Claude Skills by sirius-cc-wu

github.com/sirius-cc-wu

26 skillsA× 260 installs10 views

Architecture Decision RecordsAAuthor and maintain concise Architecture Decision Records (ADRs) capturing accepted architectural choices, consequences, and system invariants. Use when establishing significant technical decisions, interface boundaries, protocols, or irreversible system designs.businessgosqlVotes: 0GitHub stars: 5
Assess Development InputARoutes an incoming development request or artifact to the narrowest responsible Sirius skill, external add-on, repository-native process, or prerequisite. Use at task intake when the correct owner is unclear, several skills appear plausible, authority or readiness may block progress, or coordinated work must be distinguished from one localized specialist task. Preserve source meaning and select one initial route without executing it.code-qualityrustgoVotes: 0GitHub stars: 5
Audit Pr ScopeAAudits whether a pull request's scope matches its motivating problem. Use when asked if a PR is overengineered or underengineered, to evaluate PR scope creep, diff signal-to-noise ratio, or when planning to re-scope a large PR into vertical slices.code-qualitygobashVotes: 0GitHub stars: 5
Audit Vestigial ContractsAAudits code changes and diffs for removed features, configs, or tokens to identify residual passthroughs, orphaned parameters, and vestigial test scaffolding for human-approved pruning.code-qualityrefactoringapiVotes: 0GitHub stars: 5
Behavior Preserving RefactoringAImproves responsibility, dependency, and configuration structure through risk-calibrated, verified transformations without changing observable behavior. Use when moving a cohesive responsibility to an existing owner, correcting coupling or dependency direction, or consolidating configuration ownership behind adequate checks; route routine clarity cleanup to external code-simplification and boundary-sensitive redesign to iterative coordination.testinggorefactoringVotes: 0GitHub stars: 5
Cargo Worktree HygieneAManages compilation concurrency, per-worktree target isolation, and disk safety when coordinating parallel Rust builders across multiple git worktrees. Use when dispatching fleet builders, creating Rust worktrees, or operating on storage-constrained environments.ai-agentsrustgoVotes: 0GitHub stars: 5
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Create PrACreates GitHub pull requests with properly formatted titles. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.testingshellbashVotes: 0GitHub stars: 5
Create Verification HarnessAGenerates an agent-drivable verification harness and Glass Surface Map for web, CLI, desktop, or service applications, providing autonomous agents with runtime "eyes" (browser/CDP/Playwright, PTY, HTTP) to navigate, drive, and verify surfaces with concrete runtime evidence.testinggodebuggingVotes: 0GitHub stars: 5
Design Repository Artifact LayoutADesigns or revises the smallest repository-specific layout for durable candidate directions, requirements, analysis, design, recovery, decision, iteration, and verification artifacts. Use when a justified artifact has no clear home or local placement guide, when asked where technical artifacts should live, how canonical paths and indexes should be organized, whether a documentation structure should be split or consolidated, or how to migrate competing artifact homes while preserving links and...documentationgodocumentationVotes: 0GitHub stars: 5
Design Rust LifecyclesADesigns ownership-safe Rust lifecycles for resources, state transitions, staged startup, readiness, rollback, cancellation, concurrency, and fallible cleanup. Use when approved system behavior and native responsibilities must become explicit capability ownership, task supervision, consuming transitions, RAII, or shutdown design without losing the system or verification boundary.businessrustrefactoringVotes: 0GitHub stars: 5
Doubt Driven DevelopmentASubjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.testinggoshellVotes: 0GitHub stars: 5
Github Issue WorkflowAFile, triage, and advance GitHub issues through duplicate checking, structured intake, specification handoff, and evidence-based closure. Use when creating non-duplicative issues, proposing updates, or verifying and closing known issues.securitygogitVotes: 0GitHub stars: 5
HowAExplores the codebase to explain subsystem architecture, runtime flow, component boundaries, and onboarding mental models. Answers how does X work, where should this live, and which package owns this.code-qualitygorefactoringVotes: 0GitHub stars: 5
Prototype SpikeARapidly builds throwaway interactive prototypes in isolated scratch space to exhaust the design space and settle UI interactions, layout density, or architectural feel before committing to production code.designjavascriptjavaVotes: 0GitHub stars: 5
