Product & Planning

carta Skill

META-DISCOVERY ONLY — answers the question "what cap-table tools or commands exist?" when the user is lost about what's available. NEVER use this skill for any request that names a cap-table topic (stakeholders, grants, vesting, SAFEs, notes, valuations, ownership, waterfall, financing, exposure, etc.) — those are always direct data requests, even if the user phrases them vaguely. The matching specialist skill wins every time over this one.

carta Bundle

Internal config panel sub-skill for carta-issuance. Renders a pre-flight configuration panel with one full key-value block per stakeholder — name, email, stakeholder type, relationship, quantity, and the whole type-specific field set (option type / exercise price / vesting / documents for option grants, or share class / price per share / legend / Rule 144 for certificates, plus issue date and board approval) — so a single batch can carry genuinely different terms per person. Not invocable directly — dispatched by carta-issuance Phase 0.5.

carta Bundle

Internal artifact sub-skill for carta-issuance. Renders a read-only HTML review summary for option-grant AND certificate issuance batches — stat tiles plus one confirmation row per stakeholder. Not invocable directly — dispatched by carta-issuance Phase 2 via artifact-manager:render-panel.

iamdemetris Skill

Use when designing or critiquing user flows, information architecture, screen layouts, interaction patterns, microcopy, empty / error / loading states, or accessibility of a UX. Covers user research interpretation, wireframing, prototyping, usability heuristics (Nielsen, WCAG), interaction patterns (forms, search, filtering, navigation, onboarding), and design system thinking. Triggers: UX, UI design, design, wireframe, mock, flow, IA, information architecture, navigation, onboarding, empty state, error state, microcopy, usability, heuristic evaluation, persona, journey, prototype, Figma. Produces user flows, wireframes (textual / spec form), interaction specs, microcopy, heuristic-evaluation findings. Not for implementing UI code, see senior-frontend-engineer. Not for product scope / PRD, see senior-product-manager.

iamdemetris Skill

Use when scoping a product or feature, writing or reviewing a PRD / one pager / spec, defining the problem and the target user, prioritizing a roadmap or backlog (RICE, ICE, MoSCoW, Kano), drafting user stories with acceptance criteria, defining success metrics / north star / activation / retention, preparing a launch plan, or making a build / cut / defer decision. Triggers: PM, product manager, PRD, spec, one pager, user story, acceptance criteria, roadmap, prioritization, RICE, ICE, KPI, OKR, north star, activation, retention, jobs to be done, JTBD, launch plan, MVP, cut line. Produces PRDs, one-pagers, user stories, prioritization matrices, launch plans, metric definitions. Not for technical breakdown into tickets, see engineering-team-lead. Not for visual design, see senior-ux-designer.

iamdemetris Skill

Use when building a sample app or demo app, writing a getting started tutorial or integration guide, preparing a conference talk or workshop, running a livestream demo or office hours, scoping a hackathon, drafting an ambassador or partner relations plan, or routing community signal back to product and engineering. Covers dogfooding the product, time to first success, activation funnels, developer experience friction, and partner platform integration walkthroughs. Triggers: developer advocate, DevRel, developer relations, evangelist, community, sample app, demo app, tutorial, getting started, quickstart, integration guide, partner, ambassador, hackathon, workshop, conference talk, office hours, livestream, twitch stream, developer experience. Produces sample apps, getting started tutorials, integration guides, talk abstracts, workshop runbooks, community feedback reports. Not for authoritative API reference or canonical docs, see senior-technical-writer. Not for product roadmap or PRD ownership.

iamdemetris Skill

Use when designing, building, evaluating, or operating production ranking and recommendation systems: feed ranking, product recommendations, search ranking, content discovery, ads relevance, related items, you may also like, up next, home feed. Covers two stage retrieval plus ranking, two tower embedding retrieval, learning to rank (LTR), multi objective optimization (relevance plus engagement plus business value), diversity and MMR, exploration vs exploitation, contextual bandits, off policy evaluation (IPS, doubly robust), position bias correction, cold start strategies, and slice based monitoring. Triggers: recommender, recommendation, ranking, feed, candidate generation, CTR, watch time, engagement, recommender eval, NDCG, hit rate. Produces two stage pipeline designs, LTR specs, multi objective policies, off policy eval reports, exploration policies, cold start playbooks. Not for the training pipeline, see senior-ml-engineer; not for online experiment rigor, see senior-data-scientist.

