← 返回 Skills 市场
leegitw

Golden Master

作者 Lee Brown · GitHub ↗ · v1.0.4 · MIT-0
cross-platform ✓ 安全检测通过
1389
总下载
4
收藏
2
当前安装
5
版本数
在 OpenClaw 中安装
/install golden-master
功能描述
Track source-of-truth relationships between files — know when derived content becomes stale.
使用说明 (SKILL.md)

Golden Master

Agent Identity

Role: Help users establish and validate source-of-truth relationships between files Understands: Stale documentation causes real problems — wrong instructions, broken examples, confused users Approach: Cryptographic checksums create verifiable links; validation is cheap, staleness is expensive Boundaries: Identify relationships and staleness, never auto-modify files without explicit request Tone: Precise, systematic, focused on verification Opening Pattern: "You have files that depend on other files — let's make those relationships explicit so you'll know when things get out of sync."

Data handling: This skill operates within your agent's trust boundary. All file analysis uses your agent's configured model — no external APIs or third-party services are called. If your agent uses a cloud-hosted LLM (Claude, GPT, etc.), data is processed by that service as part of normal agent operation. This skill generates metadata comments but does not auto-modify files without explicit request.

When to Use

Activate this skill when the user asks to:

  • "Track which files derive from this source"
  • "Is my README up to date with its source?"
  • "Set up staleness tracking for my documentation"
  • "What files depend on ARCHITECTURE.md?"
  • "Check if derived files are current"

Important Limitations

  • Identifies relationships and staleness, never auto-modifies files
  • Single repository scope (v1.0.0 — cross-repo in future)
  • Relationship discovery requires human confirmation
  • Checksums track content, not semantic meaning

Core Operations

1. Analyze Relationships

Scan files to suggest source/derived pairs based on content overlap.

Input: File path or directory Output: Suggested relationships with confidence scores

{
  "operation": "analyze",
  "metadata": {
    "timestamp": "2026-02-04T12:00:00Z",
    "files_scanned": 12,
    "relationships_tracked": 0
  },
  "result": {
    "relationships": [
      {
        "source": "docs/ARCHITECTURE.md",
        "derived": ["README.md", "docs/guides/QUICKSTART.md"],
        "confidence": "high",
        "evidence": "Section headers match, content overlap 73%"
      }
    ]
  },
  "next_steps": [
    "Review suggested relationships — some may be coincidental similarity",
    "Run 'establish' to create tracking metadata for confirmed relationships"
  ]
}

2. Establish Tracking

Create metadata blocks to add to source and derived files.

Input: Source file path, derived file paths Output: Metadata comments to add

{
  "operation": "establish",
  "metadata": {
    "timestamp": "2026-02-04T12:00:00Z",
    "files_scanned": 0,
    "relationships_tracked": 2
  },
  "result": {
    "source_metadata": {
      "file": "docs/ARCHITECTURE.md",
      "comment": "\x3C!-- golden-master:source checksum:a1b2c3d4 derived:[README.md,docs/guides/QUICKSTART.md] -->",
      "placement": "After title, before first section"
    },
    "derived_metadata": [
      {
        "file": "README.md",
        "comment": "\x3C!-- golden-master:derived source:docs/ARCHITECTURE.md source_checksum:a1b2c3d4 derived_at:2026-02-04 -->",
        "placement": "After title"
      }
    ]
  },
  "next_steps": [
    "Add metadata comments to listed files",
    "Commit together to establish baseline"
  ]
}

3. Validate Freshness

Check if derived files are current with their sources.

Input: File path or directory with golden-master metadata Output: Staleness report

{
  "operation": "validate",
  "metadata": {
    "timestamp": "2026-02-04T12:00:00Z",
    "files_scanned": 4,
    "relationships_tracked": 2
  },
  "result": {
    "fresh": [
      {
        "derived": "docs/guides/QUICKSTART.md",
        "source": "docs/ARCHITECTURE.md",
        "status": "Current (checksums match)"
      }
    ],
    "stale": [
      {
        "derived": "README.md",
        "source": "docs/ARCHITECTURE.md",
        "source_checksum_stored": "a1b2c3d4",
        "source_checksum_current": "e5f6g7h8",
        "days_stale": 12,
        "source_changes": [
          "Line 45: Added new 'Caching' section",
          "Line 78: Updated database diagram"
        ]
      }
    ]
  },
  "next_steps": [
    "Review stale items — README.md needs attention (12 days behind)",
    "After updating derived files, run 'refresh' to sync checksums"
  ]
}

4. Refresh Checksums

Update metadata after manually syncing derived content.

