Productivity

carlvellotti Skill

Draft follow-up messages from meeting outcomes, then automatically clean them of AI writing patterns. Chains the draft-followups and humanizer skills into one step. Use when the user says 'draft and humanize', 'write and clean followups', or 'polished followups'.

carlvellotti Skill

Process meeting transcripts and extract action items with intelligent borderline-item handling. Instead of guessing on ambiguous items, collects them and asks the user which are real commitments. Use when the user says 'process meetings plus', 'process meetings', 'meeting notes', 'meeting action items', or provides meeting transcript files to process.

mattwoodco Skill

Create a project spec from an idea using the full brainstorming design workflow, then output a no-frills spec for Ralph loops and add-project. Use when the user says "spec a project", "create a spec", "spec this idea", "plan a project", "write a spec", or when add-project delegates Phase 1 spec generation. Runs brainstorming first (clarify → approaches → design approval → design doc), then writes docs/specs/{name}.md with mission, features, flows, screens, and skills mapping.

mattwoodco Skill

Task extraction and management — the AI creates structured tasks from conversation, persisted to Postgres with a task list UI panel. Use this skill when the user says "add tasks", "task management", "todo list", "extract tasks", or "ai tasks".

mattwoodco Skill

Server-side room recording with LiveKit Egress — composite and track-based recording, S3 storage, recording metadata in Postgres. Use this skill when the user says "add recording", "record room", "record video", "record meeting", "egress recording", or "save recording".

willoscar Bundle

Project completed stage Artifacts into a concise human-review block in `DECISIONS.md`; use before a Workflow checkpoint, not for Workflow routing or approval.

willoscar Bundle

Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose.

jasoncolapietro Bundle

Suede-owned lifecycle email design for welcome, onboarding, nurture, re-engagement, post-purchase, and trigger-based sequences. Use when the user needs a multi-email flow with entry criteria, cadence, message roles, and a measurement plan — drip campaigns, welcome series, win-back flows, or trigger-based automations. NOT FOR: cold prospecting (use suede-cold-email), SMS as part of the same lifecycle program (use suede-sms), in-product activation flows (use suede-onboarding), or lifecycle-stage operations beyond email (use suede-revops).

elihuvillaraus Skill

Save progress, decisions, learnings, and next steps to persistent memory before a context compact (manual /compact or auto-compact) or at any natural session boundary — using ONE fixed template and a clear decision tree for where to write it, instead of improvising a different format every time. Trigger on "/guardado", "prepare for compact", "save your progress", "guarda el progreso", "prepara memoria persistente antes del compact", "deja todo listo para continuar", "antes de compactar", "save your learnings and next steps so we can continue later" — or run it proactively right before you invoke /compact yourself. Named `guardado`, not `checkpoint` — Claude Code has its own built-in `/checkpoint` CLI command that the Skill tool cannot invoke, and not `memory` or `session-checkpoint` either, both already taken/renamed-from. Don't rename this back to any of those three.

jasoncolapietro Bundle

Suede Labs AI CI and branch-protection wiring for any repo and any stack: path-aware jobs, a single aggregator required check that cannot deadlock, lockfile hygiene, runtime pinning from the repo, and the exact branch-protection settings. Use when asked to set up CI, protect main, make CI block a bad merge, fix a required check that hangs pending forever, or repair duplicate or misfiring pipelines. Detects the repo's real apps, package managers, and runtime versions first; emits workflow files and settings, never pushes or flips protection itself. NOT FOR: reviewing or grading the change the gate is failing on (use suede-code); designing the AI eval cases to wire in (use suede-ai-eval); branch and worktree hygiene (a private Suede Labs companion, not in this pack).

jasoncolapietro Bundle

Suede-owned B2B cold-email discipline for evidence-based personalization, subject lines, opening lines, concise bodies, one clear CTA, and bounded follow-up sequences. Use when writing or repairing outbound email to qualified prospects. NOT FOR: building or qualifying the prospect list (use suede-prospecting), lifecycle or nurture email (use suede-emails), or broader sales collateral (use suede-sales-enablement).

jasoncolapietro Bundle

Suede-affiliated onboarding and activation strategy for first-run sequencing, empty states, setup checklists, activation milestones, time to value, and retention-linked measurement. Use when users sign up but fail to reach first value or the product needs a new first-session flow. NOT FOR: registration optimization (use suede-signup), lifecycle email sequences (use suede-emails), or monetization prompts (use suede-paywalls).

jasoncolapietro Bundle

Suede-owned prospecting and qualification discipline. Use when defining an ICP, sourcing and enriching a bounded lead list, finding early adopters or design partners, scoring account fit, or documenting disqualification evidence. NOT FOR: sending outreach (use suede-cold-email), changing CRM routing (use suede-revops), or profiling competitors instead of prospects (use suede-competitor-profiling).

