Productivity

mr-fang-vlsi Bundle

Perform post-experiment retrospective for EDA runs, classify failure/success mechanisms, propose high-confidence next actions, and decide whether to recursively trigger a new workflow-scoped-execution iteration. Use after each experiment batch with monitor/summary/manifest artifacts.

mr-fang-vlsi Bundle

Select backside-routing candidate nets after placement/postCTS using power-first criteria with timing-safety vetoes. Use when the task is to build or validate reusable net lists/patterns for targeted GT3 backside reroute, especially when dynamic-power reduction is the primary objective.

mr-fang-vlsi Bundle

Execute one scoped EDA task under governed gates: run bootstrap checks, validate artifacts, and return execution evidence.

rizwanzafaris Bundle

Run the weekly product review as a truth-seeking WIP walk instead of a pitch meeting. Use when a product org needs a standing review ritual, when existing reviews have decayed into status theater or demo days, or when leadership keeps discovering work at launch that they should have shaped at the idea stage. Enforces the 48-hour pre-read, the per-team 20-minute walk across pre-build, in-progress, and post-build work, and decisions that land in the decision log the same day.

unknown-333 Skill

Build Dagster pipelines using software-defined assets — asset dependencies, partitions, resources and IO managers, asset checks, and schedules/sensors. Use when creating Dagster assets or jobs, modeling data as assets, adding partitions or backfills, wiring resources/IO managers, or migrating from task-based orchestration to assets.

unknown-333 Skill

Diagnose failing or stuck Apache Airflow pipelines — task failures and retries, scheduler/executor problems, XCom errors, zombie/queued tasks, dependency deadlocks, and pools/concurrency limits. Use when an Airflow task fails or is stuck queued, the scheduler is not running tasks, a DAG will not trigger, or tasks become zombies.

mikeyobrien Skill

Implement coding tasks with an explore-plan-code workflow and explicit verification gates.

mikeyobrien Skill

Generate structured .code-task.md files from rough descriptions or PDD plans.

nativescript Skill

Use when the iOS/Android keyboard covers a text input, when building a chat/composer/search bar docked to the keyboard, or when choosing between @nativescript/iqkeyboardmanager and @nativescript/input-accessory — the decision framework, the docked-composer implementation (TextView not TextField, tab-bar exclusion rule), and the verification workflow.

paultyng Skill

End-to-end shipping workflow. Formats, lints, tests, creates a changelog entry, commits with conventional commits, pushes, updates PR description, and suggests reviewers. Use when the user says "ship it", "commit and push", "fmt lint test commit push", or similar shipping commands.

paultyng Skill

Create Jira issues (stories, epics, initiatives) with custom field introspection to fill org-specific fields correctly. Use when the user asks to create a Jira ticket, story, epic, initiative, or task.

paultyng Skill

Create or update a Notion decision document with a structured options/pros/cons/recommendation template. Use when the user asks to create a decision doc, design doc, evaluation doc, or comparison in Notion.

quantipixels Bundle

Define a coding task's boundaries or deliver one supplied build job through implementation, proof, review, and handoff. Use scope-only for non-goals and expansion triggers without implementation; deliver authorized work with proof appropriate to the changed contract. Exclude pure explanation, bare review, monitoring, and provider publication except where they support delivery.

estuary Skill

Run flowctl catalog status to check the control-plane state of an Estuary resource, or list catalog specs to see which connectors exist and which are active. Use when checking whether a task is running, disabled, or failing, interpreting status output, or enumerating connectors. Use when user says "check task status", "is my capture running", "catalog status", "flowctl catalog status", "what's wrong with my capture", "task failing", "check catalog status", "collection status", "derivation status", "why is my task disabled", "list my connectors", "show me my connectors", "list captures", "list materializations", "what connectors do I have", or "show me all my active connectors".

estuary Bundle

Create an Estuary derivation with custom SQLite state (internal tables) to make per-document decisions based on accumulated history — account balances, inventory levels, approval workflows, deduplication. Derivations add complexity and cost — confirm the user wants a derivation before reaching for this. Use when user says "stateful derivation", "derivation to track balance", "transformation to approve based on state", "derive an approval workflow", "deduplication derivation", or "build a stateful derivation".

estuary Skill

Pause and restart Estuary connectors by disabling and re-enabling shards via flowctl. Use when temporarily stopping a connector, performing source/destination maintenance, or forcing a fresh restart to clear transient errors or load updated configs immediately. Use when user says "pause connector", "stop connector", "restart connector", "disable connector", "enable connector", "re-enable task", "disable shards", "stop my capture", "stop my materialization", "disable my materialization", "force restart connector", "connector maintenance", "temporarily stop processing", "shards disable true", "enable shards", "resume connector", or "unpause connector".

horizonrobotics Bundle

HMCT 模型转换与精度调优总入口。根据用户意图自动路由： (1) 提供了校准数据 → 调用 reference/run_build.py build 执行完整量化构建； (2) 未提供校准数据 → 调用 reference/run_build.py check 使用随机数据快速验证转换流程； (3) 用户希望进行精度调优 → 转交 j6-hmct-cosine-similarity-tuning SKILL 执行多阶段调优； (4) 用户希望进行单项精度 debug 分析（节点灵敏度、数据分布、累积误差等）→ 调用 hmct-debugger CLI 执行对应分析工具。 当用户提示词中出现 HMCT、模型转换、模型量化、PTQ、精度调优、cosine similarity、节点灵敏度、数据分布、累积误差、debug 等关键词时应触发此 Skill。

hummingbot Skill

Real-time reflex for improving yourself — turn user feedback, preferences, and workflow patterns into memories and skills as they happen

a-novel-kit Skill

Write and maintain GitHub Actions workflows, composite actions (action.yaml), and repo CI config across the a-novel / a-novel-kit orgs. Use whenever adding or editing a workflow, a shared action in a-novel-kit/workflows, a CI job, a required check, or a ruleset.

