Verification procedures. Each skill runs one published protocol to produce evidence about code that already exists, rather than an argument about it. Ships /repro (delta debugging), /bisect (predicate-driven bisection), /boundary (equivalence partitioning and boundary value analysis), /differential (differential testing), /property (property-based testing), /mutate (mutation testing), and /characterize (Feathers characterization testing). All are manual except /characterize, /differential, and /mutate, which /hub can run as steps. Three skills bundle a zero-dependency Node script, and /mutate, the only skill that rewrites a tracked file, refuses to run on a dirty tree or a red suite and proves byte-identical restoration.
Plugin verify from marketplace naikidev in NaiKiDEV/claude-plugins. Commands read from the repo's manifest — 1 month ago.
bisectFind the commit that introduced a behaviour by binary search over history, with the predicate designed and validated before the search starts.
boundaryDerive test cases from the input space rather than from the code, using equivalence partitioning and boundary value analysis, then report which classes the existing tests already cover.
characterizeUse before changing code that has no tests, or only weak ones, at the point being changed, when the user asks or as a step inside /hub. Not for code whose tests already pin the behaviour the change could break, and not for stating what code should do. Pins current behaviour as lasting characterizati
differentialUse when a change claims behaviour is unchanged and a runnable reference version exists, such as the commit before a refactor or the implementation a rewrite replaces, when the user asks or as a step inside /hub. Not for changes meant to alter behaviour throughout, or where only one side can run. Ru
mutateUse only when asked to measure how well a file's tests catch changes, or when a /hub run needs to check tests a spoke wrote. Never for routine use, and never as a default check after an edit. It runs the test suite once per mutant, which takes minutes to hours, and rewrites the file under test while
propertyFind the invariants that must hold over all inputs and test those instead of examples, using whichever property-based framework the project already has.
reproShrink a failure to the smallest input, steps, or code that still triggers it. Delta debugging, with the oracle fixed before any reduction starts.
verify-mutatorMutation spoke dispatched by /mutate or /hub. Not for direct selection. Choose it when a mutation run over a file would produce many suite executions whose output is not worth carrying. Returns the survivors, classified, with the assertion each one needs.
verify-shrinkerReduction spoke dispatched by /repro. Not for direct selection. Choose it when a failure needs shrinking to a minimal case and the reduction will take many iterations whose intermediate output is not worth carrying. Returns the minimal case and what the reduction ruled out.
Manual-only visualizations (table, tree, flowchart, sequence, kanban, and 9 more) rendered by a bundled zero-dependency script so alignment never drifts, most skills drawing with Unicode box-drawing and symbols while list and checklist keep plain ASCII markers, since a single decorator glyph proved too subtle to read reliably.
14 skills
Manual-only controlled-language modes. Constrains the vocabulary, sentence shape, evidence, and order of what Claude writes to a published rule set, for one target or for the rest of the session. Ships /ste (ASD-STE100), /plain (ISO 24495-1 plain language), /ubiquitous (ubiquitous language), /calibrated (ICD 203 analytic standards), /normative (RFC 2119 keywords), /ears (Easy Approach to Requirements Syntax), /bluf (bottom line up front), /pyramid (Minto), /sbar (clinical handoff), /comments (Conventional Comments), and /diataxis (four documentation modes).
11 skills
Manual-only decision procedures. Each skill runs one published protocol against a judgment already on the table, structuring it without making it. Ships /reversible (one-way and two-way doors), /options (WRAP widening), /tradeoff (Kepner-Tregoe and Pugh), /hypotheses (ACH), /premortem (Klein), /redteam (adversarial review), /fermi (order-of-magnitude estimation), /base-rate (reference class forecasting), /quit (kill criteria), and /adr (Nygard decision records).
10 skills
Interrogatives for work in progress: /why /where /what /how /who /when. All are manual except /what, which /hub can run over the changes a run made. Claims carry checkable provenance instead of a confidence score, and nothing here writes.
6 skills
Refinement procedures. Each skill runs one published protocol against work that has been described but not yet defined well enough to execute, driving it down until every unit is unambiguous to a human and dispatchable by an orchestrator. Ships /impact (Adzic impact mapping), /wbs (work breakdown and the 100% rule), /split (Lawrence and Cohn splitting patterns), /examples (Wynne example mapping), /smells (ISO 29148 and requirements smells), and /invest (Wake's INVEST, which emits ready items in the five fields a spoke brief is made of). All are manual except /wbs and /invest, which /hub can run as steps when a task's pieces are not obvious.
5 skills
Manual-only hub-and-spoke orchestration. /hub turns the main session into a dispatcher that decomposes a task, writes self-contained cold-start briefs, gates the plan for approval, fans work out to subagents, verifies what comes back, and integrates. Delegation is the default, and a direct edit is a stated exception the hub has to justify and disclose.
1 skill · 3 agents
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.