Product & Planning

amit-t Bundle

Approve a reviewed PRD — updates status, copies to approved inbox, and updates PRD-PIPELINE.md. Run only after /prd-review-panel is complete and you are satisfied with the output.

amit-t Bundle

Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when the user wants to break a PRD into an implementation plan, or mentions "tracer bullets".

amit-t Bundle

Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when the user wants to write a PRD or plan a new feature.

amit-t Bundle

Run the full UXD workflow end-to-end for an approved PRD — design interview → user flow → wireframes → design system → hi-fi screens → design review → developer handoff → approve. Reads approved PRDs from pm-os automatically.

amit-t 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" or for a "two-axis review".

amit-t Bundle

Run a 7-perspective multi-agent PRD review (Engineering, Design, Executive, Legal, UXR, Skeptic, Customer Voice) that catches gaps and surfaces conflicts before stakeholder review. Use when the user wants a PRD reviewed, asks for panel or multi-agent feedback, or runs /prd-review-panel.

amit-t Bundle

Reformat a status update so leadership remembers you positively. Turn raw notes into outcome-first, three-sentence updates with a clear ask. Use when the user wants to give an update to a manager, exec, or stakeholder, mentions a "status update", "leadership update", "exec update", or pastes raw notes about what they've been working on.

ragnarpitla Skill

A structured interview that pins down what you are actually building before you build it.

ragnarpitla Bundle

Establish whether an agent actually works, and whether it still works, using a recorded eval set rather than ad hoc chats. Use when an agent is about to ship and the only testing was somebody typing a few questions into the test pane, when an agent that used to answer correctly now does not and nobody can say when it broke, when a knowledge source or model version changed and you need to know what it affected, when a stakeholder asks how accurate it is and there is no number to give them, when you cannot decide what "correct" even means for a generative answer, or when the agent works for the builder and fails for a user with different permissions. For a one-off read of a single agent's configuration, review-copilot-studio-agent is the better fit; this one is about measurement over time.

ragnarpitla Skill

Set up the signals that tell you an agent is healthy, being used and starting to misbehave before a user has to report it. Use when an agent has shipped with no dashboard, alert or usage number behind it, when you cannot say how many sessions escalated to a human last week, when latency or error rates need to be watched continuously rather than sampled by hand, when Application Insights or Foundry tracing needs to be wired up for an agent, or when a stakeholder asks for a usage report and the only source is memory.

ragnarpitla Skill

Work out whether an agent's message capacity, quota or spend is sized correctly, before a limit gets hit or a bill surprises someone. Use when a Copilot Studio agent is close to its message capacity or credit allocation, when Foundry model quota or token spend needs to be forecast for a launch, when a finance stakeholder asks what an agent costs and nobody can answer in real numbers, when pay-as-you-go and prepaid credits need to be reconciled, or when usage is growing and nobody has planned for what happens at ten times the current volume.

vinhnxv Bundle

Test orchestration pipeline for arc Phase 7.7 — 4-tier testing (unit, property-based, integration, E2E/browser) with diff-scoped discovery and structured reporting. Extended tier covers contract validation, visual regression, design tokens, a11y, test history, and flaky detection. Auto-loaded by the arc orchestrator during the test phase. Keywords: testing, test pipeline, unit test, integration, E2E, PBT, property-based, fast-check, hypothesis, proptest, visual regression, design token, accessibility, flaky test, contract validation.

dragoon0x Skill

Explain the same design observation to a designer, a developer, and a non-technical stakeholder. Same insight, three languages. Use when working cross-functionally or presenting design decisions to mixed audiences.

jpoindexter Skill

Use when a backlog, nav menu, settings screen, tag system, or taxonomy is ordered alphabetically or by inherited default; when a hierarchy runs past 2 levels and users call it complicated; when checklist items were chosen without asking what was excluded; when a style sheet or linter fights a list's spacing; when pros/cons or comparisons need a 2-D array; or when a list of nouns is hiding agency that verbs would show.

jpoindexter Skill

Use when a slide deck is scheduled for a decision meeting, design review, PRD review, or briefing; when planning a meeting's time budget, agenda, or pre-read; when pre-reads go out by email and nobody reads them; when a talk to a large audience needs a handout; when you are the low-power party who keeps getting interrupted; or when choosing between presenting a thing and circulating a document about it.

