agentleFS
Quad4-SoftwareQuad4-Software/skills/.agents/skills/meshchatx/SKILL.md

meshchatx

Skill1 starsChanged 42 days ago0BSDView on GitHub

This skill exposes MeshChatX docs, codebase scaffolding, and GitHub issue tools through meshchatx. Use when you need MeshChatX manual topics, feature/scaffold checks, or issue management for the repo.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add the binary to your MCP client config as meshchatx.

    line 20

≈ “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

When to use this skill

  • You need MeshChatX docs (architecture, messaging, plugins, Android).
  • You are scaffolding a Svelte feature, backend manager, or plugin.
  • You are creating or triaging MeshChatX GitHub issues.

How to use

  1. Build meshchatx: cd mcp/meshchatx && go test ./... && go build.
  2. Add the binary to your MCP client config as meshchatx.
  3. list_topics/get_topic for docs, scaffold/checks_for for code, and the issue tools need a token.

Examples

  • "Fetch the messaging section of the MeshChatX docs."
  • "Scaffold a plugin named relay-stats."
  • "File a bug issue with version and reproduction fields."

meshchatx

meshchatx is the largest server: 22 tools in three families plus one prompt. Root is MCP_REPO_ROOT or the nearest .git, and codebase tools error without a root.

Docs tools (6)

list_topics, get_topic {id}, list_sections {id}, get_section {id, section}, search_docs {query, limit 5-20}, fetch_page {url} (host allowlisted to the topic index, i.e. meshchatx.com). Topics cover overview through linux-sandbox (19 total). Pages fetch over HTTPS on demand, so they are not offline.

Codebase tools (9, need repo root)

  • scaffold {kind, name}: kinds svelte-feature, svelte-component, backend-manager, ws-handler, plugin, metamorphic-test. Names match ^[a-z][a-z0-9_-]{0,48}$.
  • checks_for {surface}: surfaces svelte, backend, plugin, ws, docs, i18n, electron, landlock.
  • god_files, split_plan, surface_snapshot, surface_diff, feature_check, route_map, impact for refactor analysis.

Issue tools (7)

issue_templates, issue_create, issue_view, issue_update, issue_comment, issue_search, issue_references. Create, update, and comment are Write-marked.

Environment: token lookup order MESHCHATX_GITHUB_TOKEN, GITHUB_TOKEN, GH_TOKEN. Repo override MESHCHATX_ISSUES_REPO (default Quad4-Software/MeshChatX, validated owner/name). The token goes only to api.github.com. The API-backed tools (create, view, update, comment, search) all need a token, including reads. issue_templates and issue_references are local and work without one. Bodies are normalized to house style and about 30 known terms get auto-linked.

Prompts

docs_answer {question} wraps the docs index for a Q&A pass.

Notes and quirks

  • MCP_READ_ONLY=1 or READ_ONLY=1, plus the --read-only flag, hides the Write-marked tools.
  • Doc pages cache in a 32-entry LRU that never expires within a session (cacheTTL is declared but unused). Restart for fresh docs.
  • README drift: feature_check is implemented but undocumented.
  • Errors arrive as error: tool content, not JSON-RPC errors.

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.