Product & Planning

aryaniyaps Bundle

Frame product problems and decide what to build. Use when establishing business context, aligning actors with conflicting goals, discovering or prioritizing features, defining traceable requirements, comparing consequential tradeoffs, or recording a product decision. Use lamina-ux for interaction details and lamina-product-behavior for authoritative runtime rules.

blendsdk Bundle

Tracks features across their lifecycle in a live, per-repo roadmap — every RD, plan, and task and the lifecycle stage each is in. Layout-aware: a single plans/00-roadmap.md in flat layout, or a two-tier per-feature + portfolio roadmap under codeops/ in nested layout. Use when the user says "roadmap", "make_roadmap", "update_roadmap", "review_roadmap", "show_roadmap", "archive_roadmap", or "compact_roadmap". Covers six actions: make_roadmap (create + seed rows from disk), update_roadmap (re-infer stages, sync to disk, cascade to the portfolio), review_roadmap (read-only health check for drift/broken links), show_roadmap (read-only status overview — progress, stages, and next steps), archive_roadmap (move a completed feature to the archive), and compact_roadmap (slim a bloated roadmap: strip the legacy Notes log and trim fat cells). Detects the action from the user's phrasing or arguments and branches. The roadmap is the cross-session source of truth at the RD/plan altitude, above any single execution plan.

blendsdk Bundle

Upgrades an outdated plan or requirements set to current CodeOps standards. Use when the user says "upgrade_plan", "upgrade_requirements", "upgrade my plan", "upgrade my requirements", "bring my plan up to date", "bring my requirements up to date", or asks for a "version upgrade" of a plan/requirements set. ONE skill covers both targets: "upgrade_plan [feature-name]" re-evaluates a plan in plans/<feature>/ against current standards, and "upgrade_requirements" re-evaluates the set in requirements/. It detects the target from the phrasing/arguments and branches. The flow is: detect version, assess gaps, present an upgrade report BEFORE changing anything, pass a non-negotiable Content Quality Gate, apply upgrades preserving all user-authored content verbatim, then verify. Does NOT auto-advance the roadmap.

blendsdk Bundle

Gather and document requirements, turn an idea into formal requirement documents (RDs). Use for "make_requirements" (full discovery: brain dump or bare idea into a structured requirements/ set), "add_requirement" (add one new RD to an existing set), and "review_requirements" (health check / gap analysis on an existing set). Trigger when the user wants to capture, expand, structure, or audit what a system must do before building it — e.g. "help me spec out my app", "document requirements", "what features am I missing", "add a feature to the requirements", "review my requirements for gaps". Acts as a proactive domain consultant: absorbs the seed idea, expands it with comparable-system features, challenges it with edge cases, then decomposes it into numbered RDs behind a hard Zero-Ambiguity Gate.

devantler-tech Skill

The ADVANCE playbook for an autonomous AI engineer — how to move a product forward once it is healthy: product strategy and roadmap stewardship, issue triage and decomposition, oldest-actionable-first implementation, test coverage, benchmarking and performance, refactoring and code quality, documentation sync, and security posture — all shipped as evidence-backed draft PRs self-promoted on genuine readiness. Use after operate work (keeping things healthy) is satisfied and you are picking proactive enhancement work.

levyflux Bundle

Drive a product requirement from evidence-backed definition through implementation, verification, acceptance, and release readiness. Use for multi-step feature delivery, PRD authoring, requirement changes, feedback rounds, traceability, or cross-component work where decisions and evidence must remain coherent.

loktar00 Bundle

Drive a local ComfyUI instance headlessly from an agent — discover installed models and nodes, build API-format graphs, queue jobs, poll for results, and pull images/audio/video to disk. Includes the discovery protocol for learning a model you have never used (pull its template, never guess the graph) and the failure modes that fail SILENTLY. Use whenever generating textures, images, sound effects, music or video on ComfyUI, or when a ComfyUI job errors or returns garbage.

tavily-ai Skill

Research competitor products, SKUs, pricing, packaging, positioning, feature comparisons, product catalogs, category pages, retailer listings, marketplace data, and market intelligence. Use when the user asks for competitor SKU discovery, product data enrichment, pricing/spec extraction, product comparison, market intelligence, or crawl/map-driven product research.

