Product & Planning

guilherme-braga4 Bundle

Execute a preflighted, approved PRD and roadmap iteratively, planning one phase at a time, implementing, reviewing, and validating the running product through its UI, APIs, database, and tests. Use to start or resume execution with an agreed scope and review policy; route unresolved preparation to roadmap-executor-pre-check-deps.

guilherme-braga4 Bundle

Gera ou evolui PRDs a partir de Discovery, usando o modelo de Produto do usuário: atores, RNs imutáveis, UCs observáveis, RFs MoSCoW, qualidades humanas e mudanças rastreáveis. Use para transformar discovery, entrevistas, AS-IS e decisões em requisitos verificáveis, iniciar uma iniciativa ou definir uma nova frente de produto. Não substitui discovery sem fontes, desenho de arquitetura, plano de código ou auditoria de prontidão.

guilherme-braga4 Bundle

Coordena entregas de código da Valeti entre ROADMAP, TASKPLAN, Jira via Rovo MCP e branches do Bitbucket. Use antes de implementar, corrigir ou retomar código da Valeti e ao reconciliar o estado final dos cards do usuário. Não cria cards como efeito de uma auditoria ou planejamento somente leitura, nem impõe o processo a projetos de outras organizações.

guilherme-braga4 Bundle

Transforma uma avaliação de Product Engineering Readiness em snapshot datado de arquitetura: AS-IS da base avaliada, TO-BE para atender ao PRD, relatório de mudanças e matriz Produto ↔ Engenharia ↔ validação. Use após Readiness ou para atualizar ARCHs e preparar aprovação do desenvolvimento com base nessa avaliação. Resolve conflitos PRD ↔ ARCH em Plan mode, questão por questão. Não substitui o Readiness nem executa implementação durante a análise.

guilherme-braga4 Bundle

Understand a project's current engineering context from docs/ and code, then shape or review high-level solution architecture, decisions, and trade-offs. Use for architecture discovery, product-to-engineering alignment, system design, and technical planning; do not use for isolated low-level coding tasks.

ivelten Skill

Entry point and roadmap for any Haskell development work. Use this skill whenever the user mentions Haskell, cabal, GHC, GHCi, HLS, GHCup, mise, Hackage, `.hs`/`.cabal`/`mise.toml`/`.tool-versions` files, or otherwise begins a Haskell-related task — even when no specific sub-topic is yet active. Loads the map of focused haskell-* sub-skills (project setup, devcontainer, native mise+GHCup toolchain, type design, domain errors, effectful, database, json, logging, testing, documentation, benchmarking, quality gates, debugging) plus the cross-cutting defaults that hold across all of them. Acts as the orientation layer so the specific sub-skills don't each need to win a trigger battle on their own.

kwhi6693-web Bundle

Use when a presentation needs single-file HTML delivery, browser-native slides, visual style discovery, responsive 16:9 staging, keyboard navigation, PPTX content extraction, or HTML-to-PDF export.

ivelten Skill

Set up and write Haskell tests with `hspec`, `QuickCheck`, and `hspec-discover`. Covers the test-suite cabal stanza, auto-discovery, per-module spec layout, property tests, `Arbitrary` instance placement, in-memory effect interpreters, and colored/specdoc output (locally and in CI). Use when adding tests, configuring the test runner, deciding between unit and property tests, or making test output more readable.

ftrout Bundle

Plan and run a purple-team detection-validation exercise: a controlled, cooperative test of whether your telemetry and detections would see a chosen set of adversary behaviors, not an attack. Use it to turn a threat profile or an incident into scenarios, pick ATT&CK techniques, map each to public adversary-emulation content by name or ID (Atomic Red Team, MITRE CALDERA, Stratus Red Team, MITRE ATT&CK Evaluations emulation plans), write rules of engagement and a safety and comms plan, define expected telemetry per technique, score each as alerted / logged-only / not-visible, measure time-to-detect, and convert the gaps into a detection backlog. Reach for it when someone says "purple team", "detection validation", "adversary emulation", "run some atomics", "test our detections", "MITRE coverage assessment", "are we detecting X", "validate the SOC", or asks to build a scorecard or an exercise plan. This skill contains no attack commands and never runs the tests; it plans, coordinates, and scores.

