Agent skill

Reference Seek

by team-attention in team-attention/hoyeon

Install Reference Seek

skills CLI

$ npx skills add team-attention/hoyeon --skill reference-seek -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install team-attention/hoyeon reference-seek --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/reference-seek .claude/skills/reference-seek && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "reference-seek" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/reference-seek into .claude/skills/reference-seek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-seek", 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.

$skill-installer

$skill-installer install https://github.com/team-attention/hoyeon/tree/main/skills/reference-seek

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 team-attention/hoyeon --skill reference-seek -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install team-attention/hoyeon reference-seek --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/reference-seek .agents/skills/reference-seek && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "reference-seek" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/reference-seek into .agents/skills/reference-seek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-seek", 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 team-attention/hoyeon --skill reference-seek -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install team-attention/hoyeon reference-seek --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/reference-seek .cursor/skills/reference-seek && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "reference-seek" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/reference-seek into .cursor/skills/reference-seek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-seek", 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.

gemini skills install

$ gemini skills install https://github.com/team-attention/hoyeon.git --path skills/reference-seek

--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 team-attention/hoyeon --skill reference-seek -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install team-attention/hoyeon reference-seek --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/reference-seek .gemini/skills/reference-seek && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "reference-seek" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/reference-seek into .gemini/skills/reference-seek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-seek", 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 team-attention/hoyeon reference-seek

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 team-attention/hoyeon --skill reference-seek -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/reference-seek .github/skills/reference-seek && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "reference-seek" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/reference-seek into .github/skills/reference-seek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-seek", 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 team-attention/hoyeon --skill reference-seek -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install team-attention/hoyeon reference-seek --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/team-attention/hoyeon.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/reference-seek .opencode/skills/reference-seek && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "reference-seek" agent skill from https://github.com/team-attention/hoyeon/tree/main/skills/reference-seek into .opencode/skills/reference-seek/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-seek", 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: reference-seek
GitHub stars: 173
Token cost: ~2.4k tokens
SKILL.md length: 633 words
Files: 1
Skills in repo: 36
Repo updated: May 21, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 5 steps: Dependency Check + Topic Classification… → Parallel Search (1 message, up to 4… → Quality Filter + context7 Query… → …
Asks to find references
SKILL.md covers Purpose, Runtime Surface, Use Cases and Execution, plus 1 more section
Calls gh and curl; reaches raw.githubusercontent.com

What it does

Reference Seek is an agent skill from team-attention/hoyeon. This skill should be used when the user asks to "find references", "참고할 만한 거", "similar implementation", "오픈소스 있나", "how others do this", "레퍼런스 찾아줘", or needs to find existing patterns (internal) and open-source examples (external) for implementing a feature.

Its SKILL.md is about 2.4k 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 Backend & APIs, covering Codebase onboarding. It works with GitHub. The repository describes itself as: Requirements-first Harness — derive, verify, execute. The licence is MIT.

When your agent uses it

Asks to find references
Similar implementation
How others do this
Needs to find existing patterns (internal) and open-source examples (external) for implementing a feature

Example prompts

“find references”
“similar implementation”
“how others do this”
“/reference-seek”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Dependency Check + Topic Classification (1 message)
Parallel Search (1 message, up to 4 sources)
Quality Filter + context7 Query (sequential after Step 1)
Repo Deep Dive (sequential after Step 2)
Synthesize & Present

What it can do on your machine

Read from SKILL.md and the folder at commit 7cff032. 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:
- gh
- curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- raw.githubusercontent.com
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

Reference Seek loads about 2.4k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 633 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~69
When it runs · the whole SKILL.md, loaded when a task matches: ~2.4k

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.

SKILL.md

The full file from team-attention/hoyeon at commit 7cff032, republished under its MIT licence (© team-attention). 633 words, ~2,350 tokens.

