ditrixnew/edt-mcp/edt-mcp-project-workmate
Claude Code and agent skill by ditrixnew/edt-mcp
- community
Checking that the SKILL.md file is still in the repository.
Use EDT-MCP ask_workmate for explicitly requested 1C project research or a second opinion, then poll and verify the result. Not a default delegation route.
Install
npx vskill@latest install ditrixnew/edt-mcp/edt-mcp-project-workmateSKILL.md
EDT-MCP Workmate research
Purpose and trigger
Use this skill only when the user explicitly asks for Workmate research or an authorized second opinion on an exact 1C project question.
Operating rule
Read and apply the common operating rules before this workflow.
Task boundary
Keep one bounded subject-matter question, exact project/object identity, and requested answer mode in scope. Workmate is not a default implementation, Git, production-write, or proof route.
Primary workflow
- Resolve the project and inspect
get_tool_guideforask_workmate. - Treat
projectNameas Workmate context, not an authorization or isolation
boundary. For a bridge/tool-capable call that could write, require a proven filtered/read-only capability set or actual filesystem/process containment limited to every authorized project and file target; a one-project EDT workspace is not containment. Otherwise do not delegate mutations and stop for authority or containment.
- Submit one
ask_workmaterequest with the resolved exactprojectNameand
retain its returned job identity; do not omit the project and fall back to Workmate's default context.
- Poll only that job with
get_job_status; do not duplicate a committed
request to discover progress or recover from ambiguity.
- Verify target identity and load-bearing claims with direct read-only
EDT-MCP evidence before using the answer.
Authority rule
External model contact, shared write-capable tools, project mutations, and any retry after uncertain dispatch require the relevant user authority. A read-only prompt alone is not an enforcement boundary.
Stop rule
Stop when Workmate is unavailable, compatibility or target identity is unclear, completion is unconfirmed, unexpected writes appear, or the next step needs new material authorization.
Completion signal
Return the exact question/target, confirmed Workmate final state, directly verified claims, unresolved uncertainty, and any detected project effects.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingagent/skills/edt-mcp-project-workmate/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ditrixnew/edt-mcp/edt-mcp-project-workmate)