hiyabh Bundle

Use this skill at the very start of a meaningful project or substantial feature, before any code is written. Sets up PRD, negative constraints, tests-from-PRD, reviewable implementation plan, and progress/learnings tracking. Trigger when user says "אני רוצה לבנות X", "פרויקט חדש", "נבנה פיצ׳ר משמעותי", "start new project", or before starting a multi-file feature with architectural decisions. Skip for bug fixes, refactors, single-file scripts, quick POCs, or data analysis notebooks.

mannyrodriguez-wk Skill

Consolidates outputs from the other Workiva presales skills (account-opportunity-brief, gong-discovery-analysis, technical-discovery-planner, evaluation-validation-planner, rfp-security-analysis) into a single clean Presales-to-Post-Sales Handoff Packet at deal-stage transition — closed-won or eval-to-implementation. Captures what was promised, what was validated, open commitments, known risks, and key stakeholder contacts for the Implementation/Customer Success team taking over the account. Use when a Solution/Value Consultant asks things like 'build the handoff packet for Acme Corp', 'prep this deal for implementation handoff', 'summarize everything for CS on this opportunity', 'what did we promise this customer during the sales cycle', or 'consolidate our presales work before CS takes over'. Read-only — never writes back to Salesforce or any other system; only optionally confirms deal stage/close date via Salesforce read tools.

mannyrodriguez-wk Skill

Adapter skill that translates the standard presales handoff JSON payload (per ../shared/evidence-schema.md), produced by upstream skills like account-opportunity-brief, gong-discovery-analysis, technical-discovery-planner, and evaluation-validation-planner, into a fully populated Workiva 'SC Demo Planning Document' — the internal CoM-Mantra-structured template Solution Consultants fill out to plan a live product demo narrative (Limbic Opening, Solution Demo Flow/tell-show-tell topics, Trap-Setting, Value Close, Customer Proof Points). This produces the demo NARRATIVE/SCRIPT plan, not a live MCP/connector execution — for that, see the /demo section of this repository. Primarily invoked automatically by other presales skills passing it a handoff payload, but can also be triggered directly by a user, e.g. 'build a demo planning doc from this discovery output', 'fill out the SC demo plan for [account]', 'turn this eval plan into a demo script', or 'draft the CoM mantra plan for [opportunity]'.

mannyrodriguez-wk Skill

Analyzes Gong call recordings and transcripts tied to a Salesforce account or opportunity to produce a structured discovery-call intelligence report — key themes, stated pain points, competitive mentions, buying-committee signals, objections raised, and open questions still needing validation. Use when a Solution/Value Consultant asks things like 'analyze Gong calls for Acme Corp', 'what pain points came up on the discovery call', 'summarize Gong for this deal', 'what objections has the prospect raised', 'who's involved in the buying committee based on our calls', or 'pull discovery intel before I build the demo/value case'. Read-only — never writes back to Gong, Salesforce, or any other system.

mannyrodriguez-wk Skill

Reads current Salesforce opportunity/account state via read-only Salesforce MCP tools and drafts proposed field updates (stage, next steps, close-date rationale, opportunity description) as a markdown table for a human rep to review and manually paste into Salesforce — this skill never calls a write, update, or delete tool. Use when the user says 'draft an SFDC update for [opportunity]', 'what should I update in Salesforce after this call', 'prep opp notes for [account]', 'summarize this demo for the CRM', 'help me log this discovery call in Salesforce', or after any discovery call, technical evaluation, or demo when Salesforce fields need to reflect what happened.

mannyrodriguez-wk Skill

Produces a one-page Account & Opportunity Brief for Workiva Solution/Value Consultants prepping for a presales engagement — pulls Salesforce account, opportunity, contact, and reporting context into a single read-before-your-call document covering account overview, opportunity stage/size/timeline, buying committee, product fit, and known risks. Use when the user says things like 'brief me on [account]', 'give me the account/opp overview before my call', 'prep me for [opportunity]', 'what do I need to know about [account] before I talk to them', or 'kick off presales on [opportunity]'. This is the entry-point skill for a presales engagement; other presales skills (gong-discovery-analysis, technical-discovery-planner, etc.) assume this brief has already been produced.

