AI & ML

gapfdev Skill

Run parallel development safely using Git worktrees with one isolated branch per ticket. Use when multiple agents need to work concurrently in the same repository without branch conflicts.

gapfdev Bundle

Create and manage GitHub epics as parent issues with clear outcomes, sub-issue decomposition, dependency mapping, and closure criteria. Use when defining a new initiative, restructuring epic scope, or reviewing epic health.

gapfdev Skill

Ensures deliverables and structured content are presented in clear, copy-friendly Markdown code blocks for easy human consumption.

gapfdev Skill

Systematic code review checklist for quality, security, and maintainability

gapfdev Bundle

Plan and manage GitHub milestones with due dates, realistic scope, and outcome-based delivery targets. Use when preparing sprint/release slices, balancing capacity, or recalibrating timeline commitments.

gapfdev Skill

Orchestrate GitHub issue dependency execution across multiple agents with explicit start gates, unblock signals, and progress transitions. Use when a milestone has chained tickets and agents must start only after dependency tickets are closed.

rsmdt Bundle

Multi-agent code review with specialized perspectives (security, performance, patterns, simplification, tests)

kenneth-liao Bundle

Use when reviewing an agent team session export for quality, when asked to "analyze this team session", "review my agent team run", "what went wrong with this session", "how can I improve my agent team usage", or when provided a markdown team session transcript and asked for feedback on agent teams effectiveness.

studiogadget Bundle

NotionページをPDFファイルに変換するスキル。Notion MCPでページ内容を取得し、見栄えのよいPDFとして出力する。ユーザーがNotionページのURL・ID・タイトルを指定してPDF化・PDF変換・PDF出力・印刷用出力を依頼した場合に使用する。「このNotionページをPDFにして」「NotionページをPDFに変換して」「Notionを保存したい」「このページを印刷したい」「ドキュメントをPDFで共有したい」といった表現で起動する。ユーザーの発言にNotionページのURLが含まれていてPDF化の意図がある場合は、明示的にPDFと言っていなくても積極的にこのスキルの使用を検討する。

aeyeops Bundle

Use when authoring a custom Claude Code slash command, debugging slash command syntax, or converting a repetitive prompt into a reusable shortcut under `.claude/commands/`. Covers the reusable Markdown prompt template format, frontmatter configuration, argument handling, variable substitution, and workflow automation patterns. Trigger phrases include "create a slash command", "make a /command", "custom command", "argument-hint", and "my slash command does nothing".

aeyeops Bundle

Use when building or hardening a production-grade Python CLI tool, admin utility, data processor, or developer tooling - with UV for package management, Ruff for linting, Pyright for strict typing, Typer for commands, and Rich for polished output. Covers fail-fast patterns and custom exception hierarchies, modular code organization and module size limits, pydantic-settings configuration from YAML and .env, Makefile tasks and pre-commit checks, Rich progress bars, strict type-checking patterns, pytest structure for CLI commands, professional UX conventions, and building and installing the distribution. For command-line tools; for full-screen terminal UIs, use agent-tui-expert.

agile-v Skill

Generates standards-based repository documentation for GitHub or any project. Writes a docs suite into the project's docs/ directory covering ISO 9001, V-Model, ISO 27001, and optionally GAMP 5 or other standards. Use when the user asks for repo documentation, compliance docs, quality docs, or to create/refresh the docs/ suite.

agile-v Skill

Defines and checks the Agile-V control matrix for agentic tasks, skills, model use, tools, logs, rights, Human Gates, tests, costs, rollback, and owners. Load when creating, reviewing, or enforcing `.agile-v/CONTROL_MATRIX.yaml` or runtime governance for agentic execution.

agile-v Skill

Bainbridge-aware human oversight for agentic tasks. Defines the Human Oversight Case (blind precommit, claim-specific independence, surprise review, active challenge, recovery readiness) so a human approval is effective-oversight evidence, not just authority evidence. Load for L2+ tasks, any Human Gate, or when reviewing whether an agent's evidence is independent.

agile-v Skill

Dart/Flutter build agent for mobile apps, Flutter widgets, and Dart packages. Extends build-agent with Dart-specific conventions. Use when building Flutter apps, Dart packages, or mobile (iOS/Android) features.

agile-v Bundle

NestJS backend build agent for REST/GraphQL APIs, microservices, and enterprise backends. Extends build-agent with NestJS architectural patterns, dependency injection, testing strategies, and security best practices. Use when building NestJS applications.

agile-v Skill

Python build agent for scripts, backends, data pipelines, and ML projects. Extends build-agent with Python conventions. Use when building Python applications, APIs, data processing, or automation.

agile-v Bundle

Create evidence explaining the actual implementation diff and its relationship to the predicted impact, closing the loop between pre-change prediction and post-change reality.

agile-v Skill

C/C++ build agent for embedded systems, firmware, and MCU projects. Extends build-agent with embedded constraints. Use when building firmware, bare-metal code, or resource-constrained systems.

agile-v Bundle

Identify the likely impact of a proposed change before implementation by mapping it to graph nodes, affected files, functions, APIs, and tests.

agile-v Bundle

Create traceability from Agile V requirements to Understand Anything graph nodes, changed files, and tests, ensuring full evidence chain coverage.

