agent-interface-design
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and…
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.
$ npx -y skills add Neeeophytee/finding-unknowns-skills --skill reference-hunt --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/reference-huntContext preview
The summary Claude sees to decide when to auto-load this 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.
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.
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.
1. 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. 2. Read the reference and produce a **semantics summary** before writing any code:
3. Have the user confirm the semantics summary. This is the moment misreadings get caught cheaply. 4. 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. 5. Close the loop: list each behavior from the summary and where the new implementation honors it, plus any place you consciously diverged and why.
14 installable skills that help your coding agent find what you don't know — before it gets expensive to fix. The map is not the territory. Your prompt is a map; the codebase and the real world are the territory.
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and…
Test a consequential technical assumption with a small, falsifiable experiment before committing to an approach. Use when a plan…
Surface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar…
Generate several genuinely different throwaway variations (designs, approaches, drafts) for the user to react to. Use when the…
After a working session, produce a report on what changed plus a quiz the user must pass before merging. Use when the user asks…
Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions,…