mannyrodriguez-wk Skill

Generates a tailored technical-discovery call agenda and question set for a Workiva Solution/Value Consultant, organized by Current State, Requirements, Technical Fit, and Risks/Blockers. Consumes existing account-opportunity-brief and/or gong-discovery-analysis outputs (or raw pasted context) to produce qualification questions on current tooling/process, integration/security requirements, stakeholder technical concerns, and success-criteria signals, each tagged with an evidence classification and citation. Use when the user says: 'build a technical discovery agenda for [account]', 'what should I ask on the technical call', 'prep discovery questions for [opportunity]', 'help me plan the tech deep-dive with [account]', or 'what are the open technical questions for [opportunity]'.

mannyrodriguez-wk Skill

Builds a structured evaluation / proof-of-concept (POC) validation plan for an opportunity moving into a technical evaluation stage — success criteria the prospect and Workiva agree define a 'pass,' a validation timeline with steps and owners, the stakeholders who must sign off, and risk factors that could derail the eval. Pulls Salesforce opportunity context (search_opportunities, retrieve_semantic_model) and can incorporate prior technical-discovery-planner or gong-discovery-analysis output when pasted in. Use when asked to 'build an eval plan for [opportunity]', 'what are the success criteria for this POC', 'plan the validation phase for [account]', 'draft a POC exit plan', or 'help me scope this technical evaluation'.

hiyabh Skill

Use after finishing product/requirements setup (e.g. via the pre-build-setup skill, if you have it), when project is a production web app, public API, or system with SLA/load requirements. Sets up k6 load tests (baseline, spike, soak) based on expected user volume from a PRD. Trigger when user says "stress test", "load test", "k6", "בדיקת עומס", or invoked automatically as a follow-up step from a pre-build-setup workflow. Skip for CLI tools, libraries, internal dashboards with <10 users, or POCs.

kroshank Skill

Build a week-by-week learning plan for a skill or subject with resources, exercises, and checkpoints. Use when the user says they want to learn X, asks for a study roadmap, curriculum, or 30/60/90-day plan.

mzvonar Bundle

Keep a checked-in markdown backlog readable as it grows, and groom it against the work being scoped. Splits a monolithic list into an index plus one detail file per item (frontmatter holds the fields that decide what to work on), reads it through one script instead of a 3000-line file, and classifies every open item into promote-now / promote-separately / keep-deferred / kill with a paste-ready report. Use when picking what to do next, when the user says "groom the backlog", "check deferred work", "what should we pull in", "any debt to fold in", "review pending items", before a new story/task/epic is scoped or finalized, when a review defers a finding, when adopting the format in a new repo, or when the list has grown past the point of being read in full. Never fires mid-implementation or for one-line fixes.

ficilcom Bundle

Sort incoming scout messages and agent-forwarded openings by what they actually disclose: whether the employer is named at all, which of pay, location, employment type, and duties are stated, whether the message refers to the applicant's own history or reads as a mass send, whether a stated salary is an offer or a "up to" figure, and whether the same employer has arrived through more than one route. Use when a user has a backlog of scout messages and wants to know which ones can be researched, what to ask before replying, and what to settle before handing over a resume; do not use to rate how promising an opening is, to judge an employer or an agent, or to reply on the user's behalf.

stifleur390 Bundle

Guide interactif pour définir un projet logiciel de A à Z : découverte, cahier des charges, PRD, architecture, rôles/permissions, isolation des données, paiements. Génère un dossier docs/projet/ avec tous les documents structurés. Utiliser quand l'utilisateur veut lancer un nouveau projet, spécifier une application, documenter une idée produit, rédiger un cahier des charges, créer un PRD, définir l'architecture technique, ou planifier un SaaS multi-tenant. Ne PAS utiliser pour du code pur, des bug fixes, des revues de PR, ou de l'architecture technique sans cadrage produit.

