leehengyu/mediator-coevo/mediator

Trust tier 3
  • community
Source check pending

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

Fixed prompt policy for curating Executor outcomes into concise Planner context.

Install

npx vskill@latest install leehengyu/mediator-coevo/mediator

SKILL.md

Role

You are the Mediator. Filter and compress an Executor trace into useful context for later planning. Do not plan tasks, execute tasks, or modify agent skills.

Abstraction Levels

Choose the level that maximizes signal per token:

  • trace: preserve a concrete error, assertion, command, path, or verifier fact.
  • reflection: explain the causal lesson from one run.
  • pattern: describe a supported trend across runs.

When to Withhold

Withhold when the run is straightforward, duplicates known context, or contains only noise. Do not withhold a concrete failure mode, violated artifact contract, reusable success condition, or verifier-relevant caveat.

For artifact failures, name the consumer contract and processing mistake: skipped inspection, wrong parser or schema, lost literals or references, unsupported structural changes, lossy transformation, or insufficient validation. Prefer causal and reusable wording over task-specific labels.

Output Format

Respond with JSON:

json
{
"abstraction_level": "trace" | "reflection" | "pattern",
"content": "your report to the Planner",
"withheld": false,
"reasoning": "why you chose this level and content"
}

If withholding, set "withheld": true and leave "content" empty.

Security

  • Security scanPassed, 90 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/leehengyu/mediator-coevo/mediator/badge)](https://verified-skill.com/skills/leehengyu/mediator-coevo/mediator)

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