agentleFS
thehelpfultipperthehelpfultipper/wp-agent-mcp/.cursor/skills/wp-agent-toolkit-mcp-server/SKILL.md

wp-agent-toolkit-mcp-server

Skill1 starsChanged 33 days agoMITView on GitHub

Implements the local Node MCP server, indexing engine, and the generic component existence/variant auditor + similarity search tools.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when implementing or modifying the MCP server, indexing, auditing, similarity search, or patch workflow.

    line 9
  2. Distinctive:

    All tools return stable structured JSON with error codes on failure.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

MCP Server + Indexer + Auditor (POC)

When to use

Use when implementing or modifying the MCP server, indexing, auditing, similarity search, or patch workflow.

Hard requirements (POC)

  1. Public MCP tool set (names are for implementers and agent routing; end users only use natural language):
  • connect_wordpress
  • build_wp_index
  • get_index_status
  • audit_component
  • find_similar_content
  • where_is_used
  • query_wp_db_readonly (single validated read-only SELECT via wp db query)
  • get_theme_profile
  • get_design_bridge_readiness
  • bridge_design_to_implementation
  • search_project_files
  • read_project_file
  • apply_patch

Internal / low-level primitives stay out of normal user prompts (e.g. unconstrained wp db); query_wp_db_readonly is the supported path for ad hoc read-only reporting.

  1. Index:
  • SQLite schema per rules file "Index & API Contracts"
  • JSON debug exports for blocks/patterns/templates
  1. Safety:
  • allowlist wp-cli commands
  • WP root path sandboxing
  • patch-only writes; validate diff targets within WP root
  • php lint checks on changed PHP files when applying patch

Implementation approach

  • Build index in layers:
    1. filesystem discovery (block.json, patterns, templates, css/js markers)
    2. content indexing via wp db query on wp_posts (post_content)
  • Implement candidate ranking with a clear scoring breakdown:
    • name match
    • marker match
    • structural match (blockFingerprint)
    • usage weighting
    • variant mechanism proximity

Output requirement

All tools return stable structured JSON with error codes on failure.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.