Loading...
Loading...
Found 1,378 Skills
Use when migrating a Meteor 2.x application to Meteor 3.x. Triggers on callAsync, *Async Mongo, removed Fibers, implicit-global ReferenceError, lost Blaze reactivity, a publish function returning a Promise, a scheduler dropping a Promise, a read API receiving update modifiers, async allow/deny, an Iron Router controller not running, "Method stub took too long", Atmosphere resolution, Express 5 WebApp handlers, lost async context, rawCollection callbacks, meteor/* TypeScript types, useTracker, and useSubscribe. Use this skill when the user asks about upgrading Meteor, async caller propagation, iterators with await, zodern:types, or replacing and forking packages.
Resolve GitHub PR review feedback with source-backed triage, fixes, autogoal plan state, focused proof, replies, and thread resolution.
Map a product's lifecycle stage and choose between extension, replacement, and retirement plays. Use when a product is maturing or declining and the next move isn't obvious.
Build the months-long work-back plan for a tech event, any edition - the doors-open anchor date, parallel tracks (venue, program/CFP, sponsors, marketing, ticketing) each worked back from that date, cross-track dependency gates, a buffer policy through latest-safe commitment dates, and replanning checkpoints that cut scope instead of moving the date. Use whenever asked to build an event planning timeline, conference retroplanning, a work-back or reverse schedule, event milestone sequencing, or to replan an event running behind schedule. Scheduling mechanics only. Do NOT use to pick the date itself - use samber/dev-event-organizer-skills@event-date-selection - or for the day-of run of show - use samber/dev-event-organizer-skills@event-run-of-show.
DingTalk email reading/writing, searching, replying and forwarding. Use when user says send email/check email/reply email/forward email/unread email/email search/email attachment. When sending an email in one sentence, first use dingtalk-contact to parse and confirm the recipient, then this skill sends it; does not handle DingTalk messages (use dingtalk-chat), urgent notifications (use dingtalk-misc). Command prefix: dws mail.
Use when the user asks for ADHD mode or focus mode, mentions overwhelm, stuck starting, too many open threads or options, losing the plot after an interruption, executive-function friction, or needs low-friction multi-turn work. Structures replies with Answer/Action/Artifact/Project contracts, working-set limits (Active 1 · Ready ≤2), interruption recovery, Clean/Flow/Zen long-form modes, and explicit ND-safe directives (persona alone is not enough). Disable on "stop ADHD mode", "normal mode", or "stop focus mode".
Investigate a specific Nx cache miss, artifact download or extraction failure, same-hash non-replay, or suspected unsafe cache replay. Use this skill whenever a user asks why an Nx task did not use the cache, why cache artifact restoration failed, why a cache hit restored stale or wrong output, or to compare two cached task executions. Use the nx-cloud-api skill for every Nx Cloud read. This skill supports API-only investigations, preserves strict hash-evidence limits, and requests local configuration only when the question requires it.
The participation content format — polls, quizzes, Q&A / scoped AMAs, this-or-that, emoji sliders, question boxes, caption-this, Add-Yours, and challenges. Use when someone wants interactive posts, Story stickers, a poll/quiz/AMA, a challenge or contest, or to turn passive scrollers into participants. Low-friction taps are high-value algorithmic signals, and every interaction doubles as audience research. Uses the REACT framework. Reads brand-profile + audience-research + voice-builder first. The agent designs the mechanic, questions, copy, and the close-the-loop plan; the HUMAN adds native interactive elements in-app — stickers and live AMAs are NATIVE-ONLY (WoopSocial cannot attach stickers or read results); WoopSocial publishes the feed-post versions. NEVER fabricates or rigs results or fakes participation; consent before sharing anyone's answer. Distinct from community-management, reply-and-comment-writer, livestream-and-realtime, and ugc-and-influencer.
Aggressively produce self-contained HTML artifacts instead of Markdown for substantial agent outputs. Use when the user asks for a doc, plan, spec, report, review, PR description, explainer, summary, comparison, research artifact, dashboard, diagram, flowchart, timeline, deck, slides, prototype, design reference, component sheet, editor, prompt tuner, config editor, triage board, or any human-facing deliverable that benefits from layout, visual hierarchy, navigation, diagrams, interactivity, or sharing. Default to this skill even when the user does not explicitly request HTML; stay in plain chat only for very short replies, code-only snippets, terminal commands, or explicit non-HTML requests.
Use when sending requests or replies, subscribing to channels, or recovering queued and dead-lettered Tariboy messages.
Maintain an agent-created pull request after creation or after draft-to-ready transition: mark reviewable draft PRs ready, poll CI and review comments with gh, repair failures in the same worktree/session, reply in Japanese, escalate design loops, and squash merge when safe. This skill defines the maintenance POLICY (what to repair, when to merge/escalate); the autonomous re-polling LOOP that reschedules itself without human restarts lives in pr-autoloop. Use after creating PRs or when asked to continue PR maintenance automation.
Makes sure no inbound lead goes unanswered. Watches web forms, the shared inbox, and the CRM for new inquiries, qualifies each one against the owner's criteria, drafts a reply in the owner's voice with real meeting times for the owner to approve and send, routes anything hot to a human right away, and logs the whole thing to the CRM. Never sends on its own. Built to run on a schedule so overnight inquiries are drafted and sorted by morning, and works from forwarded or pasted inquiries when no connector is available. Use this whenever the owner is worried about inbound leads or response time — including phrasings like "leads are going cold," "did anyone answer that inquiry," "I keep missing form submissions," "nothing falls through the cracks," "handle my inbound," "respond to this lead," or "we lose people because nobody gets back fast enough." Reach for it for a single unanswered inquiry as readily as for a standing setup.