Product & Planning

ryanalberts Skill

Walks the pmstack skill graph against the outputs/ directory to find graph gaps (missing downstream artifacts), cross-artifact drift (PRD-metrics-eval misalignment), and stale candidates (superseded files). Each finding includes a one-line "do this" recommendation. Trigger when the user says "lint my workspace," "graph check," "find drift," "tidy up outputs," "what's stale," or asks for a workspace audit. Run weekly on schedule, or before any review.

ryanalberts Skill

Draft a stakeholder brief on a topic, tailored to executive, engineering, customer, or board audience. Use when a PM asks for a "brief", "update", "readout", "exec summary", "eng comms", "customer announcement", or "board update", or when they need to communicate a status / decision / change to a specific audience and need help adapting the framing.

ryanalberts Skill

Full PM sprint orchestrator — chains pmstack-prd, pmstack-metrics, pmstack-eval, and pmstack-brief in sequence with explicit user confirmation between each step. Use when the user has a customer signal or feature ask and wants to go end-to-end (problem → spec → metrics → eval design → stakeholder comms) in one guided pass with checkpoints.

ryanalberts Skill

Run a Klein-style pre-mortem on a draft PRD before launch — simulates 3 plausible failure stories 6 months in the future, names leading indicators and mitigations, then offers to mutate the PRD's Risks section. Trigger when the user says "pre-mortem," "what could go wrong," "risk pass," "imagine this fails," "stress test the spec," or asks to harden a PRD before review. Use after /prd, before launch.

ryanalberts Skill

Pre-launch verifier. Aggregates PRD, metrics, eval design, eval run, premortem, eval-drift, and brief evidence into a single GO/NO-GO/CONDITIONAL verdict with each item showing pass/fail/missing plus the file that proves it. Trigger when the user says "are we ready to ship," "launch readiness," "release check," "pre-launch review," "ship it?" or asks to gate a release. Run before any launch.

dayfinggg Bundle

Break a large or multi-session engineering objective into ordered, verifiable stages with dependencies and checkpoints. Use when the user asks for an implementation plan or complex authorized work needs internal sequencing. Do not turn an implementation request into a planning-only response.

dayfinggg Bundle

Turn settled requirements or an existing conversation into an implementation-ready specification with testable behavior and explicit scope. Use when the desired outcome is mostly known and needs consolidation. Do not use for open-ended discovery or implementation.

devantler-tech Skill

Maintenance task menu for devantler-tech/ksail (a Go CLI for local Kubernetes GitOps). Triage, bug fixes, CI/workflow health + CI-failure & flaky-test investigation, docs, driving actionable trusted-author PRs to merge including dependency-bot PRs that cannot finish autonomously, weekly E2E coverage + live reliability testing, and the monthly KSail Strategy roadmap. Use when the daily maintainer selects KSail.

devantler-tech Skill

Maintenance + advance task menu for the 🌊 Project Board (org project 5) — the maintainer's single cross-portfolio navigation surface. Covers coverage, hierarchy, status hygiene, views, and the roadmap axis. Use when the daily maintainer selects the project board on rotation, or when a survey shows board drift.

duthaho Bundle

Job-fit evaluation and discovery for job seekers — "find roles that fit me" and "should I apply to this one?" DISCOVER searches job boards for openings matching your profile; EVALUATE takes job URLs/descriptions you provide. Both research compensation, company signal, and posting legitimacy in parallel, score each role A–F, and emit a ranked decision brief with tailored CV-bullet suggestions. Evaluated roles persist in out/jobfit/tracker.md so repeat runs skip what you passed on. Keyless and human-in-the-loop: it never applies for you. Use to find matching jobs, triage postings, decide whether a role is worth applying to, or tailor a CV to a JD — e.g. "find jobs that fit my CV", "/jobfit <url>", "score these roles against my CV". For community buzz on a company use pulse.

etrebels Skill

Turn a customer's recent calls, adoption signal, and roadmap status into a QBR brief that leads with the outcome they bought. Trigger when a quarterly business review is coming up, before a renewal or value-review call, or when the user says "QBR prep", "build the QBR", "quarterly review for X", or "value review".

uzysjung Bundle

Defines and enforces a project's long-term direction (North Star Statement, metric-as-proxy NSM, strategic Pillars with a module↔pillar map, Will/Won't, 4-gate + priority-order decision heuristics), then turns that direction into a ranked, persisted roadmap so the plan survives /compact and new sessions. Use when starting a new project, when scope creep is suspected, when a non-obvious feature request needs prioritization, or when the user asks where the project should go next. Sits one layer above SPEC/PRD — answers 'why and where to', not 'what and how'. Fires on the user's real phrasings: "앞으로 어떤 방향으로 개선·발전시킬지 고민해봐", "NORTH.md / NORTH_STAR 보고 나아갈 방향 + 기능 제안", "북극성 정렬 로드맵", and the English "what direction should we take next", "propose a roadmap from the north star". Do NOT use it to find what is broken right now — detecting bugs, gaps, or quality regressions belongs to the audit/gap skills; this skill consumes their findings and DIRECTS forward planning.

