Productivity

omonuj Skill

Diagnose rollout regressions and tune difficulty for the oncall-schedule-coverage-collapse task (<TASK_ID>). Keeps avg rollout score < <TARGET_MEAN> with both subscores varying and decorrelated (coverage_restored vs monitoring_governance share the drift surface), and never weakens the hidden <metadata-key> / gap-rule variance gates. Picks the smallest safe lever for the observed symptom.

omonuj Skill

Fetches and interprets validation logs (No-Op and Oracle) for the variation-istio-split-brain task (<TASK_ID>). Maps observed log patterns to root causes and the smallest safe fix. Use after a validation fails to understand why it failed before editing anything.

omonuj Skill

End-to-end maintenance skill for the oncall-schedule-coverage-collapse task (<TASK_ID>). Owns the pre-push safety checks, local quality/anatomy gates, push, Oracle validation handoff, and rollout monitoring. Primary goal is to keep avg rollout score < <TARGET_MEAN> with healthy, decorrelated variance across both subscores. Calls oncall-validation-debugger when Oracle fails and oncall-score-tuner when rollouts regress.

omonuj Skill

Fetches and interprets validation logs (No-Op and Oracle) for the oncall-schedule-coverage-collapse task (<TASK_ID>). Maps observed log patterns to root causes and the smallest safe fix. Use after a validation fails to understand why it failed before editing anything.

rcarmo Skill

Fetch the current user profile, manager, or quick calendar windows.

rcarmo Skill

Run targeted Microsoft Graph queries across mail, calendar, users, and files.

rcarmo Skill

Define, render, inject, and verify project architecture diagrams from JSON graph files.

stardustai Bundle

Use for reviewing an incoming mail card, resolving the complete message or thread, inspecting attachments and links, checking whether a reply already exists, and drafting or sending an authorized reply. Use ceo-document-review for a standalone material review outside the mail workflow. Load dingtalk-mail before any DingTalk mail operation.

stardustai Bundle

Use for meeting minutes, transcripts, silent meetings, preparation materials, summaries, decisions, and action items. Use ceo-calendar-invite for attendance decisions and ceo-work-tracking when an agreed action becomes tracked work. Load dingtalk-minutes before reading DingTalk meeting records.

stardustai Bundle

Guided first-run workflow for importing a user's existing work context into Friday Memory from local files, DingTalk documents/wiki, DingTalk AI minutes, and selected DingTalk data through dws. Use when the user wants to initialize Memory, connect work context, import DingTalk knowledge, seed Memory from documents or meetings, or prepare Memory for daily work.

stardustai Bundle

Use when a message, meeting, or decision creates trackable work that needs extraction, assignment, project or TODO creation, follow-up, completion evidence, or closure. Use ceo-message-triage when no durable work item is needed and ceo-meeting-work for meeting synthesis before actions are confirmed. Load the relevant task operation Skill before changing tracked work.

stardustai Bundle

Use for deciding whether an incoming DingTalk message needs a reply, reaction, clarification, handoff, or no action. Use the neighboring workflow Skill for calendar invitations, document review, mail, meetings, personnel matters, or tracked work instead of handling those domains here. Load dingtalk-chat before reading context or sending a chat action.

stardustai Bundle

Use for incoming DingTalk calendar invitations, calendar cards, meeting invitations, attendance decisions, schedule conflicts, tentative, accept, or decline responses, and questions about why the principal should attend or what input is expected. Use ceo-meeting-work for meeting content after attendance is settled. Load dingtalk-calendar before issuing any DWS calendar command.

stardustai Bundle

Use this skill for Stardust/FundFlow investor meeting preparation, investor style analysis, post-meeting transcript review, follow-up recommendations, and DingTalk financing-group updates. Trigger whenever the user mentions 融资会议, 投资人会议, 会前准备, 会后总结, 投资人问题, 投资人风格, 融管通, FundFlow, NDA, DataPack, 资料室, demo口径, or asks to send financing meeting insights to 融资支持群/融资群/Friday群.