Recover SpecificationAWrites requirements, contracts, and decision records that prescribe the required behavior of code that is already implemented, instead of describing that code. Classifies observed behavior as intended, accidental, defect, or undecided; turns only approved intent into must-rules with acceptance examples; asks the decision owner about undecided points; and lists implementation gaps in a conformance record.code-qualityrefactoringVotes: 0GitHub stars: 5
Review PrAReview a GitHub pull request with structured five-axis review, present actionable findings for human approval, and optionally post selected comments with Mermaid diagrams.code-qualitygobashVotes: 0GitHub stars: 5
Select Technical ArtifactsASelects the smallest durable disposition for candidate requirements, analysis, design, decision, planning, recovery, or verification knowledge: create a standalone artifact, update an existing owner, embed it, keep it with implementation, defer it, or omit it. Use when asked which technical artifacts should exist, whether a document should be created or split out, how to reduce a proposed documentation set, or to review an artifact budget; use design-repository-artifact-layout after a justifi...researchgodocumentationVotes: 0GitHub stars: 5
Software Design Language AdaptationAAdapts language-neutral architecture, behavior, boundaries, state, responsibilities, collaborations, patterns, and diagrams to idiomatic Rust, Python, TypeScript, C#, or C++. Use when implementation-facing design must account for a target language's native data, interface, ownership, error, concurrency, lifecycle, or runtime semantics without forcing object-oriented structure.developmenttypescriptpythonVotes: 0GitHub stars: 5
Spec QualificationAQualifies an implemented change, Builder Execution Report, and git diff against its governing behavioral specification (contracts, rules), anti-phantom call paths, and Architecture Decision Records (ADRs) to issue a binary Verified or Unverified verdict without executing builds directly.code-qualitygocode-reviewVotes: 0GitHub stars: 5
Specify Quality ConstraintsASpecifies measurable quality requirements, binding constraints, and acceptance evidence without designing the architecture. Use when performance, availability, security, privacy, accessibility, regulatory, operational, compatibility, data, platform, or other cross-cutting requirements are unclear or unmeasured; do not use for actor-goal flows, business-investment decisions, or architecture design.designgosecurityVotes: 0GitHub stars: 5
Tech LeadALead Playbook Coordinator. Routes engineering goals through structured playbooks (Golden Path, Streamlined Feature, Scoped Fix, Fleet Batch, Review Remediation, Investigation Spike, Prototype Spike, Visual Parity), enforces the Thinker/Builder boundary, and orchestrates autonomous builders in isolated worktrees.code-qualitygorefactoringVotes: 0GitHub stars: 5
Type Anchored SpecATranslates approved business rules, "Always Do / Never Do" boundaries, and agent workflow constraints into Rust's compile-time type system — using phantom types, typestate, sealed traits, and opaque wrappers — so the compiler enforces spec fidelity rather than relying on runtime checks or markdown alone. Use after a domain model, system boundary, and responsibility assignment exist but before implementation begins.businessrustgoVotes: 0GitHub stars: 5
VisionADefines, refines, or audits conformance against an evidence-backed project vision. Use to author or revise VISION.md with explicit identity, principles, non-goals, and accept-or-resist criteria, OR use to audit candidate features, design specifications, ADRs, or pull requests against an approved VISION.md to determine whether to accept, resist, or amend the project vision.businessgogitVotes: 0GitHub stars: 5
Visual ParityAVerifies pixel-exact UI equivalence between two implementations or across refactorings using automated browser harnesses and image diffs against a frozen baseline.designjavascriptgoVotes: 0GitHub stars: 5
Walkthrough MeAInteractively guides a reader through a pull request, commit, commit range, branch diff, or staged, unstaged, or selected untracked worktree changes in small, dependency-ordered sections. Use when the user wants to understand a bounded code change before reviewing, approving, committing, or modifying it, asks for a step-by-step code tour that pauses between sections, or invokes /walkthrough-me.testingrustgoVotes: 0GitHub stars: 5
WhyAInvestigates historical intent, design rationale, regressions, and postmortems behind code across 5 epistemics confidence tiers. Queries git history, PRs, issues, docs, chat, and observability to discover why code was built this way.researchgobashVotes: 0GitHub stars: 5