14 installable skills for Claude Code, OpenAI Codex, and Hermes: find unknowns, clarify requirements, manage context, test assumptions, and verify bug fixes with regression evidence.
安装
npx skills add Neeeophytee/finding-unknowns-skillsgh skill install Neeeophytee/finding-unknowns-skillsgit clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills合集内的技能
- Agent Interface DesignShilpa MitraDesign tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples. Use when building an MCP server or tool definition, writing an agent-facing script, or when an agent keeps misusing a tool it already has.
- Assumption TestShilpa MitraTest a consequential technical assumption with a small, falsifiable experiment before committing to an approach. Use when a plan depends on uncertain runtime, integration, or data behavior that inspection alone cannot establish. Not for preference interviews or routine implementation.
- Blindspot PassShilpa MitraSurface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar domain (design, video, infra), or explicitly asks for a "blindspot pass" or to find their "unknown unknowns."
- Brainstorm PrototypesShilpa MitraGenerate several genuinely different throwaway variations (designs, approaches, drafts) for the user to react to. Use when the user can only recognize what they want by seeing it — visual design, UX flows, naming, tone — or asks to brainstorm or prototype before building.
- Change QuizShilpa MitraAfter a working session, produce a report on what changed plus a quiz the user must pass before merging. Use when the user asks "what did we actually do," wants to review a large change, or invokes a quiz before merge.
- Context AuditShilpa MitraAudit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list. Use when an agent ignores its own instructions, when a CLAUDE.md has grown bloated, or when the user asks to audit or rightsize their agent context.
- Implementation NotesShilpa MitraKeep a running implementation-notes.md during a build, logging every deviation from the plan and every discovered edge case. Use whenever implementing against an agreed plan or spec, especially in long autonomous sessions.
- Implementation PlanShilpa MitraWrite an implementation plan that leads with the decisions the user is most likely to change, and buries the mechanical work at the bottom. Use when planning is requested before a build, especially after brainstorming or an interview.
- Interview MeShilpa MitraInterview the user one question at a time to resolve remaining ambiguity before implementation. Use when planning or brainstorming is done but unknowns remain, or when the user asks to be interviewed about a task or spec.
- Pitch PackagerShilpa MitraPackage a finished piece of work (spec, prototype, implementation notes) into a single document that gets reviewers to understanding and approval fast. Use when the user needs buy-in, a review, or a shareable summary of what was built and why.
- Progressive DisclosureShilpa MitraSplit an oversized skill, CLAUDE.md, or spec into an entry file plus files that load only when they're needed.
- Reference HuntShilpa MitraUse 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.
- Regression ProofShilpa MitraFix a reported bug with a regression test that demonstrably fails on the original behavior and passes after the fix. Use when implementing a bug fix or checking whether a proposed fix actually addresses a reported failure. Not a general coverage audit or new-feature workflow.
- Test BlindspotsShilpa MitraFind consequential behavior that a passing test suite does not establish, using focused exploratory checks. Use when the user asks what green tests miss or wants confidence in test coverage for a specific change. Not a general code review, routine test run, or debugging workflow for an already failing test.