janszewczyk Bundle

Use this skill to create typed test data builders with mimicry-js and Faker for any TypeScript interface or type. Invoke whenever the user asks to generate mock data, create test fixtures, build factory functions, produce seed data, or construct fake objects for unit tests, Storybook stories, or E2E scenarios. Also use when migrating from test-data-bot or Fishery to mimicry-js, or when the user mentions builders, factories, or typed mock/fake/test/seed data generation — even if they describe the task indirectly (e.g. "I need realistic invoices for testing" or "generate sample users for my stories").

janszewczyk Skill

Creates a Git branch for the work at hand, named `<type>/<english-kebab-case-description>` using Conventional Commits types as prefixes. Works with no arguments — it derives the name from the current session and the uncommitted changes; an argument is a hint that shapes the name, never literal text. On `main`/`master` it fetches and branches from the remote's real default branch; on an existing working branch it branches from HEAD so stacked work keeps its base. Never pushes, never leaves you committing on the default branch. Use when starting a new piece of work, or when you notice changes are being made directly on the default branch. Trigger on "create a branch", "start a new branch", "branch for this", "new feature branch", "I should be on a branch for this", "stwórz brancha", "zrób nowego brancha", "nowa gałąź", "przełącz na brancha dla tej zmiany".

janszewczyk Skill

Create Commit

janszewczyk Skill

Create Pull Request

darkroomengineering Bundle

Turn proven session behavior into a skill, rule, profile, AGENTS.md diff, or team learning; artifacts seed /autoresearch evals. Triggers "harvest this workflow", "turn this session into a skill", "preserve this behavior".

darkroomengineering Skill

Save or restore a mid-task rollback point before a risky refactor, migration, or destructive edit. Triggers "checkpoint", "snapshot", "rollback to", "list checkpoints". End-of-session saves go to /handoff.

darkroomengineering Skill

Coordinate agents across plan, implement, test, and review, or fan out 3+ independent workstreams. Triggers "orchestrate", "parallel agents", "fan out", "split work", "overnight", "autonomous task".

nubjs Skill

Manages the repo's supply-chain soak window (SOAK_DAYS) — checks and fixes the derived surfaces, bumps or disables the window, adds dated per-package exclusions, and bumps pinned external tools. Use when a task touches minimumReleaseAge, min-release-age, min-publish-age, external-tools.json, renovate.json, or taze cooldowns, or when investigating why a freshly published version won't install.

nubjs Skill

Find and diagnose RED CI with the gh CLI — answer "is anything failing?" and "why?" correctly, without being handed a URL. Invoke (via the Skill tool) whenever you need to check whether a branch, commit, or PR is green, whenever someone reports failing CI, before cutting a release, and before claiming any commit is green. THE FAILURE THIS SKILL EXISTS TO PREVENT: `gh run list` reports a RUN-level `conclusion`, and a run whose rollup is `cancelled` can contain a job whose conclusion is `failure` — so filtering runs on `conclusion=="failure"` silently misses real red, and taking the latest run per workflow hides an older failed run on the same SHA. The authoritative instrument is the commit's CHECK-RUNS, which is what the GitHub UI renders. Pairs with `ci-watch` (blocking until a run is terminal) and `ci-adhoc-test` (running a probe on a real OS).

nubjs Skill

Performance-trace Nub package-manager installs using the existing phase timings, structured diagnostics, and sampling-profiler workflow. Use when an install or package-manager operation is unexpectedly slow and the bottleneck needs to be localized before changing code.

cspulse Bundle

Shapes the week around the accounts that move rather than around the calendar that filled itself. Trigger whenever the user says "weekly plan", "plan my week", "how should I spend this week", "my calendar is full", "I have no time for proactive work", "plan Monday", "week ahead", "I am drowning", "everything is reactive", or describes a week where meetings have consumed the time. It starts from what has to be true by Friday, protects one block for the work that has no deadline, batches the reactive load, names the meetings to decline or shorten, and closes the week on what actually moved. Use book-triage first to decide which accounts deserve the time, since that is a different question from how the hours are arranged.

