GitHub
moonshot-evaluate-complexity
Evaluates complexity (simple, medium, complex) based on estimated files/lines/time. Use after task classification.
☆ 0View skill
munlucky AI Skills
Browse published AI skills maintained by munlucky. Compare skill descriptions and follow each source repository for setup instructions.
Browse skills
GitHub
receiving-code-review
Collects and organizes code review feedback into actionable tasks.
☆ 0View skill
GitHub
pre-flight-check
Checks essential information and project status before starting a task.
☆ 0View skill
GitHub
design-asset-parser
Parses design assets (PDF, CSS) to generate a draft design spec.
☆ 0View skill
GitHub
moonshot-detect-uncertainty
Detects missing requirements and generates clarification questions. Use after classification/complexity to decide if user input is needed.
☆ 0View skill
GitHub
moonshot-orchestrator
PM workflow orchestrator. Analyzes user requests and automatically runs the optimal agent chain.
☆ 0View skill
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.
☆ 0View skill
GitHub
codex-test-integration
Validate integration impact and regression risks via claude-delegator (Code Reviewer expert). Use for complex tasks or API integration.
☆ 0View skill
GitHub
doc-sync
Synchronizes documentation across agents to reflect planning changes and status updates.
☆ 0View skill
GitHub
efficiency-tracker
Tracks workflow status and generates a flow report.
☆ 0View skill
GitHub
codex-validate-plan
Validate architecture/plan quality via claude-delegator (Plan Reviewer expert). Use after writing context.md for complex feature/refactor work.
☆ 0View skill
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.
☆ 0View skill
GitHub
implementation-runner
Performs implementation in the chain and records completion state and changed files in analysisContext. Use during implementation.
☆ 0View skill
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...
☆ 0View skill
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)
☆ 0View skill
GitHub
session-logger
Logs development sessions in real-time to track decisions and issues.
☆ 0View skill
GitHub
moonshot-decide-sequence
Determines phase and execution chain based on analysisContext (task type, complexity, signals). Use after uncertainty detection.
☆ 0View skill
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.
☆ 0View skill
GitHub
efficiency-tracker
Track workflow timelines, blockers, verification results, and commits in flow-report.md. Use when recording execution flow or efficiency.
☆ 0View skill
GitHub
pre-flight-check
Perform pre-flight checks for required info, project state, and missing context. Use before starting work to avoid gaps.
☆ 0View skill
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.
☆ 0View skill
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.
☆ 0View skill
GitHub
receiving-code-review
Triage code review feedback and reflect follow-up tasks in pending-questions/context. Use when incorporating review results.
☆ 0View skill
GitHub
session-logger
Logs development sessions in real-time to track decisions and issues.
☆ 0View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.