Download SKILL.mdSave it as .claude/skills/reference-seek/SKILL.md (or your agent's skills folder).

name: reference-seek
description: This skill should be used when the user asks to "find references", "참고할 만한 거", "similar implementation", "오픈소스 있나", "how others do this", "레퍼런스 찾아줘", or needs to find existing patterns (internal) and open-source examples (external) for implementing a feature.
version: 2.0.0
validate_prompt: Must contain all of these sections: - Internal References section (with content or "No existing patterns found" message) - GitHub References section with at…

Reference Seek - Find Implementation References (v2.0.0)

Find internal patterns, quality-filtered GitHub repos with code-level insights, official docs, and external examples.

Purpose

When building a feature, find what you can reuse or learn from:

Internal: Existing patterns in the codebase
GitHub: Quality-filtered repos with actual code excerpts
Official Docs: context7-powered library documentation
External: Blog posts, tutorials, best practices

Runtime Surface

Claude Code

Use Task(Explore), gh, context7 MCP when available, and WebSearch as described below.

Codex

Map internal codebase search to hoyeon-code-explorer when installed.
Use Bash-first gh api and curl for GitHub discovery and code excerpts.
Do not require context7 MCP for v1; use it only if already available in the current runtime. Otherwise, use official docs via the available Codex web search/fetch surface and label that fallback.
If no native subagent adapter is loaded, perform the internal search directly with rg and targeted file reads.

Use Cases

"Looking to implement OAuth login — any good references?"
"Find references for implementing a rate limiter"
"How do I implement pagination? Find me some references"
"Any open source projects similar to WebSocket connection management?"

Execution

Step 0: Dependency Check + Topic Classification (1 message)

Run in parallel:

0-A. gh auth check:

bash

gh auth status

Result	Variable
Authenticated	`GH_AVAILABLE=true`
Not authenticated / gh not found	`GH_AVAILABLE=false`

0-B. Topic extraction + classification (reasoning, same message):

Extract from user request:

TOPIC: Normalized English topic (e.g., "rate limiting", "OAuth authentication")
TOPIC_CLASS: library | pattern | concept
GH_QUERY: GitHub search query (e.g., rate+limiter, oauth+middleware)
GH_LANG_FILTER: Language filter inferred from codebase (e.g., +language:typescript)
CONTEXT7_LIB: Library name for context7 resolve (if library class, use directly; otherwise best guess or skip)

Examples:

"any rate limiter references?" → TOPIC: rate limiting, CLASS: pattern, GH_QUERY: rate+limiter+middleware, CONTEXT7_LIB: rate-limiter-flexible
"NextAuth implementation references" → TOPIC: NextAuth authentication, CLASS: library, GH_QUERY: nextauth+authentication, CONTEXT7_LIB: next-auth
"pagination references" → TOPIC: pagination implementation, CLASS: pattern, GH_QUERY: pagination+cursor, CONTEXT7_LIB: skip

Step 1: Parallel Search (1 message, up to 4 sources)

CRITICAL: Run all available tracks in one message in parallel.

Track	Tool	Purpose
1-A	`Task(Explore)`	Internal codebase pattern search
1-B	`Bash: gh api search/repositories`	GitHub repo search (stars-sorted, top 10)
1-C	`mcp__context7__resolve-library-id`	Library docs ID lookup
1-D	`WebSearch`	Blog/tutorial search (1 query only)

1-A. Internal Search (Explore agent):

Task(subagent_type="Explore",
     prompt="""
Find existing patterns related to [{TOPIC}] in this codebase.
Look for:
- Similar implementations or utilities
- Patterns that could be reused or extended
- Related helper functions or modules

Report as file:line format with brief description of what's reusable.
""")

1-B. GitHub Search (only if GH_AVAILABLE=true):

bash

gh api "search/repositories?q={GH_QUERY}+{GH_LANG_FILTER}&sort=stars&per_page=10" \
  --jq '.items[] | select(.archived == false) | {
    full_name, stars: .stargazers_count, lang: .language,
    topics, license: .license.spdx_id, desc: .description,
    pushed: .pushed_at, url: .html_url, default_branch
  }'

1-C. context7 resolve (if CONTEXT7_LIB is set):

mcp__context7__resolve-library-id(libraryName="{CONTEXT7_LIB}")

1-D. WebSearch (1 query only):

WebSearch: "{TOPIC} implementation tutorial best practices 2024 2025"

When GH_AVAILABLE=false: Skip 1-B. Run WebSearch 3 times instead (v1.0 fallback):

WebSearch: "{TOPIC} implementation github"
WebSearch: "{TOPIC} open source example"
WebSearch: "{TOPIC} tutorial best practices"

Add warning at top of output: > ⚠️ GitHub API unavailable (gh not authenticated). Results from web search only.