agentproto Skill

Walk through authoring a portable agentwork/v1 doctype — project, initiative, or task — with a unified scope vocabulary that keeps containment, applicability, and ownership as three orthogonal axes.

alectivism Skill

Create, update, or manage Asana tasks and projects. Use for "add to Asana", "create a task", "assign to [name]", "update the Asana task", or "check Asana for".

alectivism Skill

Find documents in your organization's document storage — SharePoint, Google Drive, Notion, or other knowledge bases. Use for "find the document", "where is the file", "find on [storage platform]", "look up the [document type]".

alectivism Bundle

Help someone turn the notes they already have into an Obsidian vault, then organize it. Use when someone says they want to set up Obsidian, asks what a vault is, asks how to get their Apple Notes or Granola or Evernote or Notion notes into one place, wants their notes organized into folders or tagged, asks whether Obsidian and Claude Cowork can use the same folder, or is stuck partway through setting Obsidian up.

alectivism Skill

Draft emails in your organization's brand voice. Use for "write an email", "draft a message", "reply to", "follow up with". Applies organization-appropriate tone by audience type.

alectivism Skill

Promotional content for your organization's events — email invitations, social posts, one-pagers, and speaker or sponsor outreach. Use for "promote [event name]", "write event copy", "event invitation for", or "sell sheet for [event]".

alectivism Skill

Sweep the past week across meetings, email, and chat, then force-rank the 5 to 10 topics a leadership team actually needs to discuss. Use when asked to prep for a leadership or team meeting, build an agenda, work out what to raise, or "prep me for Monday". Adapts to whichever meeting, mail, and chat tools are connected. For a personal inbox and calendar triage rather than a team agenda, use daily-briefing instead.

alectivism Skill

Produce a prioritized daily briefing covering new email received, sent mail still awaiting a reply, upcoming calendar events, and commitments the person still owes, sorted into Urgent / Needs Reply / FYI. Use whenever someone asks for a "daily briefing", "morning brief", "daily brief", "start my day", "what's on my plate", "catch me up on my inbox", "what needs my attention today", or any request to triage their inbox and calendar together. Works with whichever mail and calendar tools are connected (Outlook/Microsoft 365, Gmail/Google Workspace). Lookback defaults to 3 days of mail and is configurable; default output renders in chat.

alectivism Skill

Strategic content planning — editorial calendars, content pillars, distribution, audience targeting. Use for "content strategy", "editorial calendar", "content plan", or "what should we publish". For drafting individual pieces, use the content-draft skill.

alectivism Skill

Your organization's audiences — by type (e.g., end-user, partner, vendor), by role/seniority (executive, governance, technical SME), and by lifecycle stage (prospect, new, renewing) — with what each cares about and how to write, pitch, or present to them. Use when drafting, editing, or tailoring any email, deck, post, or document aimed at a specific audience.

alectivism Skill

Generate segmented follow-up emails after meetings — different messages for attendees, no-shows, speakers, and internal teams. Use for "meeting follow-up", "post-meeting email", or when a transcript or notes are provided.

alectivism Skill

Design Zapier workflows (Zaps) for any automation need — architecture, troubleshooting, Copilot prompts. Use for "build a Zap", "Zapier help", "automate this", or any workflow Zapier could solve.

alectivism Bundle

Track what the person promised in their meetings, suppress what is already handled, and hand back a short ranked list of what they still owe. Use when someone asks what they committed to, what they owe people, what they forgot, what is outstanding from their calls, "collect everything I was supposed to do", "what did I promise", "what am I behind on", "what's still open from my meetings", or asks for a recurring follow-up list. Also use to set that list up as a scheduled task, to mark commitments done, and on first run to configure where the tracker stores its data. Works against any meeting-notes source that exposes transcripts or summaries (Granola and Fireflies are used below as the worked examples). This tracks commitments across meetings over time; it does not write up an individual meeting.

alterlab-ieu Skill

Invoke for game jam participation -- 48-72 hour compressed development workflow. Triggers on: "game jam", "jam mode", "Ludum Dare", "GMTK Jam", "Global Game Jam", "Brackeys Jam", "48 hours", "jam submission". Do NOT invoke for normal development timelines (use game-start). Part of the AlterLab GameForge collection.

aws-samples Skill

Strategic workflow planning for AIDLC Phase 1 close-out. Chooses sequential / parallel-units / iterative execution mode via a decision tree, maps stories to units, and defines checkpoint gates. Produces workflow-plan.md as the hand-off artifact to the aidlc plugin construction phase.

greenpau Bundle

Implement execution that crosses process, worktree, machine, or service boundaries while preserving the shared session, capability, permission, task, and transcript contracts. Use for remote control, bridge sessions, reconnect and replay, subagents, teams, coordinators, mailboxes, worktrees, or distributed cancellation and result synthesis.

herchila Skill

Identifies and eliminates repetitive, manual, or inefficient work in a solo founder's operations. Use when you're doing the same thing manually more than twice, a process is taking too long, you want to automate a workflow, or you're spending time on things that should run themselves. Triggers on: "automate this", "this is taking too long", "I keep doing this manually", "optimize this workflow", "reduce manual work", "this process is inefficient", "automate my ops"