Agent 工作流

claude-memory-curator

6agent-workflows

Audit and safely curate Claude Code instructions, rules, auto memory, and memory settings. Use when reviewing stale or misplaced Claude Code context, not Claude app memory or API memory stores.

stark-ai-de

belt

Use the belt CLI — run 250+ AI apps, manage knowledge, search skills, connect MCP servers. Purpose-built CLI interface for agent workflows — typed inputs, schema validation, no raw API calls needed.

belt-sh

tavily-search

Tavily AI search API - Optimized search for AI agents. Use when searching the web for current information, news, facts, or any task requiring real-time data.

veithly

mm2-analytics-dashboard-roblox

Murder Mystery 2 inventory tracking, analytics dashboard, and gameplay optimization toolkit for Roblox

aradotso

mm2-analytics-roblox-toolkit

Roblox Murder Mystery 2 analytics dashboard and inventory tracking toolkit with data visualization and strategy analysis

aradotso

mm2-analytics-dashboard-roblox

Murder Mystery 2 inventory tracking, analytics dashboard, and gameplay optimization toolkit for Roblox

reason-machines

mm2-analytics-roblox-toolkit

Roblox Murder Mystery 2 analytics dashboard and inventory tracking toolkit with data visualization and strategy analysis

reason-machines

seedance-2-5-reference-to-video

4agent-workflows

Generate reference-guided 1080p video with ByteDance Seedance 2.5 Reference to Video on RunComfy via the `runcomfy` CLI. Feed up to 9 reference images, 1-3 reference video clips, and 3 reference audio files into one call and get a 4-30 second 1080p clip with native synchronized audio, identity and style locked to your references. Documents the full input schema (images / videos / audios / aspect_ratio / duration / generate_audio), the counted-seconds billing model ($0.53 per second of reference video duration plus output duration), the 480p draft-then-deliver workflow, and when to route to Seedance 2.5 text-to-video, image-to-video, or Seedance 2.0 Pro instead. Calls `runcomfy run bytedance/seedance-2.5/reference-to-video/1080p`. Triggers on "seedance 2.5", "seedance 2.5 reference to video", "reference to video", "reference-to-video", "seedance 1080p", "ByteDance Seedance 2.5", "consistent character video", "style-locked video", or any explicit ask to generate video from reference images and clips.

genmedia-labs

wordspace

4agent-workflows

CLI for bootstrapping and managing wordspace projects

frames-engineering

commit-all

4agent-workflows

User-invoked via /commit-all only. Gathers the working tree into a single commit on the current branch, no push.

sentimony

value

3agent-workflows

skill does absolutely nothing, as well as the agent that uses it.

hugmouse

recoup-platform-build-os

3agent-workflows

Scaffold and run a label's self-managing "music-company OS" inside its own git repo — the full label-intelligence workspace (folders, a self-managing CLAUDE.md mirrored to AGENTS.md, a read-only doctor + never-stale janitor, compound-learning and self-improvement loops, an in-place plugin) seeded with Recoup's conventions (top-level artists/{slug}/RECOUP.md identity files, releases/{slug}/RELEASE.md) and backed by the Recoup API as system of record. Use for "set up our label OS", "build the org workspace", "turn this repo into our label brain", or onboarding a new org/label repo. Pulls the real roster from the live account (auth via recoup-platform-connect-account), onboards artists API-first via recoup-roster-add-artist, and calls the other recoup-* skills (research/content/release/song/catalog) instead of reinventing them. The single workspace/OS builder — also covers the lightweight "just mirror my roster into folders" case.

recoupable

CLI for bootstrapping and managing wordspace projects

frames-engineering

fusion-rules

Entrypoint for AI coding assistant rule authoring across GitHub Copilot, Cursor, and Claude Code. USE FOR: setting up rules, reviewing existing rules, scaffolding instruction files, or asking which editor format to use. DO NOT USE FOR: authoring skills (SKILL.md), agent definitions (.agent.md), or CI enforcement of rule files.