Show full SKILL.md (232 more words)Show less

Step 2: Quality Filter + context7 Query (sequential after Step 1)

2-A. Quality Filter (reasoning, applied to 1-B results):

Criteria	Threshold
Stars	>= 100 (relax to >= 50 if fewer than 2 pass)
Last push	Within 24 months
License	MIT, Apache-2.0, BSD-2-Clause, BSD-3-Clause, ISC, MPL-2.0
Archived	Excluded (already filtered by jq)

→ Top 5 passing repos = QUALIFIED_REPOS → Top 1-2 repos = DEEP_DIVE_TARGETS

If all repos filtered out: relax stars to >= 50. If still none, take top 3 with warning badge ⚠️ Below quality threshold.

2-B. context7 docs query (only if 1-C resolve succeeded):

mcp__context7__query-docs(
  libraryId="{resolved_id}",
  query="{TOPIC} implementation patterns examples"
)

If resolve failed in 1-C, skip this step entirely.

Step 3: Repo Deep Dive (sequential after Step 2)

For each repo in DEEP_DIVE_TARGETS (1-2 repos):

3-1. File tree lookup:

bash

gh api "repos/{owner}/{repo}/git/trees/{default_branch}?recursive=1" \
  --jq '[.tree[] | select(.type=="blob") | select(.path | test("^(src|source|lib|pkg|core)/")) | {path, size}]'

3-2. File selection (reasoning):

Match files by topic keywords
Prioritize: entry points, types/interfaces, core logic
Skip files > 20KB
Select max 3 files per repo

3-3. File content fetch:

bash

curl -s "https://raw.githubusercontent.com/{owner}/{repo}/{default_branch}/{path}"

3-4. Code analysis (reasoning): Extract from each file:

Key data structures
Algorithm / approach
Configuration options
Notable patterns worth adopting

If file tree or fetch fails for a repo, skip its deep dive and move to the next target.

Step 4: Synthesize & Present

Combine all sources into the output format below.

Output Format

markdown

## Reference Seek: [{TOPIC}]

> Sources: Internal | GitHub ({N} repos, quality-filtered) | context7 | Web

---

### Internal References (Codebase)

#### Directly Reusable
- `{file}:{lines}` - {description}

#### Pattern Reference
- `{file}:{lines}` - {pattern description}

#### Integration Points
- `{file}:{lines}` - {connection point}

---

### GitHub References (Quality-Filtered)

1. **[{owner}/{repo}]({url})** ★{stars} | {lang} | {license} | Updated {date}
   - What: {description}
   - Topics: {topics}
   - **Key Code (`{path}`):**
     ```{lang}
     {10-30 lines of key code}
     ```
   - Takeaway: {actionable insight}

2. **[{owner}/{repo}]({url})** ★{stars} | {lang} | {license} | Updated {date}
   - What: {description}
   - Topics: {topics}
   - **Key Code (`{path}`):**
     ```{lang}
     {10-30 lines of key code}
     ```
   - Takeaway: {actionable insight}

3-5. (metadata only, no code excerpt)
3. **[{owner}/{repo}]({url})** ★{stars} | {lang} | {license} | Updated {date}
   - What: {description}

*(Filtered out: {N} repos excluded — low stars / outdated / incompatible license)*

---

### Official Docs (context7)

> Only include this section if context7 resolve succeeded in Step 1-C.