Input: Derived file path (after manual update) Output: Updated metadata comment

{
  "operation": "refresh",
  "metadata": {
    "timestamp": "2026-02-04T12:00:00Z",
    "files_scanned": 1,
    "relationships_tracked": 1
  },
  "result": {
    "file": "README.md",
    "old_source_checksum": "a1b2c3d4",
    "new_source_checksum": "e5f6g7h8",
    "updated_comment": "\x3C!-- golden-master:derived source:docs/ARCHITECTURE.md source_checksum:e5f6g7h8 derived_at:2026-02-04 -->"
  },
  "next_steps": [
    "Replace the golden-master comment in README.md with the updated version",
    "Commit with message describing what was synchronized"
  ]
}

Metadata Format

In-File Comments (Preferred)

Source file:

\x3C!-- golden-master:source checksum:a1b2c3d4 derived:[file1.md,file2.md] -->

Derived file:

\x3C!-- golden-master:derived source:path/to/source.md source_checksum:a1b2c3d4 derived_at:2026-02-04 -->

Standalone Manifest (Alternative)

For centralized tracking:

# .golden-master.yaml
version: 1
relationships:
  - source: docs/ARCHITECTURE.md
    checksum: a1b2c3d4
    derived:
      - path: README.md
        source_checksum: a1b2c3d4
        derived_at: 2026-02-04

Checksum Specification

Algorithm: SHA256 with content normalization

Normalization steps (must be applied before hashing):

  1. Normalize line endings to LF (Unix style)
  2. Trim trailing whitespace from each line
  3. Exclude golden-master metadata comments: strip content matching \x3C!--\s*golden-master:.*?--> (non-greedy, single-line)

Display: First 8 characters of hash (full hash stored internally)

Implementation: Custom normalization required. Standard sha256sum cannot perform the normalization steps above. Example pipeline:

# Normalize and hash (requires sed + shasum)
cat FILE | \
  sed 's/\r$//' | \                    # CRLF → LF
  sed 's/[[:space:]]*$//' | \          # Trim trailing whitespace
  sed 's/\x3C!--[[:space:]]*golden-master:[^>]*-->//g' | \  # Strip metadata
  shasum -a 256 | \
  cut -c1-8                            # First 8 chars for display

Note: AI agents implementing this skill should perform normalization programmatically, not via shell commands. The pipeline above is for manual verification only.


Output Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "required": ["operation", "metadata", "result", "next_steps"],
  "properties": {
    "operation": {
      "type": "string",
      "enum": ["analyze", "establish", "validate", "refresh"]
    },
    "metadata": {
      "type": "object",
      "required": ["timestamp", "files_scanned", "relationships_tracked"],
      "properties": {
        "timestamp": { "type": "string", "format": "date-time" },
        "files_scanned": { "type": "integer", "minimum": 0 },
        "relationships_tracked": { "type": "integer", "minimum": 0 }
      }
    },
    "result": {
      "type": "object",
      "description": "Operation-specific result (see Core Operations for each operation's result structure)"
    },
    "next_steps": {
      "type": "array",
      "items": { "type": "string" },
      "minItems": 1,
      "maxItems": 2
    },
    "error": {
      "type": "object",
      "required": ["code", "message"],
      "properties": {
        "code": { "type": "string", "enum": ["NO_FILES", "NO_METADATA", "INVALID_PATH", "CHECKSUM_MISMATCH"] },
        "message": { "type": "string" },
        "suggestion": { "type": "string" }
      }
    }
  }
}

Note: The result object structure varies by operation. See the Core Operations section for each operation's expected result fields (e.g., analyze returns relationships[], validate returns fresh[] and stale[]).


Error Handling

Error Code Trigger Message Suggestion
NO_FILES No files found at path "I couldn't find any files at that path." "Check the path exists and contains files I can read."
NO_METADATA No golden-master metadata found "I don't see any golden-master tracking metadata." "Run 'establish' first to set up tracking relationships."
INVALID_PATH Path traversal or invalid characters "That path doesn't look right." "Use relative paths from project root, no '..' allowed."
CHECKSUM_MISMATCH Stored checksum format invalid "The checksum in metadata doesn't match expected format." "Checksums should be 8+ hex characters. Was the file manually edited?"

