gowtham0992/link/link-retrieve
Claude Code and agent skill by gowtham0992/link
- community
Checking that the SKILL.md file is still in the repository.
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
Install
npx vskill@latest install gowtham0992/link/link-retrieveSKILL.md
Link Retrieve
Use bounded CLI commands so the agent does not dump the whole wiki into context. Load this skill proactively at the first substantive turn of a session, before project/release/debug/design work, or whenever the answer may depend on prior Link memory. In a source checkout, replace lnk with python3 link.py.
- If readiness is unclear, start with:
``bash lnk health [link-root] ` To ask what was true on a date, add --as-of YYYY-MM-DD to lnk recall` (or say "in March" in the query).
- If the user is inside a project repo and Link has no project context yet, seed allowlisted source-backed context before broad searching:
``bash lnk seed . [link-root] `` This reads project docs/rule files, blocks secret-looking values, and does not create durable memories.
- For most questions, use a compact query packet:
``bash lnk query "<question or task>" [link-root] --budget micro ` Read recall_capsule first. Increase to --budget small, --budget medium, or --budget large` only when the packet says more context is needed.
- Before longer work, prime from memory:
``bash lnk brief "<current task>" [link-root] ``
- For graph context, stay bounded:
``bash lnk graph-summary "<topic>" [link-root] --limit 40 --depth 1 ``
- For performance checks, use:
``bash lnk benchmark "<topic>" [link-root] --budget small ``
Do not enumerate every page, grep raw files, or request the full graph unless the user explicitly asks for an export or exhaustive audit, or the compact packet is insufficient and tells you which follow-up to use.
Recalled memories carry confidence labels and, when the optional local semantic tier is installed, a match field: lexical, hybrid, or semantic. Treat semantic matches (paraphrase similarity, capped confidence) and weak matches as hints to verify with the user, not facts to act on. Inside a repository, memories about code carry verified (what they name was found in place) or stale_paths (what moved or disappeared, with evidence): treat a stale memory as possibly wrong and say so rather than acting on it.
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
- SKILL.md in the repositoryCheckingskills/link-retrieve/SKILL.md
Popularity
- Repository stars
- 119
- Repository forks
- 16
- 7-day trend score
- 24
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
[](https://verified-skill.com/skills/gowtham0992/link/link-retrieve)