jonbond5 Skill

Build a feature end to end, autonomously. Use when the user asks to BUILD, IMPLEMENT, ADD, or SHIP something — "build me a feature that does X", "implement X", "add X and make sure it works", "keep going until X is done". Scopes the work into units, builds each in an isolated worktree, attacks every claimed pass adversarially, and stops only when an independent judge says the ORIGINAL ask is satisfied. Expands scope on its own when a discovery blocks the ask. Not for questions, research, or reviewing existing code.

almeidamarcell Bundle

Strategic SEO planning for new or existing websites. Industry-specific templates, competitive analysis, content strategy, and implementation roadmap. Use when user says "SEO plan", "SEO strategy", "SEO planning", "content strategy", "keyword strategy", "content calendar", "site architecture", or "SEO roadmap".

akillness Bundle

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. Use when issues or external PRs need categorising, verifying, and turning into agent-ready briefs. Triggers on: triage, triage the backlog, review these issues.

involvex Bundle

Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.

we-are-move Bundle

Runs a structured six-dimension assessment of how mature a talent acquisition or people function is in its adoption of AI, and produces a written report with a score per dimension, the binding constraint, and a sequenced 30-day / next-quarter / 2-3 quarter roadmap. Use when someone asks "how good are we at AI", "where are we on AI adoption", "the CEO wants an AI plan for hiring", "we bought a bunch of AI tools and I can't tell if they're working", "the board is asking what we're doing with AI in recruitment", "AI readiness", "AI maturity", "benchmark our TA team on AI", or wants to know what to do next with AI in talent, recruiting, or the wider people function. Also use when preparing an AI position for a board paper, a budget conversation, or a leadership offsite. Not for choosing between named vendors — that is hr-tech-evaluation.

omexit Bundle

Use when defining or changing WHAT to build - a new feature idea, a PRD to write or update, or scope that needs challenging before implementation starts.

omexit Bundle

Use when asked to review work: "review this", "any issues here", "review the PRD against the code", or a review of a diff, module, architecture, or design/spec document - including multi-expert panel reviews ("review with a DDD expert and an asset-finance expert"). Also when running a removal-first simplification sweep: "what can we remove", "product simplification review".

abhillashjadhav Skill

Forces a written PRD before any code generation. Use this skill the moment the user says "build", "create app", "make me a", "vibe code", "let's build", "I want an app that", "spin up a", "prototype a", "ship a", or any phrasing that signals they want code generated from a high-level idea. Also use when the user references an existing project but the conversation has no PRD context (no /prds/ file referenced, no clear success metric). The skill blocks code generation until a 5-field PRD exists as a markdown file in the repo. Do NOT use when the user is asking factual questions, debugging existing code, editing a specific file they've named, or working in a repo where a PRD for this feature already exists at /prds/. Skip when user explicitly says "skip the PRD" or "just code it" — but flag the risk once before proceeding.

abhillashjadhav Bundle

Use this skill when a user supplies an AI feature spec, PRD, PMOS/task contract, existing eval suite, traces, outputs, state evidence, or release question and wants to define good, create or run evals, grade outcomes, agent trajectories, end-to-end system checkpoints, or promised memory behavior, add deterministic or model graders, calibrate an LLM judge against human goldens, compare repeated trials, inspect failures, debug evaluation evidence, or make a CI release decision. Produce one provider-neutral AI Evals for PMs suite through the stable pm-verifier runtime, with binary gates, gradual rubrics, provenance, operational metrics, JSON results, and a Markdown report. Also use for migrating pm-evals or Evals-pass-1 work. Do not use for ordinary non-AI unit testing, generating the AI application itself, a one-off opinion on one output without a quality contract, or live production monitoring.

aquarius-mu Skill

Break a plan, spec, or PRD into independently-committable issues using vertical slices. Use when converting a plan into trackable work items.

fradser Bundle

Lark/Feishu CLI router: query and operate Lark/Feishu via lark-cli. Use `lark-cli skills read subskill` (e.g. lark-doc, lark-base, lark-im) to load domain skills for docs, sheets, base, calendar, im, mail, tasks, okr, drive, wiki, slides, whiteboard, apps/miaoda, approval, attendance, contact, vc, minutes, note, events, etc.

fradser Bundle

This skill should be used when the user asks to "create PRD", "write product requirements document", or mentions "PRD", "product requirements document".