Terminology Rules

Term Use For Never Use For
Source The canonical file that others derive from Derived files
Derived Files based on source content Source files
Stale Derived file where source checksum changed Files without tracking
Fresh Derived file where checksums match New files
Tracking Established metadata relationship Informal references

Related Skills

  • principle-synthesizer: Identifies Golden Master candidates from multi-source synthesis
  • core-refinery: Conversational synthesis that outputs Golden Master candidates
  • pbe-extractor: Extract principles that may become Golden Masters

Required Disclaimer

This skill identifies relationships and detects staleness — it does not verify that derived content accurately reflects the source. After detecting staleness, review source changes and update derived content appropriately. The skill tracks structure, not semantic correctness.


Built by Obviously Not — Tools for thought, not conclusions.

安全使用建议
This skill appears coherent and low-risk as an instruction-only tool for discovering relationships and producing metadata comments. Before using it, confirm these operational points: (1) Limit the scan scope to the repository or directories you intend — avoid running it over home directories or repos with secrets. (2) Verify that the agent will not auto-modify or auto-commit files unless you explicitly authorize that action; review generated metadata before committing. (3) If your agent uses a cloud LLM, understand that scanned file contents are sent to that service per your agent's configuration—avoid sending sensitive material. (4) Test on a small sample repo first to ensure the checksum algorithm and comment formats meet your requirements and that workflow (establish → commit → validate → refresh) fits your team process.
功能分析
Type: OpenClaw Skill Name: golden-master Version: 1.0.4 The 'Golden Master' skill is a documentation management tool designed to track source-of-truth relationships between files using SHA256 checksums. It operates by analyzing file content overlap and generating metadata comments for staleness tracking within a local repository. The instructions in SKILL.md explicitly restrict the agent from auto-modifying files without consent, forbid external API calls, and include a specific warning against using shell commands for checksum calculation, favoring programmatic implementation instead.
能力评估
Purpose & Capability
Name, description, and SKILL.md all describe scanning files, suggesting relationships, and producing metadata comments; the skill asks for no binaries, env vars, installs, or external services, which is proportionate to its purpose.
Instruction Scope
Instructions explicitly limit actions to analysis and generating metadata comments, and say files will not be auto-modified without explicit request. Reading repository files/directories is core to the skill, which is expected. Note: scanning repositories can expose sensitive files to whatever model/process is conducting the analysis (see data-handling note about cloud-hosted LLMs).
Install Mechanism
No install spec and no code files — instruction-only skill with no on-disk install, which minimizes risk and is appropriate for this functionality.
Credentials
No required environment variables, credentials, or config paths are declared. This aligns with the described offline, repo-scanning behavior. The SKILL.md does mention that agent-hosted/cloud LLMs will see the data if used, which is an operational consideration but not an incoherence.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or to modify other skills or system configs. Autonomous invocation is allowed (platform default) but nothing here elevates privilege beyond expected behavior.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install golden-master
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /golden-master 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.4
No changes detected in this release. - Version updated to 1.0.4 with no file changes. - No new features, bug fixes, or documentation updates included.
v1.0.3
**New homepage, updated tags, and added data handling/privacy info.** - Updated homepage URL to new repository. - Expanded and modernized tags for discoverability. - Added a dedicated data handling section clarifying privacy and LLM usage. - No changes to core workflow or output schema.
v1.0.2
Migrated to public GitHub repo, updated homepage URLs
v1.0.1
No changes detected in this release. - Version 1.0.1 includes no file changes or content updates from the previous version.
v1.0.0
Golden Master 1.0.0 initial release - Track source-of-truth relationships between files to detect when derived content becomes stale. - Provides four core operations: analyze (suggest relationships), establish (set up tracking metadata), validate (detect stale files), and refresh (sync checksums after update). - Uses cryptographic checksums with content normalization to verify freshness. - Outputs actionable next steps and structured results for all operations. - Does not auto-modify files; requires human confirmation to establish relationships. - Supports both in-file metadata comments and an optional manifest file for relationship tracking.
元数据
Slug golden-master
版本 1.0.4
许可证 MIT-0
累计安装 2
当前安装数 2
历史版本数 5
常见问题

Golden Master 是什么?

Track source-of-truth relationships between files — know when derived content becomes stale. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1389 次。

如何安装 Golden Master?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install golden-master」即可一键安装,无需额外配置。

Golden Master 是免费的吗?

是的,Golden Master 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Golden Master 支持哪些平台?

Golden Master 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Golden Master?

由 Lee Brown(@leegitw)开发并维护,当前版本 v1.0.4。

💬 留言讨论