mcpbeat Sign in

Reference Hunt Agent Skill

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.

477 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
295
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/Neeeophytee/finding-unknowns-skills --skill reference-hunt

The instruction itself

3 sections, as written by the author

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.

Other skills for the same job

different authors, same section of the catalogue
GitHub Project Management
by ComeOnOliver
×3

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

14k tokens
Folder Structure Blueprint Generator
by github
vendor ×1

Comprehensive technology-agnostic prompt for analyzing and documenting project folder structures. Auto-detects project types (.NET, Java, React, Angular, Python, Node.js, Flutter), generates detailed blueprints with visualization options, naming conventions, file placement patterns, and extension templates for maintaining consistent code organization across diverse technology stacks.

3k tokens
Sequential Thinking
by mrgoonie
×1

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

4k tokens
Openserv Multi Agent Workflows
by internet-court
×1

Multi-agent workflow examples to work together on the OpenServ Platform. Covers agent discovery, multi-agent workspaces, task dependencies, and workflow orchestration using the Platform Client. Read reference.md for the full API reference. Read openserv-agent-sdk and openserv-client for building and running agents.

24k tokens
Caveman Compress
by HoangNguyen0403
×1

> Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md.

7k tokens scripts
API Patterns
by lingxling
×1

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.

5k tokens scripts
Github Workflow Automation
by lingxling
×1

Patterns for automating GitHub workflows with AI assistance, inspired by [Gemini CLI](https://github.com/google-gemini/gemini-cli) and modern DevOps practices.

5k tokens
Domain Identification Grouping
by christophacham
×1

Groups existing components into logical business domains to plan service-based architecture. Use when asking "which components belong together?", "group these into services", "organize by domain", "component-to-domain mapping", or planning service extraction from an existing codebase. Do NOT use for identifying new domains from scratch (use domain-analysis) or analyzing coupling (use coupling-analysis).

10k tokens

How to use it

Copy the folder

Take neeeophytee/reference-hunt from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.