Skill | Added | Review |
|---|---|---|
secure Threat modeling and risk audit for code changes and system designs. Walk the new attack surface, identify specific threats grounded in the change, propose security tests. Adversarial about assumptions, specific about risks. | 52 Impact — No eval scenarios have been run Securityby  Passed No known issues Reviewed: Version: 632c389 | |
experiment Design, run, and learn from experiments that test your riskiest assumptions. Handles the full experiment lifecycle — from designing the test to recording results to propagating what you learned back into the opportunity space. | 47 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
survey Home base for development work. Navigate the work graph, see what's ready, blocked, or stalled, reflect on where the team is, and decide what to pick up next. | 42 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
artifacts Type registry, schemas, and content guidance for discovery artifacts — objectives, opportunities, ideas, assumptions, experiments, critiques, memos. Load when authoring a new artifact, validating one, or resolving the type system. For simple reads (get/list/find), read the artifact file directly without loading this skill. | 68 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
critique Stress-test discovery artifacts from multiple perspectives. Examine ideas, opportunities, and plans through adversarial but constructive lenses — persona-based, framework-based, and domain-specific. | 35 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
artifacts Type registry, schemas, and content guidance for development artifacts — projects, epics, stories, tasks, specs, ADRs, spikes, work-items, workstreams, milestones. Load when authoring a new artifact, validating one, or resolving the type system. For simple reads (get/list/find), read the artifact file directly without loading this skill. | 73 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
assess Evaluate work items and designs before committing to build. Readiness checks, codebase-grounded feasibility, relative sizing, and stress-testing from multiple perspectives. The quality gate between planning and building. | 57 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
orient Home base for product discovery. Find your bearings in the opportunity space, think out loud about half-formed observations, make sense of what you're learning, and reflect on where the work stands. | 36 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
spec Write and evolve technical specifications — grounded design documents for a project, epic, or story. Record hard-to-reverse decisions as ADRs. Push back when the design isn't yet grounded in the codebase. | 58 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
ship Release engineering. Diagnose and fix CI/CD failures, get to green, cut releases, manage versioning and changelog notes. Pragmatic about getting changes safely into production — not perfect, shipped. | 60 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
plan Scope validated ideas into work items, decompose projects into parallel workstreams and epics, sequence milestones, map dependencies, and pressure-test the plan with a pre-mortem. | 63 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
prioritize Converge on what matters most. Take a set of options — assumptions, ideas, opportunities, or objectives — and decide where to focus. Evaluates, ranks, and connects prioritization to concrete next steps. | 48 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
sound Surface and examine the hidden assumptions beneath ideas, opportunities, and plans. Probe what your thinking rests on before committing to a direction. | 32 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
review Code review — yours or someone else's. Self-review before pushing, structured PR review against the story and the codebase, and feedback processing once reviewers respond. Reads the diff in surrounding context, not the patch alone. | 68 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
operate Infrastructure as code, CI/CD pipelines, containerization, observability, environment management. Read what exists before proposing change; preview blast radius before applying; never modify live infrastructure silently. | 40 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
build The developer inner loop, end to end. Pair through implementation with TDD discipline, self-review before pushing, create a PR with context for reviewers, and process review feedback. Picks up a ready story and carries it across the finish line. | 50 Impact — No eval scenarios have been run Securityby Advisory Suggest reviewing before use Reviewed: Version: 632c389 | |
test Strategy-first testing for the developer inner loop. Derive tests from acceptance criteria, write at the right layer, run and interpret, debug flakiness and ordering issues. Match the conventions already in the codebase — your tests should look like they belong. | 48 Impact — No eval scenarios have been run Securityby Advisory Suggest reviewing before use Reviewed: Version: 632c389 | |
verify Confirm a story is actually done. Walk acceptance criteria against the implementation, check test coverage at the right layer, identify edge cases the tests miss. Adversarial about "done" — does not take coverage claims on trust. | 60 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
foundation Loaded by deliver skills for the delivery model and interaction posture. Consult model.md for the six phases, skill ↔ agent pairing, and cross-plugin context (how delivery consumes development and discovery artifacts). Consult guidelines.md for ongoing interaction posture: thinking partner, ground in reality, signals to surface, anti-patterns, cross-plugin fallbacks. | 21 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
docs Keep documentation in sync with what the code actually does. Audit drift, generate new docs, update existing pages. Reads the code first, then the docs, then identifies the gap. | 56 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 | |
explore See what's in the opportunity space, notice gaps, and generate options to fill them. Handles both graph viewing and divergent generation (brainstorming). These are a continuum, not separate activities. | 36 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 632c389 |