Agent Specification
ruvnet/ruflo
Agent skill for specification - invoke with $agent-specification
Use existing source code as the specification when the user can't describe what they want in words.
MITAuto-check passed
Install Reference Hunt
$ npx skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills reference-hunt --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/reference-hunt .claude/skills/reference-hunt && rm -rf skills-srcUse ~/.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/
Install the "reference-hunt" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/reference-hunt into .claude/skills/reference-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-hunt", 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 install https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/reference-huntType 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.
$ npx skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills reference-hunt --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/reference-hunt .agents/skills/reference-hunt && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "reference-hunt" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/reference-hunt into .agents/skills/reference-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-hunt", 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.
$ npx skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills reference-hunt --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/reference-hunt .cursor/skills/reference-hunt && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "reference-hunt" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/reference-hunt into .cursor/skills/reference-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-hunt", 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 https://github.com/Neeeophytee/finding-unknowns-skills.git --path skills/reference-hunt--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills reference-hunt --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/reference-hunt .gemini/skills/reference-hunt && rm -rf skills-srcUse ~/.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/
Install the "reference-hunt" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/reference-hunt into .gemini/skills/reference-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-hunt", 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.
$ gh skill install Neeeophytee/finding-unknowns-skills reference-huntInstalls 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).
$ npx skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/reference-hunt .github/skills/reference-hunt && rm -rf skills-srcUse ~/.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/
Install the "reference-hunt" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/reference-hunt into .github/skills/reference-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-hunt", 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.
$ npx skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills reference-hunt --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/reference-hunt .opencode/skills/reference-hunt && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "reference-hunt" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/reference-hunt into .opencode/skills/reference-hunt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reference-hunt", 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-hunt- GitHub stars
- 343
- Token cost
- ~476 tokens
- SKILL.md length
- 250 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use existing source code as the specification when the user can't describe what they want in words.
- Works in 5 steps: Get the reference: a repo path, a… → Read the reference and produce a… → Have the user confirm the semantics… → …
- Cant describe what they want in words
- SKILL.md covers Steps and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Reference Hunt is an agent skill from Neeeophytee/finding-unknowns-skills. Use existing source code as the specification when the user can't describe what they want in words. Use when the user points at a library, module, folder, or site and says "like this," even if it's in a different language or stack.
Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: 14 installable skills for Claude Code, OpenAI Codex, and Hermes: find unknowns, clarify requirements, manage context, test assumptions, and verify bug fixes with regression… The licence is MIT.
When your agent uses it
- Cant describe what they want in words
- The user points at a library
- Site and says like this
- Even if its in a different language
Example prompts
- “like this,”
- “/reference-hunt”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Get the reference: a repo path, a vendored folder, a library name, or a site whose underlying code can be read. Ask what specifically to…
- Read the reference and produce a semantics summary before writing any code
- Have the user confirm the semantics summary. This is the moment misreadings get caught cheaply.
- Reimplement in the target stack: same semantics, native idioms. Do not transliterate line by line, and do not copy code verbatim from…
- Close the loop: list each behavior from the summary and where the new implementation honors it, plus any place you consciously diverged…
What it can do on your machine
Read from SKILL.md and the folder at commit ca5696a. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Reference Hunt loads about 476 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 250 words of instructions outside code blocks.
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 Neeeophytee/finding-unknowns-skills at commit ca5696a, republished under its MIT licence (© Neeeophytee). 250 words, ~476 tokens.
Download SKILL.mdSave it as
.claude/skills/reference-hunt/SKILL.md (or your agent's skills folder).- name
- reference-hunt
- description
- Use existing source code as the specification when the user can't describe what they want in words. Use when the user points at a library, module, folder, or site and says "like this," even if it's in a different language or stack.
Reference hunt
Some requirements are too intricate or too tacit to write down, but working code somewhere already embodies them. The best reference is not a screenshot or a description — it's source. Read it like a spec, then reimplement the semantics, not the syntax.
Steps
- Get the reference: a repo path, a vendored folder, a library name, or a site whose underlying code can be read. Ask what specifically to extract from it — behavior, structure, visual system, API shape — so you don't imitate the wrong dimension.
- Read the reference and produce a semantics summary before writing any code:
- the behaviors and guarantees it implements (timing, ordering, error handling, edge cases),
- the decisions that look deliberate versus incidental,
- anything that won't translate to the target language or stack, with a proposed equivalent.
- Have the user confirm the semantics summary. This is the moment misreadings get caught cheaply.
- Reimplement in the target stack: same semantics, native idioms. Do not transliterate line by line, and do not copy code verbatim from references whose license doesn't allow it — note the license if it's unclear.
- Close the loop: list each behavior from the summary and where the new implementation honors it, plus any place you consciously diverged and why.