mattwoodco Skill

Real-time and batch speech-to-text via Deepgram — live transcript overlay for video rooms, post-meeting full transcript with search, speaker labels, and Postgres persistence. Use this skill when the user says "add transcription", "setup speech to text", "add captions", "transcribe audio", or "setup transcription".

mattwoodco Skill

Platform-specific copy preview cards — tweet, Instagram caption, LinkedIn post, and email subject line mockups for previewing AI-generated copy in context. Use this skill when the user says "add copy preview", "platform preview", "social preview cards", "tweet preview", or "caption preview".

mattwoodco Skill

AI-powered meeting notes — generates executive summaries, key decisions, action items, and timestamped timelines from transcripts using structured output. Use this skill when the user says "add meeting notes", "setup ai meeting notes", "meeting summary", "extract action items", or "ai meeting notes".

wpank Bundle

PostgreSQL-based job queue with priority scheduling, batch claiming, and progress tracking. Use when building job queues without external dependencies. Triggers on PostgreSQL job queue, background jobs, task queue, priority queue, SKIP LOCKED.

taewook486 Skill

Test-Driven Development workflow. Use for ALL code changes - features, bug fixes, refactoring. TDD is non-negotiable.

taewook486 Skill

Delegate to OpenAI Codex CLI when: (1) user explicitly requests it (codex에게 맡겨줘, codex로 해줘, 외주화해줘, codex 실행해줘, codex 리뷰 돌려줘), OR (2) the task requires autonomous repo-scale execution — writing multiple test files, file-level refactoring across many files, bulk edits (type hints, formatting, comments across a directory), or code review with a clear done condition. Do NOT delegate: design/architecture decisions, small edits (under ~20 lines), explanation-only requests, or tasks where Claude needs to reason about context first.

taewook486 Skill

Update worklog files by moving tasks between todo/doing/done states. Use when recording task progress, starting new work, or marking tasks complete. Requires explicit arguments: worklog [done|doing|todo] [description].

elihuvillaraus Skill

Indexes all available skills in the current project and stores them in Engram for lazy loading. Any subagent can then search for the right skill before executing a task instead of loading all skills upfront. Run once per project setup, then again when skills change. Triggered by: 'index skills', 'skill registry', 'register skills', 'update skill index', '/skill-registry'.

taewook486 Skill

Suggest the next task to work on based on current Phase and worklog state. Use when you want to know what to do next in the project.

taewook486 Bundle

Test-Driven Development workflow specialist using RED-GREEN-REFACTOR cycle for test-first software development. Use when developing new features from scratch, creating isolated modules, or when behavior specification drives implementation. Do NOT use for refactoring existing code (use moai-workflow-ddd instead) or when behavior preservation is the primary goal.

jasoncolapietro Bundle

Suede-owned sales-enablement discipline. Use when creating pitch decks, one-pagers, objection guides, demo scripts, talk tracks, battle cards, proposal structures, buyer cards, or deal-level ROI framing. NOT FOR: setting price or terms (use suede-pricing), building the offer (use suede-offers), sending outreach (use suede-cold-email), or publishing unsupported proof.

trpc-group Skill

Use this workflow recipe when a draft, plan, proposal, or other deliverable should be independently reviewed and revised until it satisfies explicit quality criteria.

trpc-group Skill

Use this workflow recipe when a question benefits from several independent perspectives followed by a single evidence-based synthesis.

bradtaylorsf Skill

Intelligent workflow orchestrator that commits, pushes, and creates/updates PRs automatically. Use when user wants to save their work or create a PR.

brite-nites Bundle

Creates an isolated git worktree for task execution. Activates when starting work on a planned issue — sets up a new branch with Linear issue ID, runs project setup, and verifies a clean test baseline before coding begins.

brite-nites Bundle

Breaks work into bite-sized tasks before coding. Activates when a multi-step task needs planning — creates tasks small enough for a junior developer to follow (2-5 minutes each), with exact file paths, complete implementation details, and verification steps. References Linear issue context and project-specific test commands from CLAUDE.md.

brite-nites Bundle

Executes a structured plan using subagent-per-task with TDD enforcement. Activates when given an approved plan to implement — launches fresh subagents for each task, enforces red-green-refactor, runs two-stage review per task, and checkpoints between tasks. Parallelizes independent tasks.

brite-nites Skill

Runs the full post-plan workflow. Refine plan, create Linear issues, setup CLAUDE.md. Use after /plan-project produces a v1 plan. Pauses between phases for optional review.

cuioss Skill

Domain-agnostic task planning from deliverables with skill resolution and optimization

cuioss Bundle

PR review response workflow - fetch comments, triage, and respond to review feedback

cuioss Bundle

Git commit workflow with conventional commits, artifact cleanup, and optional push/PR creation

cuioss Bundle

Generic file I/O operations for plan directories

cuioss Bundle

Execute phase skill for plan management. DUMB TASK RUNNER that executes tasks from TASK-*.toon files sequentially for execute and finalize phases.