- {key concept}: {docs content}
- **Official Code Example:**
  ```{lang}
  {official example from docs}

External References (Blog / Tutorials)

{title} - Key insight: {content}

Usage Suggestions

Reuse: {how to leverage internal code}
Reference: {most relevant repo + why}
Official: {key takeaway from context7/docs}
Watch out: {pitfalls or caveats}


## Error Handling

| Situation | Response |
|-----------|----------|
| gh not authenticated | Skip 1-B, use WebSearch 3x fallback, add warning at top |
| gh rate limit (403) | Fallback: `gh search repos "{GH_QUERY}" --sort stars --limit 10 --json ...` (different rate limit bucket) |
| GH results 0 | Remove language filter, retry. If still 0, show "No GitHub results found" |
| All repos filtered out | Relax stars to >= 50. If still none, show top 3 with warning badge |
| context7 resolve fails | Omit "Official Docs" section entirely |
| File tree / fetch fails | Skip that repo's deep dive, proceed to next target |
| Explore returns nothing | Show "No existing patterns found in codebase" |
| Topic too vague | Ask user for clarification before proceeding |

Files

Just SKILL.md in skills/reference-seek of team-attention/hoyeon.

Open the folder on GitHubat commit 7cff032

Compare with similar skills

Reference Seek 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.

Reference Seek compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Reference Seek this skillteam-attention/hoyeon	173	—	~2.4k	Automated safety check: Pass	MIT	4 mo ago
Pp GitHubmvanhorn/printing-press-library	2.1k	—	~5.7k	Automated safety check: Notes	Apache-2.0	yesterday
GitHub MCPvibeeval/vibecosystem	531	—	~2.3k	Automated safety check: Notes	MIT	2 mo ago
GitDiagram Repository Overviewahmedkhaleel2004/gitdiagram	18k	—	~427	Automated safety check: Pass	MIT	yesterday
Repomix Codebase Packeryamadashy/repomix	29k	—	~1.3k	Automated safety check: Notes	MIT	4 days ago
GitDiagram Repo Architectureahmedkhaleel2004/gitdiagram	18k	—	~429	Automated safety check: Pass	MIT	yesterday

Similar skills

Pp GitHub
mvanhorn/printing-press-library
Every gh issue, PR, repo, and code-search workflow, plus a local SQLite mirror, offline full-text search Trigger phrases: find duplicate issues, who owes me reviews, what changed since the last…
2.1k GitHub stars~5.7k tokensUpdated yesterday
Backend & APIsAuto-check: notes
GitHub MCP
vibeeval/vibecosystem
GitHub MCP Server ile GitHub API erisimi. An agent skill from vibeeval/vibecosystem.
531 GitHub stars~2.3k tokensUpdated 2 mo ago
Agent WorkflowsAuto-check: notes
GitDiagram Repository Overview
ahmedkhaleel2004/gitdiagram
Explains the architecture of a public GitHub repository through GitDiagram: how the code is organized, the main components with paths, and a Mermaid diagram.
18k GitHub stars~427 tokensUpdated yesterday
DevelopmentAuto-check passed
Repomix Codebase Packer
yamadashy/repomix
Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.
29k GitHub stars~1.3k tokensUpdated 4 days ago
Agent WorkflowsAuto-check: notes
GitDiagram Repo Architecture
ahmedkhaleel2004/gitdiagram
Explains how a public GitHub repository is built by fetching its GitDiagram architecture diagram, components and optional explainer video.
18k GitHub stars~429 tokensUpdated yesterday
DevelopmentAuto-check passed
Octocode Code Research
bgauryy/octocode
Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.
946 GitHub stars~1.5k tokensUpdated 4 days ago
DevelopmentAuto-check passed

More from team-attention/hoyeon

All 36 skills in this repo

Skill Session Analyzer
team-attention/hoyeon
This skill should be used when the user asks to "analyze session", "evaluate skill execution", "check session logs", provides a session ID with a skill path, or wants to verify that a skill executed…
173 GitHub stars~1.9k tokensUpdated 4 mo ago
Auto-check: notes
Browser Work
team-attention/hoyeon
Recon-first browser automation. An agent skill from team-attention/hoyeon.
173 GitHub stars~1.9k tokensUpdated 4 mo ago
Auto-check passed
Check
team-attention/hoyeon
This skill should be used when the user wants to verify their changes before pushing, or update the project's rule checklists.
173 GitHub stars~1.8k tokensUpdated 4 mo ago
Auto-check: notes
Compound
team-attention/hoyeon