jgsystemsconsulting Bundle

Knowledge base from the FAA Systems Engineering Manual (SEM) v1.0.1. Use for civil-agency systems engineering as the FAA practices it inside the Acquisition Management System (AMS) and the National Airspace System (NAS): the five-phase AMS lifecycle and its decision points; operational concept development and implementation-free functional analysis (ConOps, FFBD/N², CMLs); requirements analysis and architectural design synthesis (PRS→MRS, the PRD ratchet pPRD→iPRD→fPRD, RAM, ISEF/DoDAF views, CPRs); the seven technical management disciplines (Integrated Technical Management/SEMP, Interface Management/IRD-ICD, Risk-Issue-Opportunity, Configuration Management, SE Information Management, Decision Analysis, Verification & Validation); and the specialty disciplines (RMA via Service Threads/STLSC, Life Cycle Engineering, E3/Spectrum, Human Factors, Information Security via the NIST RMF, System Safety via the SMS, and Hazardous Materials/Environmental/EOSH). Scope limits: this is FAA-specific guidance, not policy —

azanir Bundle

QA-adapted discovery interview that transforms vague context into structured QA briefs through iterative questioning. Works standalone or as an embedded service auto-triggered by other skills when input is insufficient.

nethereum Skill

Build wallet portfolio features with ERC-20 token discovery, multicall balances, CoinGecko pricing, and multi-account scanning (.NET/C#). Use this skill when the user asks about token balances, token portfolios, token prices, token lists, multicall token queries, multi-wallet scanning, or CoinGecko integration.

nethereum Skill

Integrate Ethereum into Unity games using Nethereum with async Web3 API, WebGL wallet support via EIP-6963 multi-wallet discovery and MetaMask (.NET/C#). Use this skill when the user asks about Unity blockchain integration, Unity WebGL wallets, Unity MetaMask, Unity Ethereum, Nethereum.Unity, game blockchain, NFT games, or Unity ERC-20 tokens.

nethereum Skill

Connect browser wallets in Blazor using EIP-6963, MetaMask, or WalletConnect/Reown (.NET/C#). Use this skill when the user asks about connecting wallets in Blazor, EIP-6963, MetaMask Blazor integration, WalletConnect, Reown AppKit, or browser wallet discovery in a Blazor web app.

rgourley Bundle

Research-tier idea generation with regime framing. Chains market-regime (context) + universe-builder (candidates) + relative-strength (rank candidates vs SPY). Optionally adds factor-research for broader factor context (heavy, off by default). Different from portfolio-review (positions) and weekly-brief (macro-only) — this is discovery mode.

knowledgeislands Bundle

Audits, conforms, and reviews the Knowledge Islands standard for any Git repo with `.ki.toml`. Use for "audit this repo", "apply the repo standard", or "review this repository". Covers repository setup, GitHub settings, and `+` / `-` areas; use `ki-engineering`, `ki-repo-harness`, or `ki-work-roadmap` for toolchain, bundle, or delivery work.

knowledgeislands Bundle

Codify, audit, and maintain Specifications — the behaviour-level contract of what a system does — in any Knowledge Islands repo. Specifications live in `docs/specs/`, flat one-file-per-area, with an `index.md` that defines the ID scheme and areas table. Each requirement is a `### <PREFIX>-NNN — title` heading carrying one RFC-2119 (MUST / SHOULD / MAY) statement and a `_Verify:_` test hook; IDs are append-only and never reused; an unnumbered `## Gaps` section holds the backlog. Decisions capture the why (`ki-decision-records`), specifications the what, guides the how (`ki-guides`), and roadmap items the when (`ki-work-roadmap`). Use when writing or auditing a specification. Triggers: "write a specification", "spec this behaviour", "audit specifications", "add a requirement", "what does the system do". Off-ramps: ki-decision-records (the governing decisions a requirement cites), ki-guides (practical procedure), ki-work-roadmap (planned work), ki-authoring (Markdown/TOML style).

knowledgeislands Bundle

Codify, audit, and maintain repository-local guides — the practical how of using, operating, contributing to, or maintaining a system — in any Knowledge Islands repository. Guides live under `docs/guides/`, whose `README.md` gives readers a concise map. Decisions record why (`ki-decision-records`), Specifications record what (`ki-specs`), guides record how, and roadmap items record when (`ki-work-roadmap`). Use when writing a procedure or contributor guide, bringing a documentation tree into shape, or deciding whether material belongs in a guide, specification, Decision Record, or roadmap item. Triggers: "write a guide", "document how", "guide structure", "audit docs/guides", "move developer docs". Off-ramps: ki-decision-records (durable rationale), ki-specs (observable behaviour), ki-work-roadmap (future work), ki-authoring (Markdown style).

