Product & Planning

dabit3 Bundle

Plan, set up, and monitor a multi-agent video production pipeline backed by Sonic Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates Sonic profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Sonic rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.

egohygiene Skill

Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.

griddynamics Bundle

To validate story readiness for a sprint or to break work into a human WBS.

griddynamics Bundle

To establish what exists — affected areas, behavior, prior attempts, dependencies, data.

griddynamics Bundle

Workflow for initializing or upgrading a workspace: context, discovery, documentation, etc.

griddynamics Bundle

Discover tech stack.

jsgforever Bundle

Pump.fun - Complete Solana memecoin launchpad. Discovery, trending, gainers, losers, token data all work without a key. Trading requires SOLANA_PRIVATE_KEY.

jsgforever Bundle

Plan a new feature with structured PRD documentation. Researches codebase patterns, designs implementation phases, and writes PRD files to .dev/. Use when starting a new feature, spike, or major task.

jsgforever Bundle

Use telnet to interact with IoT device shells for pentesting operations including device enumeration, vulnerability discovery, credential testing, and post-exploitation. Use when the user needs to interact with network-accessible shells, IoT devices, or telnet services.

jsgforever Bundle

Save progress and generate a continuation prompt. Updates PRD status markers, captures git state, and writes checkpoint.md for the next session. Use at the end of a session or before switching context.

jsgforever Bundle

Alibaba Cloud generic CLI skill for installing, configuring, and using aliyun CLI to call OpenAPI actions across products. Use when users need command-line operations on Alibaba Cloud resources (list/query/create/update/delete), credential/profile setup, region/endpoint selection, or API discovery from CLI.

zenobi-us Bundle

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

zenobi-us Bundle

TPM-orchestrated planning, audit, roadmap, and research-driven decomposition. Owns the user-facing wrappers (cycle-plan, audit-issues, roadmap-*, research-*) and the underlying TPM execution workflows.

zenobi-us Bundle

Use with root `twg` for code search, repositories using an API/package, implementation and reverse-dependency discovery, PR status and reviews, repo contributors, hot areas, and issue-to-PR lookups.

zenobi-us Skill

Creates and operates moonrepo project generators through template authoring, discovery, and safe generation flows, when scaffolding repeatable apps/packages/config in a workspace, resulting in standardized code generation with predictable destinations and variables.

openharmonyinsight Bundle

分析 HM Desktop PRD 文档，提取需求信息、验证完整性、检查章节顺序（需求来源→需求背景→需求价值分析→竞品分析→需求描述）、检查 KEP 定义、检测需求冲突并生成结构化分析报告。适用于用户请求：(1) 分析或审查 PRD 文档, (2) 从需求中提取 KEP 列表, (3) 检查 PRD 完整性或一致性, (4) 将需求映射到模块架构, (5) 验证 PRD 格式合规性, (6) 验证竞品分析章节完整性。关键词：PRD分析, requirement extraction, KEP验证, completeness check, chapter order validation, 竞品分析检查, analyze PRD, 需求提取, 完整性检查, 章节顺序验证

winsorllc Bundle

Automatically discover, evaluate, and generate manifests for new PopeBot skills from GitHub. Based on ZeroClaw's SkillForge architecture.

egohygiene Skill

Prompt for creating an Epic Product Requirements Document (PRD) for a new epic. This PRD will be used as input for generating a technical architecture specification.

egohygiene Skill

Prompt for creating Product Requirements Documents (PRDs) for new features, based on an Epic.

egohygiene Bundle

Ranks any list of impediments and their countermeasures using a value-stream scoring model (ROI, Cost to Implement, Ease of Deployment, Risk Factor) and a fixed prioritization formula. Use when someone asks to prioritize, rank, sequence, or triage impediments, countermeasures, remediation items, risks, findings, gaps, action items, or backlog entries; or mentions value-stream prioritization, A3 / lean countermeasure ranking, ROI vs. effort scoring, or building a remediation / improvement backlog. Works with GHQR findings, audit results, retrospective action items, risk registers, architecture review gaps, or any free-form `{impediment, countermeasure}` list.

egohygiene Bundle

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

egohygiene Bundle

Creates or updates ROADMAP.md from repository evidence. Use when a project needs to define, repair, or review its strategic capability evolution and sequencing across time horizons.

