AI & ML

frumu-ai Skill

Configure Model Context Protocol (MCP) servers and customize Tandem skills for your organization.

microsoft Skill

Use this skill to classify the documentation impact of a pull request diff, returning one of three verdicts -- no-change, in-place edit, or structural change -- with bounded LLM cost. Activate as a sibling skill of docs-sync; the orchestrator calls this first, before any panel spawn, to keep cost floor at 1 LLM call when no docs work is needed. Reads .apm/docs-index.yml as the corpus map; never reads the full corpus.

microsoft Bundle

Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any `apm` CLI command.

frumu-ai Skill

Manages connected MCP sources for enterprise search. Detects available sources and handles source priority ordering.

outlinedriven-odin-gemini-cli-extension Skill

Lightweight conversational QA mode — user reports bugs in plain language, agent clarifies minimally, files GitHub issues that survive refactors. Trigger when the user says "QA", "QA session", wants to file bugs conversationally, or starts ad-hoc reporting without a fixed deliverable shape. Differentiates from branch-scoped review and PR-scoped review.

outlinedriven-odin-gemini-cli-extension Skill

Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use when the user invokes /duet, says "ask before" / "pair with me" / "human-in-the-loop", or for aesthetic/architectural/irreversible decisions.

lifecycle-innovations-limited Skill

Cross-OS computer-use MCP: multi-agent exclusive desktop leases, Xvnc pool on Linux, single-session macOS/Windows. Use for GUI/desktop automation and concurrent agent desktops.

outlinedriven-odin-gemini-cli-extension Bundle

Grill against the existing domain model. Stress-test a plan's terminology against `CONTEXT.md` and ADRs; update both inline as decisions crystallise. Trigger when user proposes a feature/refactor that touches business concepts and the project has documented domain language to honor — or when domain language is missing and needs capture.

outlinedriven-odin-gemini-cli-extension Skill

Restructure Web-UI / human-triggered tasks into CLI + file-output loops the LLM can iterate alone. Open LLM-side observability — structured logs, file dumps, addressable scratchpads. Apply the trap-or-abandon decision: if a step cannot be looped, improve the harness rather than babysit. Trigger when the user mentions iterative grunt-work, "I have to push a button in a web UI to trigger this", monitoring dashboards, designing Claude-driven automation, or any workflow whose inner loop currently requires a human in the middle.

camoneart Skill

Claude Code workflow tips from Boris Cherny (creator of Claude Code) and the Claude Code team. Use when: setting up Claude Code, optimizing workflows, running parallel sessions, configuring CLAUDE.md, using skills/commands, subagents, hooks, MCP integrations, or learning best practices. Covers: git worktrees, plan mode, verification, permissions, Slack MCP, BigQuery, prompting tips, plugins, custom agents, sandboxing, keybindings, status lines, output styles, and customization.

notque Skill

Verify VexJoy Agent installation, diagnose issues, and guide first-time setup.

notque Bundle

Metric-driven optimization loop: baseline a number, profile the cost, then accept or revert one change per iteration on measured evidence until the target is hit or the curve plateaus. Use when the user says "make this faster", "reduce memory", "speed up CI", "get p99 under 200ms", "improve the frame rate", "cut the bundle size", "make the tests run quicker", or "reduce token cost". Requires one number, a repeatable command that prints it, and a fixed dataset; the loop stops and says so when the harness is too noisy to measure the improvement being chased.

camoneart Bundle

Run external Ralph Loop (Geoffrey Huntley method) with clean context per iteration. Supports Simple mode (single PROMPT.md) and Full Ecosystem mode (specs/, fix_plan.md, AGENT.md, plan/build prompts). Unlike the official ralph-loop plugin which uses Stop hooks (same session, context pollution), this spawns fresh `claude -p` sessions each iteration. Use when user mentions "camone-ralph-loop", "external ralph", "clean ralph loop", "外部ラルフ", "ラルフループ実行", or wants to run iterative AI development with isolated context windows.

camoneart Bundle

Generate detailed, agent-executable feature specifications by interviewing the user with AskUserQuestionTool. Transforms rough ideas into comprehensive SPEC.md files through phased deep interviews (5 phases) covering technical architecture, data design, API design, UI/UX, edge cases, security, performance, and tradeoffs. Produces hybrid specs with Acceptance Criteria and phased implementation tasks with dependencies. Use when user mentions "spec", "仕様書作成", "仕様駆動", "インタビューして", "SPEC.md", "feature spec", "仕様を書いて", "大きな機能を計画", or wants to plan a feature before implementation.

camoneart Bundle

Install MCP servers into the current project scope using claude mcp add. Use when setting up a new project, when user mentions MCP setup, project MCP, MCPインストール, MCPセットアップ, or /installing-project-mcps.