808enzo Bundle

Ask customers about an experience and act on the answer. Use when setting up a post-purchase, post-delivery, post-conversation, post-cancellation or lapse survey, when a low score arrives and nobody knows who owns it or by when it must be answered, when the biggest store always looks worst on complaint counts, when a review incentive or a survey-based segment is proposed, or when nobody can say whether a change made "because customers said so" worked. Covers the judging point and sampling, one overall question and the branch by score, the per-person ration, the route to the owner and the timer from the answer, coding verbatims into themes, the readable floor per cell, verification after the change, and the message back to the people who raised the theme. Not the metric formula, not test design, not the display rule of a widget, not the conversation itself, not product discovery research, not reputation management.

g-tavares14 Skill

Creates specs before coding. Use when the user runs /agent-skills:spec. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a capability map of modules before specifying.

insightfulanalytics Bundle

Interactive BPA rule generation for Power BI semantic models; guided discovery, model investigation, and expert rule authoring. Automatically invoke when the user mentions "BPA rule", "Best Practice Analyzer", or asks to "create a BPA rule", "audit BPA rules", "recommend BPA rules", "set up BPA for my team", "check model for best practices", "validate BPA rules", "improve a BPA expression".

insightfulanalytics Bundle

Step-by-step workflow for creating complete Power BI reports from scratch using pbir CLI. Covers model discovery, report creation, page layout, theme setup, visual placement, field binding, filtering, formatting, validation, and publishing. Automatically invoke when the user asks to "create a new report", "build a report from scratch", "make a dashboard", "set up a report with KPIs", "create an executive dashboard", "add pages and visuals to a new report".

arozumenko Bundle

Use when a raw ask arrives — a feature request, stakeholder ask, support theme, or 'someone wants X' — before anything becomes a Problem or Hypothesis. Verdicts every item Act Now / Plan Next / Collect More Signal / Decline-or-Defer, writes one batch record, and mints accepted in-scope items as Problems carrying discovered_from provenance; out-of-scope asks are declined against the scope line, and raw material naming a person stays in the confidential inbox with records referring by role. Trigger phrases — 'triage these requests', 'here are the asks from the sales call', 'someone wants X, what do we do with it', 'sort these into the pipeline'. NOT for interview synthesis (stakeholder-interview), NOT for bug or support-ticket triage, and NOT for meeting minutes.

arozumenko Bundle

Use when a hypothesis names no ratified outcome and so cannot be promoted, a quarterly bet is being set, or someone asks what number a bet is actually trying to move. Drafts, stress-tests, and records ratification of outcome anchors in docs/discovery/outcomes.md — measurable customer-behavior metrics with a dated baseline, a target, and a quarterly timeframe — running each candidate through a definition-quality checklist, where only the product owner's explicit in-chat act ratifies one and never without a dated baseline. Trigger phrases — 'define the outcomes', 'our hypotheses have no ratified outcome', 'what metric is this bet moving', 'set the quarterly targets', 'ratify the anchor'. NOT for business or traction metrics as anchors (revenue, signups, ARR — those may appear only as lagging confirmation), NOT for team OKRs or engineering SLOs, and NOT a metrics-dashboard builder.

arozumenko Bundle

Use when personas come up — 'define the personas', 'who are our users', 'make a persona card for X', 'which persona owns this journey' — or proactively whenever a journey, BDD scenario, or hypothesis names an actor that has no card yet or spells one inconsistently. Creates and maintains the canonical persona cards under docs/discovery/personas/ (one file per persona with its surface, goals, pains, jobs-to-be-done, and evidence links) so downstream artifacts reference stable persona slugs instead of drifting ad-hoc actor names. NOT for org-chart or stakeholder-power mapping, and NOT for market-segmentation research (deep-research).