knowledgeislands Bundle

Governs typed, directional cross-repository trades between locally registered Knowledge Islands repositories: mutable committed preparations, work and knowledge routes, TRD eight-hexadecimal identities, immutable submitted sender projections, receipt, receiver-only decisions, sender observation policies, release, and pruning. Use when preparing or submitting work or knowledge to another repository, observing a preparation, receiving or reviewing an inbound trade, auditing routes or records, or resolving direct application, adoption, retention, parking, clarification, decline, or supersession. A route grants visibility only; ki-work-roadmap and the receiving repository retain priority and acceptance authority.

knowledgeislands Bundle

Governs concise, repository-owned checkpoints for resuming one human-named active thread in a fresh agent context without a transcript or vendor session. Use when asked to checkpoint current work, update or retire a checkpoint, resume a named thread, audit `+/_CHECKPOINTS/`, or explain portable reconstruction state. It keeps one active snapshot per thread, retains explicit retired evidence, and leaves decisions, roadmap state, knowledge, recap, runtime hooks, and session continuity to their proper owners.

knowledgeislands Bundle

Selects, captures, promotes, defers, and spawns the next work through one shared queue: now, next, soon, future, waiting-for, and parked. It also records the receiver's confirmed disposition of validated inbound trades, including direct application of a trivial local work change versus a separately prioritised work record. Use when asked "what should we do next", "review these inbound trades", "apply this trade directly", "promote this work", or "defer this". It resolves the selected local roadmap or KB Streams adapter and refuses unavailable remote execution; local trade transport belongs to ki-trades.

knowledgeislands Bundle

Shapes selected Now or Next draft work through readiness in the selected local roadmap or KB Streams adapter. It enriches the canonical record in place, including an item under `Streams/Roadmap/` in a Knowledge Base, then stops at ready. Use when asked "plan this", "make this ready", or "prepare this work for implementation". It refuses unavailable remote execution and does not capture work, implement it, or close it.

knowledgeislands Bundle

Governs repository selection of a forward-work adapter and the shared lifecycle vocabulary used by change-management processes. Use when choosing or auditing a work tracker, configuring roadmap, KB Streams, GitHub Issues, or Linear change management, or mapping repository work to a common lifecycle. The selected adapter owns its records; use ki-work-roadmap, ki-repo-kb-streams, ki-work-github-issues, or ki-work-linear.

knowledgeislands Bundle

Prepares and runs a bounded, single-repository batch of independent work records under either reviewed exact-item authority or explicit human outcome authority such as "crack on with the roadmap". Outcome authority lets the orchestrator select, deliver, and consolidate acceptance without another pre-run gate while recording exact scope, evidence, stops, and remedial follow-ups. A process skill: it does not infer authority, bypass lifecycle or verification, prune, push, release, or introduce a tracker. Remote execution fails closed pending KI-HARNESS-FND-014. Use when asked to "prepare a work batch", "run this approved batch", "crack on autonomously", "coordinate several ready work items", or "record this batch run". For ordinary selection use ki-next; for plan shape use ki-plan; for single-item delivery use ki-implement; for closure use ki-accept.

knowledgeislands Bundle

Captures an explicitly submitted link, scans a bounded public-source brief, and triages current signals into read or learn, watch, act, or discard without keeping an inbox. Use for "capture this link", "scan these interests", "what changed in these public sources", or "triage these signals". It does not select backlog work, persist subscriptions, or implement recommendations.

knowledgeislands Bundle

Recaps a live session: summarises changes, decisions, and files; surfaces only unfinished session work; and routes durable learnings. Use for "recap this session", "what's outstanding", or "harvest what we learned". It does not select backlog work—that is `ki-next`—or mechanically mine historical transcripts.

knowledgeislands Bundle

Audit, conform, and design Knowledge Islands compatible harnesses — source repositories that co-locate skills, subagents, MCP servers, evals, and hooks while publishing a verified installed capability payload. Use when creating a harness, checking its five-part source layout, validating its declared capability prefix and skill identities, reviewing its CLAUDE.md orientation, confirming its `.ki.toml` harness declaration, or distinguishing source shelves from the directly installed payload. Triggers: "audit the harness", "scaffold a new harness", "does this repo follow the harness standard", "refresh the harness standard", "is this a compatible harness". Governs the container and publication boundary, not its contents: skill quality → `ki-skills`; agent quality → `ki-subagents`; repository roadmap → `ki-work-roadmap`; MCP code → `ki-repo-mcp`; engineering toolchain → `ki-engineering`; repository settings → `ki-repo`; CLI installation and activation → `tools-ki`.

knowledgeislands Bundle

Defines the configuration and safety guidance for Linear as a Knowledge Islands change-management adapter: mutable team-scoped locators, workflow metadata, review, closure, archive/delete semantics, and remote-write authority. Use when a repository configures Linear as its tracker or needs guidance for a future authorised remote operation. Remote process execution fails closed pending KI-HARNESS-FND-014. For local files use ki-work-roadmap; for GitHub use ki-work-github-issues.