camoneart Bundle

Orchestrate a comprehensive TDD workflow with multi-agent Red-Green-Refactor discipline, phase gates, and coverage validation. Use when user mentions "tdd-cycle", "TDDサイクル", "厳密なTDD", "TDDオーケストレーション", or needs strict test-first development with automated quality checks.

notque Bundle

AI image generation: Gemini and Nano Banana backends; single/series/batch workflows with prompt-to-disk.

sandbaseai-sandbase-skills Bundle

Portable multi-source research with cross-source validation and an offline evidence ledger. Use for fact-checking, comprehensive research, or any question requiring multiple independent perspectives; work with the host agent's search tools and optionally add SandBase Tavily, Exa, Scholar, and Cloudsway coverage.

notque Bundle

Classify user requests and route to the correct agent + skill. Primary entry point for all delegated work.

notque Bundle

A/B test agent variants for quality and token cost.

notque Bundle

Mandatory rules for agents in git worktree isolation.

grtninja Bundle

Operate and debug the Shockwave dashboard/router lane when shim-first model routing, startup contracts, tool-bridge behavior, and operator handoff must stay aligned. Use when recent dashboard work touches startup verification, bridge services, authority metadata, or router-facing docs.

notque Skill

Package session state for the next agent, or rehydrate it at start.

notque Bundle

Multi-agent consultation for architecture decisions.

grtninja Bundle

Audit Cybertron remote-host readiness, repo parity, WinRM auth-state, MeshGPT host-terminal bootstrap, canonical model-matrix validation, Starframe/Cybertron offload checks, and VRM display readiness.

grtninja Bundle

Operate and debug <PRIVATE_REPO_B> Control Center and thin-waist service surfaces. Use when working on connector routing, Lighthouse checks, MCP/Agent Bridge endpoints, pose bridge, canonical desktop startup/restart behavior, shortcut ownership, or window lifecycle/state ownership.

notque Bundle

Analyze agent/skill reference depth and generate missing domain-specific reference files.

oaustegard Bundle

Semantic Python code queries via a stdio LSP client driving pyright-langserver. Provides binding-resolved go-to-definition, find-references, hover types, type diagnostics, file symbol outlines, and project-wide symbol search — name resolution and type inference that tree-sitter and ripgrep cannot do. Use when you need to follow an import to a definition, find all real uses of a symbol (excluding same-named-but-unrelated ones), get an inferred type, surface type errors, outline a file, or search symbols across a project. Triggers on "go to definition", "find references", "what type is", "resolve this symbol", "symbol outline", "find symbol in project", "pyright", "type-check this file".

oaustegard Bundle

Builds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained `.skill` bundle (BM25 index + bundled searcher + query protocol). Use when a user wants to turn uploaded files, a folder, or a corpus into a searchable knowledgebase they can hand to any agent — phrased as "make a knowledgebase", "build a KB skill", "package these docs for retrieval", "create a searchable bundle", or references to a `.skill` KB. The output runs anywhere with Node or Python — no model, no install, no network. Distinct from `bm25` (ephemeral in-session search) and `building-github-index` (markdown project-knowledge index).

grtninja Bundle

Operate and secure the Continue Agent Bridge in <PRIVATE_REPO_B>. Use when configuring bridge modes, validating /api/agent endpoints, enforcing controlled-write safety gates, or diagnosing bridge availability and permission failures.

grtninja Bundle

Govern per-skill credit and token spend with deterministic warn/throttle/disable actions. Use when usage spikes, agent chatter, or budget overruns must be detected and contained.

grtninja Bundle

Operate the STARFRAME Media Workbench desktop app and its local 9040 worker as one restart-safe local contract. Use when fixing or validating the Electron shell, source staging flow, prompt-head automation, queue submission, live telemetry, output preview, or desktop startup acceptance for the private media app.

grtninja Bundle

Validate MX3 shim model-router, ORT provider, and runtime packaging contracts. Use when changing route-mode derivation, router environment mapping, capability metadata, inference routing responses, exact ORT provider builds, or Electron/embedded-Node ABI ownership.

grtninja Bundle

Operate Media Workbench source staging, prompt-head generation order, lane assignment, and resume-safe draft continuity as one workflow surface. Use when staging, previews, or generation-order logic change together.

oaustegard Bundle

Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when spawning subagents via the Agent or Workflow tools, when fanning out more than a handful of agents, or when asked which model or effort a task should get. Grounded in measured calibration (references/calibration-2026-07-15.md), a 2026-08 coding-cost study, and a 2026-09 agentic-repair battery that measured the cascade rungs directly; Managed Agents API specifics are operational, not calibrated.

oaustegard Bundle

Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.