GitHub
moonshot-evaluate-complexity
Evaluates complexity (simple, medium, complex) based on estimated files/lines/time. Use after task classification.
munlucky AI Skills
Explorez les skills IA publiés de munlucky et consultez leurs instructions source.
Explorer
GitHub
receiving-code-review
Collects and organizes code review feedback into actionable tasks.
GitHub
pre-flight-check
Checks essential information and project status before starting a task.
GitHub
design-asset-parser
Parses design assets (PDF, CSS) to generate a draft design spec.
GitHub
moonshot-detect-uncertainty
Detects missing requirements and generates clarification questions. Use after classification/complexity to decide if user input is needed.
GitHub
moonshot-orchestrator
PM workflow orchestrator. Analyzes user requests and automatically runs the optimal agent chain.
GitHub
codex-review-code
Review implementation quality and regression risks via claude-delegator (Code Reviewer expert). Use after implementation for complex tasks, refactors, or API changes.
GitHub
codex-test-integration
Validate integration impact and regression risks via claude-delegator (Code Reviewer expert). Use for complex tasks or API integration.
GitHub
doc-sync
Synchronizes documentation across agents to reflect planning changes and status updates.
GitHub
efficiency-tracker
Tracks workflow status and generates a flow report.
GitHub
codex-validate-plan
Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work.
GitHub
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.
GitHub
implementation-runner
Performs implementation in the chain and records completion state and changed files in analysisContext. Use during implementation.
GitHub
project-md-refresh
Analyze the current repository and create or refresh .claude/PROJECT.md to match the project. Use when PROJECT.md is missing, stale, or the user asks to generate/update project-specific rules, structure, comman...
GitHub
claude-codex-guardrail-loop
Use after planning or implementing non-trivial tasks - runs Codex MCP background verification/review for quality gates (plan validation + implementation review)
GitHub
session-logger
Logs development sessions in real-time to track decisions and issues.
GitHub
moonshot-decide-sequence
Determines phase and execution chain based on analysisContext (task type, complexity, signals). Use after uncertainty detection.
GitHub
session-logger
Log work sessions with timestamps, decisions, agent handoffs, issues, and outcomes. Use when a session log needs to be created or updated.
GitHub
efficiency-tracker
Track workflow timelines, blockers, verification results, and commits in flow-report.md. Use when recording execution flow or efficiency.
GitHub
pre-flight-check
Perform pre-flight checks for required info, project state, and missing context. Use before starting work to avoid gaps.
GitHub
design-asset-parser
Parse Figma/PDF design exports to extract UI specs and draft design-spec.md and pending-questions.md. Use when analyzing design assets.
GitHub
claude-codex-guardrail-loop
Run Codex plan validation or implementation review as a quality gate for non-trivial tasks. Use after planning or implementation.
GitHub
receiving-code-review
Triage code review feedback and reflect follow-up tasks in pending-questions/context. Use when incorporating review results.
GitHub
session-logger
Logs development sessions in real-time to track decisions and issues.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.