Guardrails
- The reference defines what; the target codebase's conventions define how.
- If the reference itself turns out to be buggy or inconsistent, surface that instead of faithfully reproducing the bug.
- Respect licenses: extracting semantics is fine; copying incompatible code is not.
© Neeeophytee, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/reference-hunt of Neeeophytee/finding-unknowns-skills.
Open the folder on GitHubat commit ca5696a
Compare with similar skills
Reference Hunt 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Reference Hunt this skillNeeeophytee/finding-unknowns-skills | 343 | — | ~476 | Automated safety check: Pass | MIT | |
| Agent Specificationruvnet/ruflo | 74k | 3 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Hunt Fintech Graphqlsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.9k | Automated safety check: Pass | MIT | |
| Specificity Managementthedaviddias/Front-End-Checklist | 74k | — | ~477 | Automated safety check: Pass | MIT | |
| Hunt Graphqlsickn33/agentic-awesome-skills | 47k | 1 repos | ~5.7k | Automated safety check: Pass | MIT | |
| Hunt Dispatchsickn33/agentic-awesome-skills | 47k | 1 repos | ~5k | Automated safety check: Notes | MIT |
Similar skills
Hunt Fintech Graphql
sickn33/agentic-awesome-skills
Hunt fintech-specific GraphQL vulnerabilities. An agent skill from sickn33/agentic-awesome-skills.
Specificity Management
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Keep CSS specificity low and flat.
Hunt Graphql
sickn33/agentic-awesome-skills
Hunting skill for graphql vulnerabilities. An agent skill from sickn33/agentic-awesome-skills.
Hunt Dispatch
sickn33/agentic-awesome-skills
Skill-set loader for /hunt orchestrator. An agent skill from sickn33/agentic-awesome-skills.
Hunt Sharepoint
sickn33/agentic-awesome-skills
Hunt Microsoft SharePoint Server (2013/2016/2019/Subscription Edition) on-prem farms
More from Neeeophytee/finding-unknowns-skills
All 14 skills in this repoAgent Interface Design
Neeeophytee/finding-unknowns-skills
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.
Assumption Test
Neeeophytee/finding-unknowns-skills
Test a consequential technical assumption with a small, falsifiable experiment before committing to an approach.
Blindspot Pass
Neeeophytee/finding-unknowns-skills
Surface the user's unknown unknowns before work starts. An agent skill from Neeeophytee/finding-unknowns-skills.
Brainstorm Prototypes
Neeeophytee/finding-unknowns-skills
Generate several genuinely different throwaway variations (designs, approaches, drafts) for the user to react to.
Change Quiz
Neeeophytee/finding-unknowns-skills
After a working session, produce a report on what changed plus a quiz the user must pass before merging.
Context Audit
Neeeophytee/finding-unknowns-skills
Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list.
Questions about Reference Hunt
What does Reference Hunt do?
Use existing source code as the specification when the user can't describe what they want in words. Reference Hunt is an agent skill from Neeeophytee/finding-unknowns-skills. Use existing source code as the specification when the user can't describe what they want in words.
When should I use Reference Hunt?
Reference Hunt fits situations like: cant describe what they want in words; the user points at a library; site and says like this; even if its in a different language.
How do I install Reference Hunt in Claude Code?
Run `npx skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt -a claude-code`. Or copy the skill folder (skills/reference-hunt in Neeeophytee/finding-unknowns-skills) into .claude/skills/reference-hunt in your project. Claude Code loads it when a task matches its description.
How do I install Reference Hunt in Codex?
Run `npx skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt -a codex`. Or copy the skill folder (skills/reference-hunt in Neeeophytee/finding-unknowns-skills) into .agents/skills/reference-hunt in your project. Codex loads it when a task matches its description.
Can I use Reference Hunt 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 Neeeophytee/finding-unknowns-skills --skill reference-hunt -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-hunt, .gemini/skills/reference-hunt, .github/skills/reference-hunt and .opencode/skills/reference-hunt in your project.
What does Reference Hunt need to run?
SKILL.md names no scripts, command-line tools or credentials: Reference Hunt is instructions for the agent only.
Does Reference Hunt 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 Reference Hunt 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 Hunt use?
Reference Hunt 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 Hunt use?
About 476 tokens (SKILL.md is roughly 1.9k 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 Hunt?
Skills that share tags, products or a category with Reference Hunt: Agent Specification (ruvnet/ruflo, 74k stars), Hunt Fintech Graphql (sickn33/agentic-awesome-skills, 47k stars), Specificity Management (thedaviddias/Front-End-Checklist, 74k stars) and Hunt Graphql (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reference Hunt?
Neeeophytee (a GitHub user) maintains it in Neeeophytee/finding-unknowns-skills, which has 343 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 28, 2026.
Source: Neeeophytee/finding-unknowns-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.