uzysjung Skill

Detects when SPEC.md or PRD.md exceeds 300 lines and proposes feature-based splitting with a master route document. Use when SPEC.md grows too large to be effectively used as a single document.

uzysjung Bundle

Runs work through GitHub Issues so the user and the agent can see the same backlog: normalize an incoming request into an issue before building, group tasks under a parent (epic) issue, order them with milestones and priority labels, read every comment before starting, and promote decisions out of comments into the issue body so they survive. Enforces the body template (배경/문제/근거/레퍼런스/제안/전제/방향성/AC/후속) so issues become reusable agent context, and keeps read-only, draft, remote-write, implement, verify, and status stages distinct. Use whenever a request will outlive the chat turn, whenever work needs an order the user can review, or when the user names issues ("이슈로 등록해줘", "에픽으로 묶어줘", "이슈 정리해줘", "#42 작업해줘", "우선순위 다시 잡자", "backlog this", "break this into sub-issues", "implement issue #N"). Read-only stages make no remote change; never create, edit, label, comment on, close, or re-parent a remote issue, and never touch a project board, without the user asking for that change.

pixiesgeosun Skill

Use when creating a new OpenCLI adapter from scratch, adding support for a new website or platform, or exploring a site's API endpoints via browser DevTools. Covers API discovery workflow, authentication strategy selection, YAML/TS adapter writing, and testing.

nahisaho Bundle

Copilot agent that assists with project planning, scheduling, risk management, and progress tracking for software development projects Trigger terms: project management, project plan, WBS, Gantt chart, risk management, sprint planning, milestone tracking, project timeline, resource allocation, stakeholder management Use when: User requests involve project manager tasks.

arkan Skill

Autonomous execution of a plan, PRD, or context document. Decomposes the input into discrete tasks, dispatches each to a subagent (using TDD workflow for testable code changes, normal execution for config/docs), then runs an automated code review via Codex and iterates fixes until the review passes (up to 5 review cycles). Supports `--skip-review` (no Codex review) and `--only-review` (review + fix loop on the user's existing uncommitted changes, no implementation). Use this skill whenever the user says '/do', asks to 'implement the plan', 'execute the PRD', 'ship this spec', 'run the plan autonomously', wants a plan/PRD/issue translated into working code without hand-holding, or hands over a docs/plans/*.md file and asks you to build it. Also use when the user says something like 'take this and build it', 'do everything in this document', or 'make it happen' while referencing a planning document, or 'just review what I have' / 'run the review loop on my WIP' (use `--only-review`). Trigger even if the user do

arkan Skill

Rework a change from the intended end state and generate an HTML architecture report with diagrams, risks, migration guidance, architecture invariants, and PRD handoff information.

open-gsd Skill

Break a plan or milestone brief into independently-grabbable vertical slices (tracer bullets), written to `M###-ROADMAP.md` by default (GitHub issues only on explicit confirmation). Prefers many thin slices over few thick ones and marks dependency order. Use when asked to "break this into slices", "decompose the plan", "vertical slices", "break into issues", or when a plan needs task-level decomposition.

open-gsd Skill

Synthesize the current conversation into a milestone brief (PRD). Writes to `M###-CONTEXT.md` by default, or files a GitHub issue only with explicit user confirmation. Use when asked to "turn this into a PRD", "draft a milestone brief", "capture this context", "write it up", or when enough has been discussed to commit the plan to paper. Does not interview — it synthesizes what is already known.

quanpersie2001 Skill

Use when Pulse planning or discovery needs graph-based architecture context, execution-flow tracing, symbol relationships, or blast-radius analysis beyond plain file search.

witooh 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".

hylarucoder Bundle

Decides whether a PRD is needed, drafts one from a product problem, repairs an existing PRD, or judges its split/merge boundary. Use for PRDs, product requirements, requirement specs, scope, user-visible behavior, and acceptance criteria（写 PRD、需求文档、PRD 拆分或打磨）. Use hai-goal for execution phases, hai-architecture for technical design, entity-model-auditor for field placement, and document-audit skills when the task is consistency diagnosis rather than product shaping.

hylarucoder Bundle

Tests whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent existence, then classifies it as Keep, Merge, Defer, Delete, Replace, or Prove first. Use when the explicit decision is what can be removed or collapsed（奥卡姆剃刀、砍需求、这个字段/状态/层有必要吗、是否过度设计）. Use hai-prd to shape product requirements and hai-architecture to redesign module boundaries after the cuts are known.

hylarucoder Bundle

Audits documentation for internal contradictions and/or mismatches with code, config, schemas, and approved contracts. Use for 文档审计、前后冲突、术语漂移、README 是否过时、文档和代码一致吗, including check-and-fix requests. Select evidence sources from the request; return prioritized findings, source precedence, and repair ownership. Apply clear local repairs only when requested. Use hai-rewrite-doc for wholesale reconstruction, hai-prd for product shaping, and readme-beautifier for formatting only.