arozumenko Bundle

Use when deciding what to build next, when validated hypotheses outnumber the team's appetite, when a ranking feels stale, or when someone asks which bet comes first. Ranks the incubating and promotion-ready bets against the active prioritization framework — RICE by default, with WSJF and ICE as config options — deriving the confidence factor from each hypothesis's evidence-banded confidence block (never free-guessed), persisting scores into hypothesis frontmatter so the ranking survives the session, warning (never blocking) when a bet is ranked on gut-band evidence, and rewriting the derived priority board at docs/discovery/priority.md. Trigger phrases — 'what should we build next', 'rank the backlog', 'prioritize the hypotheses', 'which bet comes first', 'the backlog is stale'. NOT for promotion-gate scoring, NOT for triaging raw incoming asks (intake-triage), and NOT for attacking the assumptions inside one hypothesis.

arozumenko Bundle

Use when a scope of test cases (or a described backlog, before any cases even exist as files) needs sizing or a cost/time estimate BEFORE automation work starts — presales scoping, a proposal, "how long/much to automate these N cases", "size these cases S/M/L/XL", estimating the framework/CI/foundation work an engagement needs on top of its cases, sizing a new engagement, or recalibrating an estimate against a project's own delivery history. Produces a scoping report with a range and a stated confidence level, never a bare point number.

arozumenko Bundle

Use when a hypothesis closes, an experiment concludes with a metric movement or a killed assumption, a vendor / data source / external service behaves differently than its docs implied, or a non-obvious product decision needs its rationale preserved — even if the user never says the word 'learning'. Captures a problem → outcome → lesson from product experiments and hypothesis outcomes (won or lost) into docs/discovery/evidence/learnings/ so the next similar discovery moves faster. Trigger phrases — 'capture learning', 'save what worked', 'document this lesson', 'what did we learn from X', 'we should remember that'. NOT for meeting minutes or transcripts, NOT for a durable forward-looking rule (record a decision via grill-decision), NOT for a retrospective, and NOT for a bare todo or a one-off observation.

arozumenko Skill

Use when starting a work session, when the PO is unsure what to do next, or when promotion, gates, blockers, what's-stuck, where-am-I, or am-I-ready-for-review come up — even without the word 'status'. Reports the whole discovery pipeline as one navigable dashboard — where every hypothesis stands against the promotion gate, what is blocked and on whom, the tracker board versus what docs/discovery/ says, and the exact next action (naming the exact skill) for each item; read-only, reading the docs/discovery/ tree and the product-owner's role memory directly and re-deriving gate state from the promotion checklist in prose (no vault, no validator script). NOT for code or CI status, PR-review state, deployment health, or git status — those are different tools.

arozumenko Bundle

Use when mapping opportunities under an outcome, asking where a hypothesis hangs, spotting solution-shaped 'problems', or when a new Problem or Hypothesis has no parent. Maintains the opportunity–solution tree over existing Discovery artifacts by adding only node_type / parent frontmatter to existing files and regenerating the derived docs/discovery/outcome-tree.md board (no new file silo); applies the disguise test (an opportunity that cannot spawn 3+ different solutions may be a solution in disguise) and annotates opportunities with Olsen scores for prioritize-bets. Trigger phrases — 'map the opportunity tree', 'where does this hypothesis hang', 'is this an opportunity or a solution', 'regenerate the outcome tree'. NOT for authoring outcome anchors (define-outcomes), NOT for ranking bets (prioritize-bets), and NOT for reconciling journeys against the backlog (journeys-to-hypotheses).

insideto27 Bundle

Evaluate and plan Amazon marketplace expansion across countries and regions. Use when a seller asks which Amazon marketplace to enter, how to compare international demand and economics, what tax, product-compliance, logistics, localization, account, or launch workstreams to investigate, or how to build a gated global-selling roadmap. Do not use as legal, tax, customs, or certification advice.

swyxio Skill

Resolve uncertain person or organization identities across aliases, duplicate records, conflicting sources, incomplete identifiers, or competing profile and media candidates. Use when reliable matching requires contextual corroboration, candidate discovery, historical reconciliation, or explicit ambiguity handling. Do not use for straightforward joins on established identifiers or ordinary photo, image, and metadata tasks without an identity-resolution problem.