hicccc77/relink/relink

Claude Code and agent skill by hicccc77/relink

Trust tier 2
  • community
LLM review pending
Source check pending

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

Use the configured Relink MCP server for evidence-oriented analysis of authorized interaction records, timelines, patterns, and events. Do not use it for speculation when no Provider is configured.

Install

npx vskill@latest install hicccc77/relink/relink

SKILL.md

Relink Skill

This is an optional integration wrapper. The Agent Runtime, SDK, CLI, HTTP API, and MCP server remain fully usable without this Skill.

Workflow

  1. Call relink_dataset_summary to understand data coverage.
  2. Call relink_sessions to confirm available relationship sessions.
  3. For an investigation, call relink_run with a clear prompt, scope, and mode.
  4. For long runs, retain the returned runId so the caller can resume or replay it.

Use deep-research for questions that require cross-period reading, multiple source records, or an explicit evidence trail. Use standard for focused questions.

Evidence Presentation

Treat the answer, source pages, tool calls, and research trace as one evidence chain. Do not present model inferences as observed facts. Preserve missing data, Provider scope limits, and uncertainty in the final response.

Data and Privacy

Read only data returned by the authorized Provider. Do not send source content to an external model without user authorization. Model configuration, redaction, and tenant isolation belong to the integrating application. The Skill never reads files, databases, or platform-specific data directly.

Available Tools

  • relink_dataset_summary
  • relink_sessions
  • relink_search
  • relink_run
  • relink_runs
  • relink_abort
  • relink_conversations
  • relink_memory
  • relink_feedback
  • relink_title

The equivalent tool contracts are documented in MCP.md.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
62
Repository forks
7
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. 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/hicccc77/relink/relink/badge)](https://verified-skill.com/skills/hicccc77/relink/relink)

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