equinor

implement-issue-tree

親イシュー配下のサブイシュー（孫含む）を依存順を保ちつつ worktree で並列に自動実装・push 前 review・PR 作成・CI 監視・マージ可能状態化まで一括自動化。「イシューツリーを並列実装」「配下のサブイシューをまとめて実装」「ツリー全体を並列で実装して」「イシュー階層を自動開発」で使用。 per-issue 計画立案（Plan: セッション継承モデル）→実装（Implement: sonnet）の分業。push 前 review（Review 通過後にのみ push・PR 作成して CI を 1 回だけ起動）。外部チェック構成は args の externalChecks で明示（{"app", "context"} の組で宣言。[] で「なし」を確定して不要待機なし・未指定なら自動マージ停止・slug のみの旧形式は自動マージ fail-closed）。自動 squash merge は autoMerge: true + externalChecks 明示（全 App の信頼済み context 宣言込み）の opt-in で実行（merge-exec の自己取得再検証 + サーバー側 branch protection 実測が前提。既定 false はマージ可能状態で停止し人間がマージ。サーバー側 workflow サンプル（upstream の docs/implement-issue-tree/auto-merge-sample.yml 参照）+ branch protection への委譲も可）。並列度（parallel）と依存（dependsOn）で実行順を制御。 Phase 単位で厳密に直列化したい場合は phaseGate: true（opt-in。ルート直下の子〔Phase 親〕を sub-issues リスト順に直列化し、前 Phase の全子孫が merged/closed になるまで次 Phase 配下に着手しない。既定 false は現行の post-order 優先度のみ）。単一イシューの実装は implement-issue、PR レビューは implement-review-pr を参照。

fandhe-ai

implement-issue

GitHub Issue を読み込み、`_/local-plans/<issue-number>-<slug>.md` に詳細計画を作成して**ユーザー承認後**にコードを実装する。実装後はセキュリティレビュー (OWASP Top 10) → テスト実行 → Conventional Commits でコミット。Issue 番号や URL を渡された実装依頼、「Issue #N を実装して」「この Issue を着手」などで使用。

fandhe-ai

devrel-budget-allocation

Splits a developer relations budget across pillars - events, content, community, tooling, education, OSS sponsorship - into line items that each carry a cash cost, an hours cost, a pre-set return threshold, a review date and a reallocation rule, plus a ranked cut list. Use whenever someone asks how to plan or split a devrel budget, how much to spend on events versus content versus community, whether a line item is worth its money, how to defend a devrel budget at review, or what to cut first when the budget shrinks - even if they only say "we spend too much on conferences". Not the metrics framework (samber/developer-relations-skills@devrel-metrics) or one event's ROI (samber/developer-relations-skills@developer-event-sponsorship).

samber

event-budget

Build the budget and P&L for a technical event - every cost line split into fixed and per-head, the revenue mix against the funding model, a Good/Better/Best scope-tier ladder so break-even has three answers instead of one, a contingency sized as a stacked floor, pad and downgrade ladder, and outflows scheduled against the dates sponsor and ticket money actually lands. Use whenever asked to build an event budget, model conference or hackathon costs, find break-even, size a contingency reserve, plan event cash flow, or decide what to cut when revenue falls short. Consumes prices and real vendor quotes, never sets them. Do NOT use to set ticket or sponsor prices - use samber/dev-event-organizer-skills@event-ticket-pricing or samber/dev-event-organizer-skills@event-sponsor-pricing.

samber

dev-event-hiring

Employer-side hiring for tech-event-organizing roles - producer/manager/coordinator, and the community-manager-shaped end of the field. Calibrates the scorecard to operating context (in-house, agency, non-profit/community, or a standing conference business), builds the loop from the general event-planner sequence plus CMX's five-competency set and paid mini-audit work sample, flags the "one hire owns sponsorship, content and production" consolidation pattern seen in postings, sources candidates from general event-industry boards since no tech-specific one exists, and gates compensation on named sources (PCMA, BLS, Glassdoor) rather than a blended figure. Use when the user asks how to hire an event producer or manager, write a posting, design a loop, or hire an event community manager. Do NOT use for candidate prep (samber/dev-event-organizer-skills@dev-event-career) or team org design (samber/dev-event-organizer-skills@event-team-structure).

samber