egohygiene Bundle

Creates, reads, reconciles, compacts, and verifies a repository-root CONTINUITY.md operational handoff. Use when resuming repository work in a fresh session, repairing stale task state, or preparing an authorized repository change for pull-request review; do not use for conversation archiving, roadmap authoring, automatic merges, publication, or unrelated read-only questions.

dreamlab-ai Bundle

PRD to complete documentation in a single command. Use when you have a PRD and need specs, DDD domain model, ADRs, and an implementation plan generated from it.

dreamlab-ai Bundle

Context, persistence, and process-tracking companion for single-agent Claude Code sessions. Use when hydrating session context (git/plan/memory), tracking phased read/plan/implement/validate/document task plans, running blueprint workflows, doing progressive file discovery, persisting decisions across sessions, running a quick security scan before committing, or building autonomously from a PRD. Not for multi-agent swarms or hive-mind — use ruflo for those.

dreamlab-ai Bundle

Author a new Claude Code / Codex Agent Skill or audit an existing one against the estate's adopted authoring contract: correct frontmatter (name/description rules, which keys are portable vs harness-specific), the SKILL.md + references/ + scripts/ + assets/ progressive-disclosure layout, and the master-copy registration model. Use when scaffolding a new skill directory, writing or reviewing YAML frontmatter, deciding whether a field belongs in shared frontmatter or a Codex agents/openai.yaml sibling, or checking a skill will pass skills/lint-skills.sh. Not for cross-link/prose consistency across an existing corpus (docs-alignment), scaffolding from a PRD (prd2build), empirically tuning a skill's wording against a measured reward (skill-tuning), or general code generation without skill packaging.

dreamlab-ai Bundle

AI-first development methodology with specification-driven artifact traceability. PRD → SPEC → ADR → TASK → CODE → REVIEW → DEPLOY pipeline with AI-native ADRs (model selection, prompt strategy, agent orchestration), LLM evaluation suites, guardrails specifications, and sprint-driven workflows. Optimised for Claude Code and Ruflo/RuVector. Use when you need SPEC/ADR/TASK artifact chain traceability, AI-native ADR categories, or sprint scaffolding.

dreamlab-ai Bundle

Ground agent reasoning in DreamLab's formal knowledge graph (5,975 OWL classes, Oxigraph/Whelk) via the pervasive ontology binding (PRD-020/ADR-112). Use when you want to ground or augment thinking in the ontology, check what the knowledge graph says about a concept, retrieve a budget-bounded provenance-scoped subgraph (ontology_ask), run read-only SPARQL, find class neighbours or shortest paths, or propose a governed enrichment. Read-pervasive, write-governed; budget-bounded and fail-open so it never bloats the context window or blocks a turn.

majesticlabs-dev Skill

Discovery phase for blueprint workflow - interview triggers, acceptance criteria, and feature classification

majesticlabs-dev Skill

Post-documentation decision menu for fix-reporter. Routes to critical patterns, skill updates, cross-references, or discovery enablement.

majesticlabs-dev Skill

Framework for automated decision-making during multi-step planning workflows. Classifies planning decisions as Mechanical (auto-decide silently), Taste (auto-decide but surface at gate), or User Challenge (never auto-decide). Reduces question fatigue by batching only decisions that need human judgment. Use when running blueprint, PRD, refactor-plan, or any workflow that asks 5+ intermediate planning questions.

conectlens Skill

From idea to 12-week roadmap with deep-thinking checks and a weekly operating cadence.

conectlens Skill

Builds a 12-week startup roadmap with metrics, milestones, risks, and kill criteria — calibrated to current stage.

conectlens Skill

Use when designing feed, discovery, recommendation, and social-graph ranking rules that depend on follows, mutuals, privacy state, and account lifecycle.

zhaoxuya520 Bundle

端到端功能交付时使用。适用于从 PRD 到部署的一人闭环：Schema → API → UI → 联调 → 测试 → 部署。融合全栈交付清单 + 垂直切片 + 增量交付。

noorqureshi Skill

One line: port/host/service discovery tool arsenal for authorized engagements. Pack in trigger signals so it auto-loads: "new target", "enumerate", "scan", an in-scope target, open-port lists needing deeper enum. Authorized, in-scope targets only.