AGENT SKILL

enhance-cross-file

Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.

License 许可
MIT
所属仓库
agisota/old-one
最近更新
2026-07-04
Stars
★ 3
Forks
1

01 前言 Front Matter

name
enhance-cross-file
version
5.1.0
description
Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.
argument-hint
[path]

03 SKILL.md 正文

enhance-cross-file

Analyze cross-file semantic consistency across agents, skills, and workflows.

Parse Arguments

const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const targetPath = args.find(a => !a.startsWith('--')) || '.';

Purpose

Detects issues that span multiple files - things single-file analysis misses:

  • Tools used in prompt body but not declared in frontmatter
  • Agent references that don't exist
  • Duplicate instructions across files (maintenance burden)
  • Contradictory rules (ALWAYS vs NEVER conflicts)
  • Orphaned agents not referenced by any workflow
  • Skill tool mismatches (allowed-tools vs actual usage)

Workflow

  1. Run Analyzer - Execute the JavaScript analyzer to get findings:

    node -e "const a = require('./lib/enhance/cross-file-analyzer.js'); console.log(JSON.stringify(a.analyze('.'), null, 2));"
    

    For a specific path: a.analyze('./plugins/enhance')

  2. Parse Results - The analyzer returns JSON with summary and findings

  3. Report - Return findings grouped by category

The JavaScript analyzer (lib/enhance/cross-file-analyzer.js) implements all cross-file detection. The patterns below are reference documentation.

Detection Patterns

1. Tool Consistency (MEDIUM Certainty)

tool_not_in_allowed_list: Tool used in prompt body but not in frontmatter tools: list

# Frontmatter declares:
tools: Read, Grep

# But body uses:
Use Write({ file_path: "/out" })  # <- Not declared!

skill_tool_mismatch: Skill's allowed-tools doesn't match actual tool usage in skill body

2. Workflow Consistency (MEDIUM Certainty)

missing_workflow_agent: subagent_type: "plugin:agent-name" references non-existent agent

orphaned_prompt: Agent file exists but no workflow references it (may be entry point - check manually)

incomplete_phase_transition: Workflow phase mentions "Phase N" but no corresponding section

3. Instruction Consistency (MEDIUM Certainty)

duplicate_instructions: Same MUST/NEVER instruction in 3+ files (extract to shared location)

contradictory_rules: One file says "ALWAYS X" while another says "NEVER X"

Output Format

## Cross-File Analysis

**Files Analyzed**: {agents} agents, {skills} skills, {commands} commands

### Tool Consistency ({n})
| Agent | Issue | Fix |
|-------|-------|-----|
| exploration-agent | Uses Write but not in tools list | Add Write to frontmatter |

### Workflow Issues ({n})
| Source | Issue | Fix |
|--------|-------|-----|
| workflow.md | References nonexistent agent | Check spelling or create agent |

### Instruction Consistency ({n})
| Instruction | Files | Fix |
|-------------|-------|-----|
| "NEVER push --force" | 4 files | Extract to CLAUDE.md |

Constraints

  • All patterns are MEDIUM certainty (require context)
  • No auto-fix (cross-file changes need human review)
  • Skip content inside <bad-example>, <bad_example>, <badexample> tags
  • Skip content inside code blocks with "bad" in info string
  • Entry point agents (orchestrator, validator, discoverer) are not orphaned

Pattern Statistics

Category Patterns Auto-Fixable
Tool Consistency 2 0
Workflow 3 0
Consistency 3 0
Total 8 0

04 同仓库更多 Skills

agisota
agisota/old-one

zoom-out

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

★ 3
agisota
agisota/old-one

zeroize-audit

Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or other sensitive data.

★ 3
agisota
agisota/old-one

yeet

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

★ 3
agisota
agisota/old-one

yara-rule-authoring

Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection, threat hunting, IOC, signature, crx module, dex module.

★ 3
agisota
agisota/old-one

x-twitter-growth

X/Twitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X/Twitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.

★ 3
agisota
agisota/old-one

x-api

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.

★ 3