christopheralphonse Skill

Generates tasks by analyzing the PRD and breaking it into actionable work items.

alihusains Skill

Assembles a proposal or RFP response around explicit win themes tied to the buyer's stated evaluation criteria, with a compliance matrix, an evidence-sourced claim register, a named answer owner per requirement, and a go/no-go decision before writing starts. Use when responding to an RFP, RFI, ITT, or tender, or when writing a solution proposal after discovery; trigger on 'respond to this RFP', 'write the proposal', 'bid/no-bid', 'tender response', 'put together a quote and scope for X'. Not for preparing the discovery meeting that produces the inputs (use sales-discovery-preparation), not for evaluating an incoming vendor's bid — that is the buy side (use operations-vendor-evaluation) — and not for substantiating individual claims in isolation (use marketing-claim-substantiation).

alihusains Skill

Writes a PRD that states the problem with evidence, an explicit and enforced non-goals list, the decisions already made with their rationale, the open questions with owners and due dates, and the launch and rollback criteria. Use when a feature or product change needs a written requirements document before build; trigger on 'write a PRD', 'spec this feature', 'product requirements for X', 'what are we actually building', 'we need a one-pager before engineering starts'. Not for breaking an agreed PRD into implementable stories (use product-user-story-acceptance-criteria), not for communicating timeline commitments outward (use product-roadmap-communication), and not for system or interface design decisions (use engineering-decision-record).

alihusains Skill

Prepares a discovery call from real account research: builds an evidence-backed account picture, forms falsifiable hypotheses about the buyer's problem, writes a question plan that tests them, and sets the qualification and next-step criteria before the call. Use when preparing for a first or follow-up discovery meeting with a prospect or existing customer; trigger on 'prep me for this call', 'discovery call with X', 'research this account', 'what should I ask them', 'meeting with a prospect tomorrow'. Not for building the proposal or RFP response after discovery (use sales-proposal-assembly), not for market-level campaign audience work (use marketing-campaign-brief), and not for writing the standing sales process itself (use operations-sop-authoring).

alihusains Skill

Writes a campaign brief that survives review — required fields, a single measurable primary objective, the audience-evidence check, and the named approval gate before any asset is produced. Use when someone asks to brief a campaign, launch, promotion, always-on channel push, or event marketing programme; trigger on 'write a campaign brief', 'brief the agency', 'we need a campaign for X', 'kick off the launch marketing'. Not for reviewing claims already written into copy (use marketing-claim-substantiation), not for organic search briefs (use marketing-seo-content-brief), and not for the product launch decision itself (use product-roadmap-communication).

alihusains Skill

Communicates a roadmap with commitment level attached to every item — committed, planned, or exploratory — using date precision that matches actual confidence, and a change-notification rule for when an item slips or is dropped. Use when preparing a roadmap update, a stakeholder or customer-facing plan, or an internal delivery outlook; trigger on 'roadmap update', 'what are we shipping this quarter', 'share the plan with the customer', 'stakeholders want dates', 'when will X be delivered'. Not for defining what a specific item is (use product-requirements-doc), not for breaking items into stories (use product-user-story-acceptance-criteria), and not for a commercial promise inside a contract or bid (use sales-proposal-assembly with your legal owner).

alihusains Skill

The pre-publication check for any report, dashboard, or number going to decision-makers: freshness, completeness, reconciliation to an independent source, segment additivity, period-over-period sanity, and a statement of what the numbers cannot support. Use before a report ships, when a figure looks surprising, when a dashboard has quietly stopped updating, or when a stakeholder asks whether a number can be trusted. Trigger on 'check this report before I send it', 'does this number look right', 'sanity check these figures', 'the dashboard looks off', 'can we trust this number', 'QA the deck numbers'. Not for settling what a metric means when two teams disagree — that is data-analytics-metric-definition; not for reviewing query correctness and cost, which is data-analytics-sql-review.

