
---

# skill-tuning output preview

## PART A: Task fit
- Use case: 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"..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Architecture / Core Issues Detected / Problem Categories (Detailed Specs)” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “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".”.
- **02** When the source has headings, the agent prioritizes “Architecture / Core Issues Detected / Problem Categories (Detailed Specs)” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.

## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.

SKILL.md SKILL.md

---
name: skill-tuning
description: Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including…
category: data
source: catlog22/Claude-Code-Workflow
---

# skill-tuning

## When to use
- Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including context explosion, lo…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.

## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.

## Execution rules
- Organize steps around “Architecture / Core Issues Detected / Problem Categories (Detailed Specs)” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.

## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.

Evidence boundary and execution chain

The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.

skill "skill-tuning" {
  input      -> user goal + target files + boundaries + acceptance criteria
  context    -> Architecture / Core Issues Detected / Problem Categories (Detailed Specs)
  rules      -> SKILL.md triggers / order / output contract
  runtime    -> no special runtime | read files, write/modify files, run shell commands | mostly runs locally
  guardrails -> usually needs no extra API key + small-sample validation + diff/log review
  output     -> copyable result + checklist + next iteration
}

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

Decide Fit First

Core job: Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including context explosion, long-tail fo…
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 “Architecture”, “Core Issues Detected”, “Problem Categories (Detailed Specs)”, “Tuning Strategies (Detailed Specs)”, 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-tuning 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 “Architecture / Core Issues Detected / Problem Categories (Detailed Specs)” 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 / shell-exec; 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.

Skill Tuning

Autonomous diagnosis and optimization for skill execution issues.

Architecture

┌─────────────────────────────────────────────────────┐
│  Phase 0: Read Specs (mandatory)                    │
│  → problem-taxonomy.md, tuning-strategies.md         │
└─────────────────────────────────────────────────────┘
                        ↓
┌─────────────────────────────────────────────────────┐
│  Orchestrator (state-driven)                         │
│  Read state → Select action → Execute → Update → ✓ │
└─────────────────────────────────────────────────────┘
        ↓                           ↓
┌──────────────────────┐   ┌──────────────────┐
│  Diagnosis Phase     │   │ Gemini CLI       │
│  • Context          │   │ Deep analysis    │
│  • Memory           │   │ (on-demand)      │
│  • DataFlow         │   │                  │
│  • Agent            │   │ Complex issues   │
│  • Docs             │   │ Architecture     │
│  • Token Usage      │   │ Performance      │
└──────────────────────┘   └──────────────────┘
                ↓
        ┌───────────────────┐
        │  Fix & Verify     │
        │  Apply → Re-test  │
        └───────────────────┘

Core Issues Detected

Priority	Problem	Root Cause	Fix Strategy
P0	Authoring Violation	Intermediate files, state bloat, file relay	eliminate_intermediate, minimize_state
P1	Data Flow Disruption	Scattered state, inconsistent formats	state_centralization, schema_enforcement
P2	Agent Coordination	Fragile chains, no error handling	error_wrapping, result_validation
P3	Context Explosion	Unbounded history, full content passing	sliding_window, path_reference
P4	Long-tail Forgetting	Early constraint loss	constraint_injection, checkpoint_restore
P5	Token Consumption	Verbose prompts, state bloat	prompt_compression, lazy_loading

Problem Categories (Detailed Specs)

See specs/problem-taxonomy.md for:

Detection patterns (regex/checks)
Severity calculations
Impact assessments

Tuning Strategies (Detailed Specs)

See specs/tuning-strategies.md for:

10+ strategies per category
Implementation patterns
Verification methods

Workflow

Step	Action	Orchestrator Decision	Output
1	`action-init`	status='pending'	Backup, session created
2	`action-analyze-requirements`	After init	Required dimensions + coverage
3	Diagnosis (6 types)	Focus areas	state.diagnosis.{type}
4	`action-gemini-analysis`	Critical issues OR user request	Deep findings
5	`action-generate-report`	All diagnosis complete	state.final_report
6	`action-propose-fixes`	Issues found	state.proposed_fixes[]
7	`action-apply-fix`	Pending fixes	Applied + verified
8	`action-complete`	Quality gates pass	session.status='completed'

Action Reference

Category	Actions	Purpose
Setup	action-init	Initialize backup, session state
Analysis	action-analyze-requirements	Decompose user request via Gemini CLI
Diagnosis	action-diagnose-{context,memory,dataflow,agent,docs,token_consumption}	Detect category-specific issues
Deep Analysis	action-gemini-analysis	Gemini CLI: complex/critical issues
Reporting	action-generate-report	Consolidate findings → final_report
Fixing	action-propose-fixes, action-apply-fix	Generate + apply fixes
Verify	action-verify	Re-run diagnosis, check gates
Exit	action-complete, action-abort	Finalize or rollback

Full action details: phases/actions/

State Management

Single source of truth: .workflow/.scratchpad/skill-tuning-{ts}/state.json

{
  "status": "pending|running|completed|failed",
  "target_skill": { "name": "...", "path": "..." },
  "diagnosis": {
    "context": {...},
    "memory": {...},
    "dataflow": {...},
    "agent": {...},
    "docs": {...},
    "token_consumption": {...}
  },
  "issues": [{"id":"...", "severity":"...", "category":"...", "strategy":"..."}],
  "proposed_fixes": [...],
  "applied_fixes": [...],
  "quality_gate": "pass|fail",
  "final_report": "..."
}

See phases/state-schema.md for complete schema.

Orchestrator Logic

See phases/orchestrator.md for:

Decision logic (termination checks → action selection)
State transitions
Error recovery

Key Principles

Problem-First: Diagnosis before any fix
Data-Driven: Record traces, token counts, snapshots
Iterative: Multiple rounds until quality gates pass
Reversible: All changes with backup checkpoints
Non-Invasive: Minimal changes, maximum clarity

Usage Examples

# Basic skill diagnosis
/skill-tuning "Fix memory leaks in my skill"

# Deep analysis with Gemini
/skill-tuning "Architecture issues in async workflow"

# Focus on specific areas
/skill-tuning "Optimize token consumption and fix agent coordination"

# Custom issue
/skill-tuning "My skill produces inconsistent outputs"

Output

After completion, review:

.workflow/.scratchpad/skill-tuning-{ts}/state.json - Full state with final_report
state.final_report - Markdown summary (in state.json)
state.applied_fixes - List of applied fixes with verification results

Reference Documents

Document	Purpose
specs/problem-taxonomy.md	Classification + detection patterns
specs/tuning-strategies.md	Fix implementation guide
specs/dimension-mapping.md	Dimension ↔ Spec mapping
specs/quality-gates.md	Quality verification criteria
phases/orchestrator.md	Workflow orchestration
phases/state-schema.md	State structure definition
phases/actions/	Individual action implementations

Install command

One-click installPick a runner, click Copy, paste into your terminal, press enter

npx skills add catlog22/Claude-Code-Workflow/.claude/skills/skill-tuning -y

Open general install guide

View skill source

Works with

Claude Code
Cursor
Cline
Codex
Windsurf
Gemini
OpenCode
Roo Code
AAide
+Augment
GitHub Copilot
OpenClaw
KKiro
Junie
WWarp
Goose
Trae
Kilo Code
OpenHands
Amp
Zencoder
CContinue
AIAider
CodeBuddy
CodeGeeX
Replit Agent

Security audit

88 / 100

Community

未声明 license/许可。
未声明 version。
未限定 allowed-tools，默认拥有全部工具权限。

Metadata

Source: github
catlog22/Claude-Code-Workflow
中文

More by @catlog22

Category & tags

Category Data