knowledgeislands Bundle

Governs flat repository work items and their concise root orientation in project repositories. Use for "audit the roadmap", "audit plans", roadmap horizons, theme grouping, work-item identity, lifecycle detail, lifecycle and pruning commit boundaries, plan dependencies, or root-orientation drift. Project work items live directly under docs/roadmap; Knowledge Bases apply the same record model under Streams/Roadmap through ki-repo-kb-streams. Records gain detail in place as they move from draft through readiness, delivery, required review, and retained completion. Process skills apply the shared lifecycle; ki-decision-records owns durable decisions.

knowledgeislands Bundle

Governs the Streams operational container of a Knowledge Islands base: Streams/Roadmap for flat forward work and Streams/Housekeeping for recurring-work templates. It is the KB placement adapter for the shared change-management lifecycle, not a second Focus-based queue. Use to establish or audit KB Streams structure, route roadmap or housekeeping work, or migrate legacy Active/Background/Dormant stream trees. For common selection, planning, delivery, review, and closure use ki-next, ki-plan, ki-implement, and ki-accept; for the five-zone model and note CRUD use ki-repo-kb.

knowledgeislands Bundle

Governs safe acquisition of installed ChatGPT session material through opaque, read-only local-store evidence. Use for "acquire ChatGPT sessions", "import ChatGPT sessions", or "audit ChatGPT sessions". It guides discovery, listing, faithful source reads, checkpoints, staging, and later harvest without treating source-session deletion as part of acquisition.

knowledgeislands Bundle

Governs read-only Granola meeting acquisition and later housekeeping. Use "acquire Granola meetings", "import Granola meetings", "audit Granola acquisition", or "reconcile Granola changes". It defines complete date-window discovery, folder and unfoldered routing evidence, faithful MCP reads, content checkpoints, amendment detection, and a separate human-approved retirement gate. CLI staging belongs to tools-ki; canonical acquisition lifecycle belongs to Arcadia.

knowledgeislands Bundle

Audits, conforms, and scaffolds the deliberately minimal repository structure for KI Specifications: a keyless `[skills.ki-repo-specifications]` marker plus the top-level proposals, specifications, schemas, templates, examples, docs, and tooling areas. Use when bootstrapping KI Specifications, checking its repository shape, or evolving that shape as the specification system matures. Triggers: "audit KI Specifications", "bootstrap the specifications repo", "check the KIP/KIS repository structure", "conform the specifications repository". It adds only the specifications-specific structural delta; use `ki-repo` for universal repository files and GitHub settings, `ki-decision-records` for decisions, and `ki-work-roadmap` for planning.

knowledgeislands Bundle

Defines the configuration and safety guidance for GitHub Issues as a Knowledge Islands change-management adapter: mutable issue locators, lifecycle metadata, review, closure, hierarchy, dependencies, and remote-write authority. Use when a repository configures GitHub Issues as its tracker or needs guidance for a future authorised remote operation. Remote process execution fails closed pending KI-HARNESS-FND-014. For local files use ki-work-roadmap; for Linear use ki-work-linear.

tbc-servicos Bundle

Gera um relatório TOTVS SmartView de ponta a ponta, do código ao artefato renderizando dados. A partir de uma especificação (tabelas/campos Protheus, query SQL ou dados literais), gera o Business Object TLPP (IntegratedProvider), compila no AppServer via advpls (TDS CLI remoto), registra na discovery e monta o artefato no SmartView (Data Grid, Tabela Dinamica/Pivot ou Report). Esta skill deve ser usada quando o usuario pedir para criar ou gerar um relatorio SmartView, fazer um Business Object para o SmartView, publicar um IntegratedProvider, gerar Data Grid, Pivot ou Report no SmartView, ou desenvolver relatorios SmartView com agentes de IA. Cobre um ambiente SmartView (TReports) self-hosted ligado a um AppServer Protheus.

anton-abyzov Skill

START HERE — Skill discovery and installation assistant. The recommended first skill when you don't know which skills you need. Searches verified-skill.com, recommends plugin bundles, and installs skills. Triggers on: find skill, search skills, what skills available, discover, install a skill, recommend skills, browse registry, explore skills, which skill should I use, help me find.

kennyolofsson23-netizen Skill

Structured deep research and investigation. ML papers, competitor analysis, market research, domain intelligence, data source discovery. Uses firecrawl for web search/scraping. Outputs actionable findings with sources and confidence levels. Use when the user says "research", "investigate", "deep dive", "analyze the market", "find papers on", "competitor analysis", or needs multi-source synthesis on any topic.

kennyolofsson23-netizen Bundle

Tool Discovery Skill