alihusains Skill

Produces a recurring project or programme status that survives a steering group: a RAG rating with stated criteria rather than sentiment, an explicit diff against the last report, decisions needed FROM the reader each with an owner and a date, and the rule that a status green for six consecutive weeks is not a status. Use when assembling a weekly or monthly update from systems of record, when a status is written but reads as reassurance, or when a project went from green to red with nothing in between. Trigger on 'write the status report', 'weekly project update', 'steerco update', 'what do I tell the steering group', 'RAG status', 'update on the programme'. Not for the post-hoc analysis of something that already failed (use engineering-incident-postmortem), not for communicating a roadmap to a broad audience (use product-roadmap-communication), and not for a board pack where decision rights and options analysis are the substance (use executive-board-pack-preparation).

alihusains Skill

Splits requirements into vertically sliced user stories and writes acceptance criteria a tester could execute without asking the author a question — observable, bounded, and covering the negative and edge paths, not just the happy path. Use when turning a PRD, epic, or feature request into backlog items, or when a story is rejected as unclear or untestable; trigger on 'write user stories', 'break this epic down', 'acceptance criteria for X', 'this ticket isn't clear enough', 'refine the backlog'. Not for authoring the requirements document itself (use product-requirements-doc), not for stakeholder-facing timelines (use product-roadmap-communication), and not for writing the test automation (that is an engineering task).

omicverse Bundle

Convert OmicVerse single-cell preprocessing and marker-discovery notebooks into a reusable, triggerable skill. Use when cleaning AnnData, choosing a preprocessing mode, building PCA and neighborhood graphs, clustering with Leiden, or extracting marker genes with OmicVerse.

omicverse Bundle

Monocle2-style single-cell trajectory analysis on AnnData via the `ov.single.Monocle` class - DDRTree pseudotime + branch detection + per-gene differential test + BEAM branch-dependent gene discovery, plus the unified `ov.pl.trajectory` / `ov.pl.trajectory_overlay` / `ov.pl.trajectory_tree` plotters and the shared pseudotime visualisations (`branch_streamplot`, `dynamic_heatmap`, `dynamic_trends`). Use when fitting a Monocle2 trajectory on an annotated AnnData, when deriving branch-aware gene trends with `dynamic_features`, or when reproducing `t_traj_monocle2`.

omicverse Bundle

OmicVerse Single-Cell NMF / cNMF Program Discovery

harshanandak Bundle

Forge kernel data portability — getting issue data in and out of the local kernel. `forge export [--dir] [--dry-run]` writes the kernel backlog to deterministic git-tracked JSONL (D16 portability projection); `forge export --import` reads that committed snapshot back into the kernel (hydrate). `forge migrate --from beads [--dry-run] [--source <dir>]` imports a Beads issue store into the kernel — the onboarding path for users coming from Beads. Use when the user says "export the kernel backlog to JSONL", "back up / snapshot the backlog", "re-import / hydrate the backlog", "migrate from beads", or "import a beads store". Honesty: bare `forge migrate --dry-run` (no `--from`) is v2→v3 preview only; a re-import that applies nothing reports "already hydrated". NOT the cloud/backend sync of the kernel (that is `forge sync`, cloud-native), NOT a database/schema migration (plan/dev), NOT memory notes (memory), NOT syncing a git branch with main (ship).

harshanandak Bundle

Everyday single-issue CRUD over the `forge issue` verbs: create/update/show/list/search/close/reopen/comment, set priority/labels/assignee, claim or release one issue, add/remove dependency edges, plus backlog `stats`. Use for ANY routine one-off issue op: "create an issue/bug/task for X", "update/edit issue <id>", "close or reopen this issue", "comment a handoff note on <id>", "list/filter open bugs by status/label/priority", "bump this to P1", "reassign to alice", "mark <id> blocked by <id>". Also the parity floor migrating off a Beads-style tracker (label/reopen/delete map to forge equivalents). Single-operation plumbing only. Does NOT choose, rank, or explain the next issue to work on or why it's blocked (use triage-ready); does NOT run claim-then-prove-lease-ownership safety (use claim-safety); does NOT drive an issue through the plan->dev->validate->ship pipeline or open a PR (use smith or stage skills); does NOT report the current stage or what's in flight (use status).

