Update a PR title and description based on the complete changeset.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Update a PR title and description based on the complete changeset.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Evidence before assertions.
Configure electron-updater with code signing verification, delta updates, staged rollouts, and multiple update channels for Electron applications
Automate Apple notarization with xcrun notarytool for macOS application distribution
Analyze and fix WPF applications for high DPI support, per-monitor DPI awareness, and scaling issues
Automated escalation path determination and workflow execution
Structured root cause analysis for incidents and problems
Sensitivity analysis skill for identifying critical inputs and understanding model behavior under uncertainty
Automated account reconciliation skill with matching algorithms and exception handling
Automated intercompany transaction identification and elimination skill for consolidated reporting
Expert skill for implementing parametric polymorphism including type parameter bounds, monomorphization, type erasure, variance, higher-kinded types, and associated types.
Container image and Kubernetes security scanning for CVEs, misconfigurations, and compliance
Run security scans including SAST, dependency scanning, and secret detection
Git workflows, branching strategies, and hooks.
A progressive AI literacy tutor that meets learners at their current level and advances them through three layers of competency: **AI User** (prompt engineering and output evaluation), **AI-Enhanced W
A structured tutor for medical and health sciences students covering anatomy, physiology, pharmacology, pathology, and clinical reasoning. This skill supports students preparing for medical licensing
Create handoff document for transferring work to another session
Mapping design, query optimization, aggregation patterns, index lifecycle management, and search relevance tuning.
Pattern for progressively refining context retrieval to solve the subagent context problem
Problem-solving strategies for hilbert spaces in functional analysis
Problem-solving strategies for gradient methods in optimization
Claude Code session analysis, tool call patterns, efficiency metrics, and anti-pattern detection
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Typosquatting detection, install script analysis, dependency confusion prevention, and phantom dependency detection for npm/pip.
Tum ekibi ayni anda devreye sok. Agent'lar paralel calisir, birbirine soru sorar, birlikte gelistirir. Kullanim: /swarm <gorev>
Find similar vulnerabilities across a codebase after discovering one instance. Uses pattern matching, AST search, Semgrep/CodeQL queries, and manual tracing to propagate findings. Adapted from Trail of Bits. Use after finding a bug to check if the same pattern exists elsewhere.
'Manage the PROGRAM.md operational contract that bounds autonomous development loops. Use when setting up or validating PROGRAM.md/AUTODEV.md, choosing between autodev and evolve, or turning a repeated postmortem -> analyze -> plan -> pre-mortem -> implement -> validate cycle into the v2 autonomous workflow.'
Track progress through the RPI workflow with permanent gates.
Help users write correct R code for async, parallel, and distributed computing using mirai. Use when users need to: run R code asynchronously or in parallel, write mirai code with correct dependency passing, set up local or remote parallel workers, convert code from future or parallel, use parallel map operations, integrate async tasks with Shiny or promises, or configure cluster/HPC computing.
Compute metrics for Claude Code sessions. Discovers via ccrider, filters trivial, computes friction/opportunity/fingerprint scores. Use for broad session triage.
Output rules for all agents - concise, scannable, actionable. Based on Matt Pocock's planning principles.
Produce an implementation plan at `.turbo/plans/<slug>.md`. Capture the task, survey patterns, escalate decisions, discuss, and draft.
Commit, push, and optionally create or update a PR for the current staged changes.
Provides Python patterns for type-first development with dataclasses, discriminated unions, NewType, and Protocol. Must use when reading or writing Python files.
Python asyncio patterns for concurrent programming. Triggers on: asyncio, async, await, coroutine, gather, semaphore, TaskGroup, event loop, aiohttp, concurrent.
This skill enables control of macOS applications and system functions through AppleScript execution via the `osascript` command.
Security architecture and implementation patterns. Use when designing
Create a thoughtful, supportive commit message from your staged changes.
Hooks are event-driven automation scripts that execute in response to Claude Code events. Use hooks to validate operations, enforce policies, add context, and integrate external tools into workflows.
Add a new third-party dependency to the project following the version catalog and approval workflow.
Transfer knowledge from source domains to novel target situations through structural mapping. Use when facing new markets, products, or situations where past experience provides relevant patterns. Produces adapted solutions with explicit mappings and context adjustments.
Evaluate alternative scenarios by simulating interventions on past decisions or hypothetical futures. Use when assessing decisions in hindsight, planning scenarios, or comparing paths not taken. Produces comparative analysis with probability-weighted outcomes.
Use when creating new skills, documenting workflows, or standardizing processes into reusable skill definitions.
Use when starting, pausing, completing, or transitioning task status in the development workflow.