Claude Skills by MVPavan

github.com/MVPavan

40 skillsA× 400 installs46 views

Authoring For AgentsAUse when creating or changing agent instructions or their activation behavior. Skip edits that only correct spelling or formatting.businessawstestingVotes: 0GitHub stars: 2
BeadsAUse for Beads dependencies, intake states, recovery, workstream tracking, or unfamiliar task-lifecycle operations. Routine tracking uses AGENTS.md and runtime context.businessgogitVotes: 0GitHub stars: 2
BrainstormingAUse when material scope or behavior decisions need exploration, or the user requests brainstorming. Handle a single routine ambiguity directly.documentationVotes: 0GitHub stars: 2
Check InvariantsARun mechanically checkable invariants from the project overlay and report pass or fail.toolsVotes: 0GitHub stars: 2
Code ReviewAUse for substantive code review or to verify and act on review findings. Routine final diff inspection is not a separate review workflow.securityrustcode-reviewVotes: 0GitHub stars: 2
Codebase DesignAUse for substantive module-interface, encapsulation, or testability decisions. Skip ordinary code explanations and cosmetic refactors.designtestinggitVotes: 0GitHub stars: 2
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Codebase ResearchAGraduated research on an external or unfamiliar codebase — survey its capabilities, map its architecture, or trace one mechanism — into durable reports under docs/research/codebases/. Descriptive rather than a refactor proposal; local code explanations also fit, while improvement proposals use improve-codebase-architecture.documentationrustgitVotes: 0GitHub stars: 2
Cost EstimateALegacy entrypoint; the uncalibrated code-volume and commit-based estimation method is retired.researchVotes: 0GitHub stars: 2
Design EvolveAUse when integrating supplied discussions or decisions into a self-contained next version of existing design documents.businessVotes: 0GitHub stars: 2
Document ReviewAUse when a spec or plan document exists and needs a focused review for gaps, scope bloat, missing constraints, or risky assumptions. To interrogate the author about the plan instead, use grilling.researchsecurityperformanceVotes: 0GitHub stars: 2
Domain ModelingABuild and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model. Trigger on ADR phrases (record, write, supersede an ADR).documentationdocumentationVotes: 0GitHub stars: 2
ExecutionAUse to execute tracked multi-step work, a standalone plan, or a roadmap phase. Clear bounded implementation can proceed directly under AGENTS.md.code-qualitygodebuggingVotes: 0GitHub stars: 2
First Principles ThinkingAUse when explicitly requested, or only when a consequential decision hinges on an unresolved foundational assumption that ordinary inspection or the active workflow cannot settle. Skip routine edits, straightforward fixes, settled implementation plans, and generic requests to think critically.code-qualitydebuggingVotes: 0GitHub stars: 2
Grill MeAStart a decision interview using the shared grilling workflow.documentationVotes: 0GitHub stars: 2
Grill With DocsAStart a grilling interview and record authorized domain terminology and architectural decisions.documentationdocumentationVotes: 0GitHub stars: 2
GrillingAUse when the user explicitly requests a grilling interview to resolve or challenge material decisions. For a written critique, review the artifact directly.securitydocumentationVotes: 0GitHub stars: 2
Html ArtifactAUse for requested standalone HTML documents or interactive explanations when that format materially helps. Skip agent-facing files, Markdown-native deliverables, and ordinary short answers.designapiVotes: 0GitHub stars: 2
I Have AdhdAApply explicitly requested concise, easy-to-act-on communication preferences.documentationVotes: 0GitHub stars: 2
Idea RefineAExplore a raw idea through brainstorming using the legacy idea-refine entrypoint.documentationVotes: 0GitHub stars: 2
Improve Codebase ArchitectureAFind evidence-backed architecture improvements within a named area or requested codebase survey.code-qualityrefactoringVotes: 0GitHub stars: 2
Model CouncilAUse only for an explicitly requested council of named models or agents with a judge. Ordinary review and brainstorming do not need a council.researchVotes: 0GitHub stars: 2
Performance OptimizationAUse for measured latency, throughput, memory or cost problems, profiling, or explicit resource targets. Skip prose optimization and speculative tuning.researchdebuggingfrontendVotes: 0GitHub stars: 2
Perspective CouncilAUse only when the user explicitly requests a perspective council or war room. Answer ordinary decisions and critique requests without a council.researchVotes: 0GitHub stars: 2
Phase ExecutionAExecute one phase of a workstream roadmap. Thin entry point for the execution skill's phase scope.toolsVotes: 0GitHub stars: 2
PlanningAUse when settled work needs a durable implementation plan, dependency graph, or workstream decomposition. Skip planning ceremonies for clear bounded tasks.designgoVotes: 0GitHub stars: 2
PrototypeAUse when a runnable throwaway experiment can resolve a specific design, state-model, algorithm, or UI question.designgoVotes: 0GitHub stars: 2
Receiving Code ReviewAUse when explicitly invoking the legacy receiving-code-review entrypoint; incoming feedback is owned by code-review.code-qualitycode-reviewVotes: 0GitHub stars: 2
ResearchAUse when a decision needs multiple sources gathered and weighed. Answer a single factual lookup directly from an appropriate source.researchVotes: 0GitHub stars: 2
Resolving Merge ConflictsAUse when a git merge, rebase, or cherry-pick is already in a conflicted state and the conflicts need resolving. Trigger on merge-conflict / rebase-conflict phrases.researchgogitVotes: 0GitHub stars: 2
Run PhasesARun every remaining phase of a workstream unattended. Thin entry point for the execution skill's workstream scope.documentationVotes: 0GitHub stars: 2
SecurityAUse for material changes to trust boundaries, sensitive data, permissions, dependency execution, or untrusted inputs, and for requested security reviews.securityrustgoVotes: 0GitHub stars: 2
Show MeAShow the current topic visually, inline in the conversation. Use when the user asks to see the shape of code, a flow, an architecture, or a change ("/show-me", "show me", "sketch it", "draw the flow", "what does the structure look like"). For a rendered standalone document, use html-artifact instead.developmentgonodeVotes: 0GitHub stars: 2
Skill RouterAUse when unsure which skill or command fits a task, when two seem to overlap, or when the user asks what skills or commands exist, what one does, or which to use.researchgodebuggingVotes: 0GitHub stars: 2
Systematic DebuggingAUse when a failure cause is unclear, an attempted fix failed, or flaky behavior needs investigation. Handle obvious localized errors with a focused reproduction and fix.researchrustdebuggingVotes: 0GitHub stars: 2
Teach SessionAWalk through the current session using the shared teach workflow.ai-agentsVotes: 0GitHub stars: 2
TeachATeach a concept, walk through a session, or conduct an explicitly requested ongoing course.educationgoVotes: 0GitHub stars: 2
Test Driven DevelopmentAUse for risky behavior changes, regression proof, legacy characterization, or substantive test design. Trivial test renames do not require a test-first workflow.testinggoVotes: 0GitHub stars: 2
TriageAEvaluate unevaluated beads issues and move each to an intake state — ready-for-agent, human, needs-info, backlog, or a wontfix close. Use to review what needs attention or to triage a specific issue.ai-agentsrustVotes: 0GitHub stars: 2
Verification Before CompletionAUse only when explicitly invoking this legacy entrypoint; verification policy is owned by AGENTS.md.toolsVotes: 0GitHub stars: 2
WayfinderAMap and resolve material decision dependencies across a multi-session effort.documentationexpressdocumentationVotes: 0GitHub stars: 2