gtrabanco Skill

Audit cross-document coherence: docs ↔ roadmap ↔ code ↔ fix index ↔ issues. Finds drift — features in docs/ not in the roadmap (or vice versa), fix-index entries already merged/closed, broken documentation-map links, dependency cycles, artifacts in the wrong language, naming-convention violations — and reports them ranked by severity, fixing only low-risk items on request. On Claude Code and want hand-tuned per-skill model/effort tiers? Install the `#claude` branch instead (`npx skills add gtrabanco/agentic-workflow#claude`) — see the README. This branch is model-agnostic: the skill inherits whatever model and effort your agent session is already using. Triggers: "check doc consistency", "are the docs in sync", "audit the docs", "doc coherence review", "did the docs drift", "validate the roadmap".

gtrabanco Bundle

Route designed features or issues into engineering planning and roadmap registration; undesigned work stops at design-feature. Supports `--next`, `--from-issue`, and `--scaffold`. Triggers: "plan-feature", "plan a feature", "plan the next roadmap feature", "create SPEC and TASKS".

aws-samples Skill

Run the AI-DLC `practices-discovery` stage (inception phase) in isolation, without advancing the main workflow. Packages `/aidlc --stage practices-discovery --single`: the engine emits one run-stage directive for practices-discovery and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.

buildgreatproducts Skill

Use in the app repo — the repository that contains `productos/` — when the user wants the full MVP built from their ProductOS spec documents. Triggers on phrases like "build my MVP", "build the app", "execute the roadmap", "start the build", "work through the whole roadmap", "build everything", or any request to implement the entire plan rather than a single task or phase. Requires `docs/PRD.md` and `docs/ROADMAP.md` (plus `docs/PRODUCT.md` and `docs/DESIGN.md` for context). Works through every roadmap task in order — implementing, testing, and verifying each before moving on, marking checkboxes and updating the status line, committing at each phase boundary — and runs until all tasks are complete and the magic moment works end to end.

buildgreatproducts Skill

Use when the user has a finished `docs/PRODUCT.md` and `docs/DESIGN.md` and is ready to scope their MVP and generate the two documents a coding agent builds from — `docs/PRD.md` (technical spec) and `docs/ROADMAP.md` (phased build plan with task checkboxes). Triggers on phrases like "create my PRD", "generate my roadmap", "scope my MVP", "what should my MVP be", "turn my product docs into a build plan", "start the develop phase", "I'm ready to build", or any request to translate Define and Design outputs into implementation-ready spec documents. Reads the Define docs, Magic Moment, Onboarding Flow, and Landing Page or App Store Listing, runs a structured MVP scoping interview in the voice of a senior technical product lead — core loop, feature cuts, tech stack selection — then generates both documents per the guides in `productos/develop/guides/`. Especially appropriate as the first step in a ProductOS-style Develop workflow.

buildgreatproducts Skill

Use inside an **existing app codebase** when the user wants a plan to bring the code in line with their ProductOS spec documents. Triggers on phrases like "create a refactor plan", "audit my codebase against the PRD", "plan the refactor", "what's different between my app and the PRD", "make REFACTOR.md", or any request to compare an existing codebase to `docs/PRD.md` and produce an actionable migration plan. Reads `docs/PRD.md` and `docs/ROADMAP.md` when they exist; when they don't, generates its own refactor-scoped PRD from `docs/PRODUCT.md`, `docs/DESIGN.md`, the codebase, and a short interview — no need to run `studio-develop-prd-roadmap` first. Audits the codebase, classifies every difference (missing / divergent / extra), walks the user through keep-or-remove decisions one at a time, then writes `docs/REFACTOR.md` — a phased, checkbox-tracked plan in the same format as the roadmap, executable by `studio-develop-refactor-build`.

buildgreatproducts Skill

Use in the app repo — the repository that contains `productos/` — when `docs/REFACTOR.md` exists (generated by `studio-develop-refactor-plan`) and the user wants the refactor executed. Triggers on phrases like "run the refactor", "execute the refactor plan", "work through REFACTOR.md", "start refactoring", "apply the refactor plan", or any request to carry out the planned refactor task by task. Works through every task in `docs/REFACTOR.md` in order — implementing, testing, and verifying each before moving on, marking checkboxes and updating the status line, committing at each phase boundary — and runs until all tasks are complete and the codebase is fully aligned with `docs/PRD.md`.