agile-v Bundle

Select and prioritize regression tests based on the impact map and graph dependency relationships, flagging coverage gaps before the Red Team step.

agile-v Bundle

Consume Understand Anything outputs and create a concise, reviewable system overview that gives agents sufficient context before modifying code (Gate 0).

letta-ai Bundle

Set up and run LettaBot - a multi-channel AI assistant for Telegram, Slack, Discord, WhatsApp, and Signal. Supports both interactive wizard and non-interactive (agent-friendly) configuration.

aeyeops Bundle

Use when architecting a Model Context Protocol (MCP) integration, building or deploying a custom MCP server, choosing a transport mechanism, or debugging protocol-level issues and connectivity failures. Covers the JSON-RPC 2.0 spec, the MCP protocol lifecycle, FastMCP framework patterns, dual-client authentication, deployment patterns, production hardening, and diagnostic techniques. Trigger phrases include "build an MCP server", "MCP server won't connect", "server disconnected", stdio versus streamable HTTP transport, and exposing tools, resources, or prompts to an MCP client.

aeyeops Bundle

Use when automating browser or UI testing with a computer-use model - generating Gemini 2.5 computer-use automation scripts, natural-language goal files, or Playwright-based test harnesses for web application QA. Covers requirements analysis, goal file generation and validation, harness script generation, test iteration, scenario generation, visual regression testing, form automation, decision trees for automation type and goal scope, and the templates, examples, and validator scripts that ship with the skill. For AI-driven browser interaction workflows, not for unit or API test suites.

varalix-digitech-solutions Bundle

Build a Godot 4 / GDScript game feature with a coordinated agent team — a Manager (you), a Creative Director, a Logic Developer, an Animation Developer, and a Tester — that iteratively and autonomously design, build, juice, and verify the feature against the project's design contract to a strict, un-skippable quality bar. TWO gates are control flow, not judgment calls: the Tester gate (headless GDScript suite green + screenshot matches the design contract + project invariants hold) AND the Creative Director's fun gate (the running feature feels like the brief intended) — a feature does not advance until both pass, and the Manager runs a final on-device gate after. Use this whenever the user wants a game feature built thoroughly, end-to-end-verified, multiple features at once, or wants to stop Claude from half-assing and declaring "done" without proof. Triggers on "build this feature properly", "do it for real this time", "build it and don't stop until it passes", "use the build team", "oneshot this feature wi

synaptiai Bundle

Combine heterogeneous data sources into a unified model with conflict resolution, schema alignment, and provenance tracking. Use when merging data from multiple systems, consolidating information, or building comprehensive views.

arcblock Bundle

Deterministic issue-relationship graph over GitHub native sub-issues + dependencies — compute the ready set / parent-rollup candidates / close-kick targets as pure calculation (scripts, no LLM judgment), write real edges when creating spin-off issues, and mutually exclude terminal actions across parallel agents via claim-comment fencing. Called by issue-sweep (candidate injection), issue-review (edge writing + rollup), and the future agent:ready producer routine.

sontek Bundle

Review a PR or branch with specialized reviewers and propose concise, deduplicated comments. Use for "review this PR", "full PR review", "give me review comments", multi-agent review, or self-review/merge-readiness. Propose-only: never edit or post without approval. Use review-code for a focused pass, auto-review-code for fixes, and iterate-pr for CI/feedback.

sontek Skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill. Also covers when to ship a capability as an agent instead of a skill.

hivellm Skill

Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.

zate Skill

How to use Forge to submit headless agent jobs, check status, and retrieve output via MCP tools. Use when the user wants to delegate work to a background agent, run a task on another LLM, or interact with forge.

arcblock Skill

Upload a media file (image OR video/screen-recording) — or a whole directory of them — to the shared public asset repo and get back raw.githubusercontent.com/main URLs. For images that URL embeds inline via ![](); for video it is a LINK (GitHub won't inline-play raw video). Binary-safe: never MCP file-write (#1079). The mechanism is two universal plugin scripts (gh-upload-media.sh single, gh-upload-dir.sh dir); this skill is the discoverable entry + the doctrine. Used by test-sweep, ui-verify, and any repo's screenshot/recording flow.

arcblock Bundle

Attended multi-agent implementation of a WHOLE epic. One resident conductor decomposes an epic into dependency-ordered sub-issues, fans out an isolated worker per sub-issue (implement, verify, open PR), spawns an independent clean-context reviewer per PR, routes review and bot findings to a fixer, then gates and merges each PR and unlocks the next wave. Bot review (Codex + Cursor Bugbot) is short-wait (≤10m): findings or 👍 or silence-then-advance — never multi-hour stall. Every actionable inline review has an in-thread resolution; P1/High are fixed or REJECT-replied before merge; every fix re-stamps SHA-matched gates before merge. Human stays for high-level forks only (safe-default ratchet). Distinct from issue-sweep and pr-sweep (unattended batch over existing items) and build-phases (single agent phases of one issue). Use when implementing a whole epic end-to-end with a reachable human. Composes pr-review, verification, and the repo merge gate.

sontek Skill

Use this skill when the user asks to "write AGENTS.md", "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.