asr-extractor
Internal Moonshot Architecture stage for extracting architecturally significant requirements and quality attribute scenarios from normalized requirements.
assumption-ledger
Keep product-definition work moving by recording ambiguity as assumptions or blockers instead of stopping the workflow.
audit
Run a technical UI quality audit across accessibility, performance, responsive behavior, theming, and design anti-patterns.
browser-verifier
Runs runtime/browser verification for web projects using URL health checks and optional E2E commands.
build-error-resolver
Resolves build and compilation errors. Use when build fails or type errors occur.
code-simplifier
Simplifies and refines recently modified code for clarity, consistency, and maintainability while preserving exact functionality.
codebase-architecture-recovery
Internal Moonshot Architecture stage for recovering current architecture from repository evidence before Brownfield design.
codebase-understanding
Build and query the regenerable account-root Code Index for the current Kernel project.
codex-review-code
Review non-trivial implementation changes for quality and regression risk before completion or merge.
codex-validate-plan
Runtime-adaptive plan validation skill (Plan Reviewer rubric). Use after writing context.md for complex feature/refactor work.
commit-moonshot
Update project memory and commit when the user explicitly wants both.
completion-verifier
Run required checks and decide whether implementation has enough evidence to be treated as complete.
context-readiness-gate
Checks whether a downstream task has the minimum context contract and routes to context-builder when it does not.
design-asset-parser
Parses design assets (PDF, CSS) to generate a draft design spec.
project-contract-gate
Checks whether a downstream project has a usable PROJECT.md contract and routes to project-md-refresh when it does not.
figma-spec-synthesizer
Synthesize implementation-ready UI design specs and planning/policy specs from live Figma files, Figma URLs, node IDs, screenshots, or large Figma planning boards. Use when a user asks to organize Figma design specs, planning specs, product policy specs, interaction states, screen behavior, or update an existing spec from added Figma cases.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use for React/web UI implementation and redesign work where visual direction matters.
harness-memory-promoter
Promote explicitly approved reusable project or harness knowledge after review, replay, rollback, and release evidence gates.
implementation-runner
Performs implementation in the chain and records completion state and changed files in analysisContext. Use during implementation.
karpathy-execution-gate
Pre-implementation execution gate based on four principles (think before coding, simplicity first, surgical changes, goal-driven execution).
kernel-browser-proof-adapter
Internal Kernel proof adapter for explicitly required browser scenarios.
kernel-commit-closeout
Internal Kernel skill for explicit, approved Git closeout after project knowledge commit.
kernel-commit
Safely commit explicit Git changes and optionally close out Kernel project knowledge.
kernel-conditional-frontend-guidance
Internal Kernel guidance for frontend and visual behavior changes.
kernel-diagnosing-bugs
Internal Moon Relay Kernel capability.
kernel-domain-modeling
Internal Moon Relay Kernel capability.
kernel-minimal-correct-change
Internal Moon Relay Kernel capability.
kernel-review-complexity
Internal Moon Relay Kernel capability.
kernel-review-spec
Internal Moon Relay Kernel capability.
kernel-review-standards
Internal Moon Relay Kernel capability.
kernel-security-review-policy
Internal Kernel policy for security-sensitive verification and independent review.
kernel-simplification-check
Internal conditional simplification guidance for non-trivial Kernel changes.
kernel-test-driven-development
Internal Moon Relay Kernel capability.
kernel-tracer-slicing
Internal Moon Relay Kernel capability.
kernel-verification-before-completion
Internal Moon Relay Kernel capability.
moonshot-architecture
Convert a PRD or existing codebase objective into an evidence-grounded architecture design package before implementation planning.
moonshot-classify-task
Classifies a user request into task types (feature, modification, bugfix, refactor) and extracts intent keywords. Use at the start of PM analysis.
moonshot-decide-sequence
Determines phase and execution chain based on analysisContext (task type, complexity, signals). Use after uncertainty detection.
moonshot-detect-uncertainty
Detects missing requirements and generates clarification questions. Use after classification/complexity to decide if user input is needed.
moonshot-evaluate-complexity
Evaluates complexity (simple, medium, complex) based on estimated files/lines/time. Use after task classification.
moonshot-in-session-coordinator
Coordinates phase-by-phase execution inside the current session while delegating each round to a fresh forked attempt agent.
moonshot-orchestrator
Use for bounded implementation work that already has enough context and does not need the phase harness.
moonshot-phase-executor
Skill-level phase execution adapter that routes prepared phase work to in-session coordinator execution, with delegated-terminal kept as legacy compatibility only.
moonshot-phase-runner
Use for large, phase-based, or long-running implementation work that should run from a prepared plan package.
moonshot-plan-writer
Create, refresh, and organize project-scoped account-root master and phase plans for phase-based work.
moonshot-relay-maintainer
Maintain the Moonshot harness and downstream .claude installs. Use when adopting external skill or harness patterns, improving moonshot-orchestrator or moonshot-phase-runner policy, fixing runtime parity or completion-gate fixtures, updating commit-memory defaults, or syncing shared .claude assets into target projects while preserving project-local PROJECT.md, memory, settings, logs, and task docs.
moonshot-relay-setup
Complete Moonshot Relay account-root installation after installing the repository with Agent Skills CLI.
moonshot-retro
Use for advisory retrospective collection, daily pattern analysis, and local improvement proposal or issue draft generation.
moonshot-teams-runner
Runs parallel Agent Teams for review, research, verification, and implementation workflows.
normalize
Realign UI work to the repository's design system, tokens, spacing, and established component patterns.
Page 1296 of 1665 · 83240 results