cspulse Bundle

Stress-tests a customer email the user has already drafted and returns a straight verdict plus a tightened version, checked against the source transcript, the account plan and their voice principles rather than in a vacuum. Trigger whenever the user pastes or points at a draft email and asks any of: "is this good", "would you send this", "review this email", "critique this", "tighten this", "make this better", "does this sound right", "too long?", "what would you change", or shares a draft with no instruction at all - a bare draft is a request for a read on it. Also trigger when they say an email "feels off" or ask how a customer will take it. Use this for drafts that already exist; use call-recap when the input is a recording and no draft has been written yet.

cspulse Bundle

Produces a defensible read on whether an account will renew - the decision, the decider, the mechanism, the evidence, the dollars at stake and the play - rather than a colour on a dashboard. Trigger whenever the user asks "will they renew", "is this account at risk", "renewal risk", "churn risk", "should I be worried about this account", "what's the read on", "health check on", or names an account and a renewal date in the same breath. Also trigger when preparing for a forecast call, a risk review, or a QBR on an account whose renewal is inside two quarters. Use business-review when the job is running the meeting; use this when the job is deciding what is true. The skill works from whatever evidence exists and states plainly what it could not check.

cspulse Bundle

Prepares a customer business review that earns the next meeting - the customer's goals first, value proved in their numbers, three to five themes, and an explicit ask - instead of a usage readout nobody asked for. Trigger whenever the user says "QBR", "EBR", "business review", "quarterly review", "exec review", "prep for my customer meeting", "build the deck for", "what should I present to", or names an account and an upcoming review in the same breath. Also trigger when they ask whether they should run a review at all. Use renewal-risk when the job is deciding whether the account will renew; this skill is for the meeting. It will tell the user when a business review is the wrong meeting to run.

cspulse Bundle

Writes the proactive message nobody wants to send: an incident, a delay, a deprecation, a price change, planned maintenance, or a change of CSM. Trigger whenever the user says "customer update", "notify customers", "we need to tell them", "announcement to customers", "we are deprecating", "end of life", "maintenance window", "outage notice", "I am handing over my accounts", "changing CSM", "tell them about the delay", or describes news that has to reach a list of customers rather than one person. It segments by impact rather than by mailing list, leads with what changes for them, says plainly whether action is needed, and writes to survive a forward to their executive and their legal team. Use hard-conversation when the news is going to one account by voice, escalation when something is already on fire, and email-critic once a draft exists.

cspulse Bundle

Produces a renewal and expansion forecast in dollars with a stated confidence, with contraction sized separately and correlated risks named as one bet rather than thirty. Trigger whenever the user says "renewal forecast", "forecast the quarter", "what will we renew", "gross retention forecast", "commit number", "roll up my team's renewals", "forecast call", "what is the risk to the number", or is preparing a retention number for finance or a board. It sets evidence-based entry criteria for each category, separates timing slip from loss, pulls auto-renewals out of the judgement pool, and tracks per-forecaster accuracy so the number stops being a personality test. Use renewal-risk for the read on any single account, and portfolio-review for the meeting where the reads get challenged.

rockclaver Skill

Convert a phased plan into GitHub issues, a CI workflow, and a PR template mapping PRs to criteria. Use when user wants to create issues from a plan, push phases to GitHub, set up acceptance-criteria CI, or track plan phases.

rockclaver Skill

Design and build durable workflow engines — state machines, saga orchestration, durable execution, timers, versioning, and worker concurrency. Use when building a workflow runtime, orchestrator, saga engine, or long-running job system.

stephenrogan Bundle

Synthesizes team health signals from surveys, 1:1 themes, meeting behaviour, workload, attrition indicators, and execution patterns into risks and interventions. Use when morale, trust, psychological safety, workload, or team cohesion may be drifting.

stephenrogan Bundle

Designs a staff or team meeting that prioritizes decisions, risks, and alignment over status reporting. Use when preparing recurring leadership meetings, team meetings, operating reviews, or when a meeting needs to be cut, redesigned, or made decision-oriented.

stephenrogan Bundle

Turns strategy into an operating system with priorities, bets, decision calendar, metrics, operating cadence, owner map, risks, and kill criteria. Use for quarterly planning, annual planning, strategic resets, or converting executive direction into management rhythm.

yamcodes Bundle

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.