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…
Install the "link-retrieve" agent skill from https://github.com/gowtham0992/link/tree/main/skills/link-retrieve into .claude/skills/link-retrieve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-retrieve", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add gowtham0992/link --skill link-retrieve -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "link-retrieve" agent skill from https://github.com/gowtham0992/link/tree/main/skills/link-retrieve into .agents/skills/link-retrieve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-retrieve", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add gowtham0992/link --skill link-retrieve -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "link-retrieve" agent skill from https://github.com/gowtham0992/link/tree/main/skills/link-retrieve into .cursor/skills/link-retrieve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-retrieve", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add gowtham0992/link --skill link-retrieve -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "link-retrieve" agent skill from https://github.com/gowtham0992/link/tree/main/skills/link-retrieve into .gemini/skills/link-retrieve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-retrieve", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
GitHub CLI
$ gh skill install gowtham0992/link link-retrieve
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add gowtham0992/link --skill link-retrieve -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "link-retrieve" agent skill from https://github.com/gowtham0992/link/tree/main/skills/link-retrieve into .github/skills/link-retrieve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-retrieve", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add gowtham0992/link --skill link-retrieve -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "link-retrieve" agent skill from https://github.com/gowtham0992/link/tree/main/skills/link-retrieve into .opencode/skills/link-retrieve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-retrieve", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
link-retrieve
GitHub stars
201
Token cost
~519 tokens
SKILL.md length
223 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT
At a glance
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…
Works in 6 steps: If readiness is unclear, start with → If the user is inside a project repo and… → For most questions, use a compact query… → …
Knowledge Management work in your project
Calls python3
What it does
Link Retrieve is an agent skill from gowtham0992/link. 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.
Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Knowledge Management. It works with Model Context Protocol. The repository describes itself as: Local personal memory for LLM agents. The licence is MIT.
When your agent uses it
Knowledge Management work in your project
Example prompts
“/link-retrieve”
Requirements
Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
1If readiness is unclear, start with
2If the user is inside a project repo and Link has no project context yet, seed allowlisted source-backed context before broad searching
3For most questions, use a compact query packet
4Before longer work, prime from memory
5For graph context, stay bounded
6For performance checks, use
What it can do on your machine
Read from SKILL.md and the folder at commit cc92f36. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Link Retrieve loads about 519 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 223 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~56
When it runs· the whole SKILL.md, loaded when a task matches
~519
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/link-retrieve/SKILL.md (or your agent's skills folder).
name
link-retrieve
description
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.
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]
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.
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.
Link Retrieve next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Collects content from WeChat articles, web pages, YouTube, podcasts, documents and more, uploads it to NotebookLM and generates podcasts, slides or mind maps.
Creates NotebookLM notebooks from URLs, text and files, asks cited questions, runs web research and generates audio, slides, quizzes and other artifacts.
Read when the user asks what OpenKnowledge is, wants to install it on a repository, wants to open or preview a single markdown file that is not part of an OpenKnowledge project, wants to share an…
A skill your agent uses when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference.
A skill your agent uses when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates…
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore…
Use at the start of Link work when readiness is unclear, after installs or upgrades, and before repairs; verify health, inspect interrupted writes, back up, and repair generated indexes without MCP.
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…. Link Retrieve is an agent skill from gowtham0992/link. 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.
When should I use Link Retrieve?
Link Retrieve fits situations like: knowledge Management work in your project.
How do I install Link Retrieve in Claude Code?
Run `npx skills add gowtham0992/link --skill link-retrieve -a claude-code`. Or copy the skill folder (skills/link-retrieve in gowtham0992/link) into .claude/skills/link-retrieve in your project. Claude Code loads it when a task matches its description.
How do I install Link Retrieve in Codex?
Run `npx skills add gowtham0992/link --skill link-retrieve -a codex`. Or copy the skill folder (skills/link-retrieve in gowtham0992/link) into .agents/skills/link-retrieve in your project. Codex loads it when a task matches its description.
Can I use Link Retrieve in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gowtham0992/link --skill link-retrieve -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/link-retrieve, .gemini/skills/link-retrieve, .github/skills/link-retrieve and .opencode/skills/link-retrieve in your project.
What does Link Retrieve need to run?
Going by SKILL.md and its folder, Link Retrieve needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Link Retrieve access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Link Retrieve safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Link Retrieve use?
Link Retrieve is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Link Retrieve use?
About 519 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Link Retrieve?
Skills that share tags, products or a category with Link Retrieve: Multi-Source to NotebookLM Processor (joeseesun/qiaomu-anything-to-notebooklm, 6.2k stars), NotebookLM Research Workflow (claude-world/notebooklm-skill, 467 stars), Arkon Edit (nduckmink/arkon, 1.5k stars) and Open Knowledge Discovery (inkeep/open-knowledge, 4.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Link Retrieve?
gowtham0992 (a GitHub user) maintains it in gowtham0992/link, which has 201 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 28, 2026.
Source: gowtham0992/link on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
