ditrixnew/edt-mcp/edt-mcp-project-local-fix

Claude Code and agent skill by ditrixnew/edt-mcp

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Apply one bounded BSL correction through EDT-MCP with lost-update protection, targeted validation, and minimal diff. Not for broad refactors or plugin code.

Install

npx vskill@latest install ditrixnew/edt-mcp/edt-mcp-project-local-fix

SKILL.md

EDT-MCP local BSL fix

Purpose and trigger

Use this skill when the defect and exact BSL method or small query-bearing fragment are known and the user requested a bounded correction.

Operating rule

Read and apply the common operating rules before this workflow.

Task boundary

Change one logical BSL surface in the exact project/module/method. Do not expand into architecture, metadata/form/DCS structure, unrelated cleanup, or plugin code.

Primary workflow

  1. Resolve and read the exact method with read_method_source; retain the

returned contentHash for lost-update protection.

  1. Validate a changed 1C query with validate_query before writing when

applicable.

  1. Consult get_tool_guide for the current write contract, then apply the

smallest guarded write_module_source edit. Mode replace overwrites the whole module; use it only for an intentional full-module replacement, not a method-sized edit.

  1. Re-read the method, revalidate any final query, and run targeted

revalidate_objects plus get_project_errors after every code write.

  1. Inspect the minimal repository diff and add only the focused test or runtime

probe required by acceptance.

Authority rule

The request authorizes only the bounded source correction. It does not authorize infobase updates, client launches, runtime data changes, broader refactors, or unrelated Git changes.

Stop rule

Stop before writing on target ambiguity, non-unique replacement, stale lost-update evidence, failed query validation, unready project state, or an unresolved design decision.

Completion signal

Return the exact changed method, minimal diff, successful readback and targeted validation, focused runtime/test evidence when required, and remaining static versus runtime gaps.

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

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ditrixnew/edt-mcp/edt-mcp-project-local-fix/badge)](https://verified-skill.com/skills/ditrixnew/edt-mcp/edt-mcp-project-local-fix)

Something wrong with this skill or its page? Tell us.