mmkkkkzz Bundle

Operate First Step Hub through the repository-owned `first-step` CLI, including installation, OAuth login/status/logout, discovery and execution of every OpenAPI operation, JSON and binary transfer, and private or public HTML workflows. Use when Codex or Claude needs to inspect, read, create, update, archive, import, export, upload, download, authenticate, troubleshoot, or otherwise automate First Step Hub; trigger on `first-step`, First Step Hub API, CLI authentication, operationId, HTML upload, or HTML sharing requests.

mmkkkkzz Bundle

Authorized local-only black-box web application penetration testing and red-team assessment workflow for disposable local targets. Use when Codex is asked to run or plan a local web pentest, destructive local attack simulation, vulnerability discovery pass, or authenticated local app security assessment where the expected output is evidence-backed vulnerability reporting, attack-lens subagents, and safe cleanup notes. Do not use for staging, preview, production, or third-party targets. Do not use for code modification or remediation unless the user explicitly changes scope.

mmkkkkzz Bundle

Resolve a project's complete live unresolved Sentry queue end to end: inventory every issue, classify and root-fix each cause, add regression coverage, merge reviewed fixes through the repository's release flow, verify the production deployment, resolve Sentry issues against the verified release, and confirm the final queue is empty. Use only when the user explicitly asks to handle every or all unresolved Sentry issues, drain or clear the full Sentry backlog, or sweep the complete unresolved queue through production. Do not use for one named incident, investigation-only requests, or requests that do not authorize the necessary repository and production changes.

algorand-devrel Bundle

Builds x402 HTTP-native payment applications on Algorand using Python. Covers clients (httpx, requests), servers (FastAPI, Flask), facilitators, Bazaar discovery, and the x402-avm library. Use when implementing x402 payment flows in Python, creating payment-gated APIs, building x402 facilitators, or integrating the x402-avm package.

roadofriot Skill

Create professional product requirements documents from ideas, existing projects, feature requests and project analysis.

roadofriot Skill

Orchestrate complete software projects from discovery through PRD, architecture, implementation, testing, security and review.

roadofriot Skill

Perform deep repository and software project discovery before implementation.

practical-office Skill

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".

practical-office Skill

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

practical-office Skill

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

practical-office Bundle

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so Practical Office engineering skills know this repo's issue tracker (GitHub default), triage label vocabulary, and domain doc layout. Run once per application repo before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out`.

huruizhi Bundle

Generate and review monthly OKR progress summaries for the technical support team from GitLab OKR data and related project work. Use when collecting personal KR updates, preparing department O/KR reviews, or checking OKR status before a confirmed GitLab update.

fengmo11 Bundle

Use when scanning recent papers, GitHub repositories, Agent Skills, MCP servers, venue rules, AI research tools, or academic workflow updates before planning or revising a paper pipeline. Produces a source-grounded frontier ledger, freshness score, novelty tags, and action backlog.

devcsde Skill

List and filter AI models from OATDA's unified gateway — ChatGPT/GPT-5, Claude Sonnet 4.5, Gemini 3, Grok 4, Qwen3, Kimi K2.7, GLM-5, and 100+ more across 10+ providers. Triggers when the user wants to see available models, pick the right LLM for a task, discover provider-specific parameters for image/video/audio generation, or filter by capability (chat/image/video/audio/vision) and provider. Ideal for model discovery, pricing comparison, and capability lookup before calling other OATDA skills.

m1nga Bundle

Design, audit, repair, and operationalize reliable agent loops with explicit goals, triggers, persistent state, orchestration, independent verification, failure recovery, open skill discovery or creation, experience distillation, controlled self-improvement, and retirement conditions. Use when the user asks to build a loop, autonomous or recurring agent workflow, multi-agent operating system, self-improving process, knowledge/experience distillation pipeline, zero-context recovery flow, permanent update/replacement loop, or to turn a prose plan or repeated prompt into a genuinely executable loop.

nikhil8bph Skill

Expert Business Analyst (BA) workflow for conducting thorough requirement elicitation, comprehensive client discovery grilling, scope definition, and end-to-end requirement documentation. Use when a user shares a new product, platform, feature, or business idea and wants it elicited, discovered, or "grilled"; when defining project scope, boundaries, assumptions, and constraints; when translating ambiguous stakeholder visions into structured BRD, PRD, user stories, or acceptance criteria; or when conducting gap analysis, risk evaluation, and edge-case discovery.