This skill should be used when the user says "/compound", "compound this", "document learnings", "save what we learned", or after completing a PR.
173 GitHub stars~1.1k tokensUpdated 4 mo ago
Auto-check: notes
QA
team-attention/hoyeon
Systematically QA test any application — web apps, native macOS apps, Electron apps, CLI tools, interactive REPLs, or anything on screen.
173 GitHub stars~2.6k tokensUpdated 4 mo ago
Auto-check: notes
Tech Decision
team-attention/hoyeon
This skill should be used when the user asks about "technical decision", "what to use", "A vs B", "comparison analysis", "library selection", "architecture decision", "which one to use"…
173 GitHub stars~1.4k tokensUpdated 4 mo ago
Auto-check passed

Works with

GitHub

Questions about Reference Seek

What does Reference Seek do?

This skill should be used when the user asks to "find references", "참고할 만한 거", "similar implementation", "오픈소스 있나", "how others do this", "레퍼런스 찾아줘", or needs to find existing patterns (internal)…. Reference Seek is an agent skill from team-attention/hoyeon. This skill should be used when the user asks to "find references", "참고할 만한 거", "similar implementation", "오픈소스 있나", "how others do this", "레퍼런스 찾아줘", or needs to find existing patterns (internal) and open-source examples (external) for implementing a feature.

When should I use Reference Seek?

Reference Seek fits situations like: asks to find references; similar implementation; how others do this; needs to find existing patterns (internal) and open-source examples (external) for implementing a feature.

How do I install Reference Seek in Claude Code?

Run `npx skills add team-attention/hoyeon --skill reference-seek -a claude-code`. Or copy the skill folder (skills/reference-seek in team-attention/hoyeon) into .claude/skills/reference-seek in your project. Claude Code loads it when a task matches its description.

How do I install Reference Seek in Codex?

Run `npx skills add team-attention/hoyeon --skill reference-seek -a codex`. Or copy the skill folder (skills/reference-seek in team-attention/hoyeon) into .agents/skills/reference-seek in your project. Codex loads it when a task matches its description.

Can I use Reference Seek 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 team-attention/hoyeon --skill reference-seek -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reference-seek, .gemini/skills/reference-seek, .github/skills/reference-seek and .opencode/skills/reference-seek in your project.

What does Reference Seek need to run?

Going by SKILL.md and its folder, Reference Seek needs the command-line tools its instructions call (gh and curl).

Does Reference Seek access the network?

SKILL.md names 1 domain. In commands or code: raw.githubusercontent.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Reference Seek 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 Reference Seek use?

Reference Seek 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 Reference Seek use?

About 2.4k tokens (SKILL.md is roughly 9.4k 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 Reference Seek?

Skills that share tags, products or a category with Reference Seek: Pp GitHub (mvanhorn/printing-press-library, 2.1k stars), GitHub MCP (vibeeval/vibecosystem, 531 stars), GitDiagram Repository Overview (ahmedkhaleel2004/gitdiagram, 18k stars) and Repomix Codebase Packer (yamadashy/repomix, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reference Seek?

team-attention (a GitHub organization) maintains it in team-attention/hoyeon, which has 173 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on May 21, 2026.

Source: team-attention/hoyeon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Reference Seek

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Reference Seek - Find Implementation References (v2.0.0)

Purpose

Runtime Surface

Claude Code

Codex

Use Cases

Execution

Step 0: Dependency Check + Topic Classification (1 message)

Step 1: Parallel Search (1 message, up to 4 sources)

Step 2: Quality Filter + context7 Query (sequential after Step 1)

Step 3: Repo Deep Dive (sequential after Step 2)

Step 4: Synthesize & Present

Output Format

External References (Blog / Tutorials)

Usage Suggestions

Files

Compare with similar skills

Similar skills

More from team-attention/hoyeon

Related

Questions about Reference Seek