hylarucoder Bundle

Rebuilds a drifted, repeatedly patched document from verified current conclusions. It inventories old blocks, preserves verified wording, removes disproved material, writes authoritative replacement coverage only from verified sources, and reports keep/delete/replace/undecided dispositions. Use when the user wants a rotten document verified and rewritten rather than patched again（按最新结论重写、逐条核实、推倒重写）. Use hai-prd for PRDs, hai-goal for plans, and a document-audit skill when no rewrite is requested.

hylarucoder Bundle

Turns an idea, PRD, plan, review, architecture topic, or other substantive source into a self-contained, multi-section HTML report with structure-appropriate diagrams, matrices, evidence, risks, and next moves while preserving the source’s meaning. Use when the user asks for a visual/HTML/web/slides-like report（可视化报告、做成网页、汇报页）. Use create-visual-card for one single-frame shareable image; this skill owns presentation, not the underlying architecture or product judgment.

hylarucoder Bundle

Audits an entity model field by field: what should exist, what exists now, where each value belongs (column, config, computed runtime value, or removal), and what must migrate. Use when comparing a PRD with a schema/model, designing entity fields, or deciding “store or compute?”, “column or JSON?”, or “does this field belong at all?”. Use hai-prd first when the product intent is still unsettled.

injectivelabs Bundle

Integrate Injective RFQ taker flows into browser apps and operational quote monitors. Use this skill when building, reviewing, or debugging RFQ gateway autosign settlement, Web3Gateway AuthZ setup, manual TakerStream quote collection, client-side gateway-style quote selection, RFQ open/close flows, gateway prefetch, optimistic position updates, conditional TP/SL intents, quote uptime probes, market-readiness checks, or mainnet RFQ frontend integrations. Covers mainnet parameters, canonical decimals, quote windows, signer slots, market discovery, quote-hit diagnostics, and production RFQ gotchas.

jamillazarev Skill

Use when the user wants to build or run a team of AI agents out of one git repository — you act as their advisor (the skill ships under the name Opsinist); you interview progressively (defaults everywhere, small jobs stay small), keep every entity as a file (roles, tasks, teams, pipelines, requests, runs), dispatch agents against those files, and stay their console for status, cost, recovery, shipping and reshaping the team. Also for joining an existing repo, importing a backlog, or answering a question with no machinery at all.

jpantsjoha Bundle

Govern discovery, eligibility, and submission of a plugin or skill to official directories, registries, marketplaces, and curated GitHub lists. Use when preparing or sending plugin listings, marketplace forms, directory PRs, or repository recommendations; require current policy evidence and a final human confirmation before every external submission.

irwebtools Bundle

Convert product ideas into clear problems, users, goals, and success metrics.

iskron-ai Skill

Используй, чтобы впустить ВНЕШНЕЕ СЛОВО в граф Искрона — шабда-интейк. Триггеры: «впусти внешнее слово», «засей граф из issue/доков», «внеси issue», «запиши пост», «внеси новость», intake, ingest issues, shabda intake. Источник-независим: issue, доки, код, разговор входят через адаптер под одной дисциплиной — форма→тип узла, эпистемика по виду источника, source_kind=shabda, дедуп, якорение, сверка. Distinct from writing (узел из готового различения), iskronify (derived-конфиг), product-roadmap (композиция с GitHub-адаптером). Нужны тулы iskron_*.

iskron-ai Bundle

Используй, чтобы собрать продуктовый роадмап GitHub-репозитория — или мультирепо-продукта (org или набор репо как один продукт) — выведенный из issues и PR через граф рассуждений. Триггеры: «собери роадмап из issues/PR», «роадмап по продукту», «что в этом репо делать дальше», roadmap from repo/github, roadmap for my org, multi-repo roadmap, quick roadmap, product-roadmap. Отыгрывает мейнтейнера: проверенная почва настоящего, взвешенный бэклог как шабда, направления (bianhua), рендер graph+markdown+HTML. Композирует iskronify, intake и assembly. Нужны gh CLI и тулы iskron_*.

cdatasoftware Skill

Use when the user has CData Connect AI MCP available and is asking business questions that require querying live enterprise data. This includes: questions for live data from an enterprise system (Salesforce, Workday, NetSuite, HubSpot, Jira, SQL Server, Snowflake, etc.); requests to retrieve, look up, or explore data from a connected system, even without naming a specific platform (e.g. "show me my accounts," "pull up recent orders"); the user naming a connector or data source; business-domain questions ("top customers," "open tickets," "headcount by dept," "pipeline by stage") when at least one Connect AI connection is available; or conversations already involving Connect AI tool calls. Enforces the required discovery workflow (getInstructions before any schema/table/column call), covers query construction patterns, error recovery, and SQL dialect guidance. Load connector-specific (connect-ai-salesforce, connect-ai-jira, or connect-ai-googlesheets, etc) skills on top for deeper patterns.

crissmoldovan Bundle

Discover UX improvements a codebase can already support — across UI, API, CLI, MCP and notifications — and gate every candidate through a not-already-implemented sweep and a no-confusion check before proposing it. Use when you want evidence-backed UX opportunities, riding a change or from pure analysis.