Product & Planning

legioncodeinc Bundle

Implements end-to-end authentication: provider selection (Clerk / Better Auth / Auth.js / Supabase Auth / WorkOS / Stack Auth / Kinde / Stytch), Google OAuth flows including the October 2025 unused-client-deletion policy and GIS migration, MFA / passkeys, RBAC, session storage, and B2B SSO. Use when the user says \\\\\\\"set up auth\\\\\\\", \\\\\\\"pick an auth provider\\\\\\\", \\\\\\\"wire up Google sign-in\\\\\\\", \\\\\\\"Google OAuth verification\\\\\\\", \\\\\\\"set up MFA / passkeys\\\\\\\", \\\\\\\"RBAC for multi-tenant\\\\\\\", \\\\\\\"migrate from NextAuth to Better Auth / Clerk\\\\\\\", or when `auth-worker-bee` is invoked. Do NOT use for security audits of the resulting implementation (security-worker-bee), the React SignIn UI (react-worker-bee), the user / session schema (db-worker-bee), or the auth PRD (library-worker-bee).

legioncodeinc Bundle

Equips asset-worker-bee with the Universal Asset Registry: the 19-asset taxonomy (Features, Pages, Routes, Surfaces, Controls, Displays, Layouts, NavEntries, DesignTokens, Icons, MediaAssets, Fonts, Motion, Breakpoints, ContentEntries, Translations, FeatureFlagBindings, MeterBindings, Entitlements), the registration workflow, the code-vs-DB drift audit, the sync-generator contract, the deprecation/sunset rules, and the canonical Prisma + SQL schema. Use when registering, auditing, deprecating, or generating sync code for any of the 19 asset types, when checking for drift between code and the registry, or when standing up the registry in a new repo. Not for QA report authorship (use quality-stinger), PRD numbering (use library-stinger), UX design decisions (use ux-ui-svelte-stinger), or security audits of the registry tables (use security-stinger).

legioncodeinc Bundle

Reviews, refactors, and authors React 18/19 codebases using the bulletproof-react architectural pillars and the curated 2025-2026 React ecosystem. Use when the user says \\\"review this React code\\\", \\\"react architecture review\\\", \\\"audit our React app\\\", \\\"state management decision\\\", \\\"what's the bleeding-edge React pattern for X\\\", \\\"propose a React refactor\\\", \\\"is this React anti-pattern\\\", or when `react-worker-bee` is invoked. Do NOT use for visual design (ux-ui-svelte-worker-bee), SEO/Next.js metadata strategy (seo-aeo-worker-bee), security audits (security-worker-bee), or PRD authoring (library-worker-bee).

legioncodeinc Bundle

Designs, audits, and authors Docker / Docker Compose / GitHub Actions / Depot pipelines for Node / Next.js / TypeScript stacks. Use when the user says \\\"review my Dockerfile\\\", \\\"design our CI pipeline\\\", \\\"audit our workflow security\\\", \\\"migrate to Depot\\\", \\\"add a healthcheck to compose\\\", \\\"this build is slow\\\", \\\"we leaked a secret in CI\\\", or when `devops-worker-bee` is invoked. Do NOT use for cloud provisioning (cloud-platform Bees), DB schema or migrations (db-worker-bee, devops-stinger wires the migration step but does not author it), security CVE deep audits (security-worker-bee, devops-stinger surfaces concerns and hands off), or PRD authoring (library-worker-bee).

legioncodeinc Bundle

Equips library-worker-bee with the documentation lifecycle - knowledge-base authoring (public vs private audience split), feature PRD authoring (prd-{###}-{slug}/ with index + sub-PRDs + qa/), issue IRD authoring (ird-{###}-{slug}/ with index + qa/), backwards-PRD generation, sync audits / drift detection, and lifecycle moves (backlog/in-work/completed) against this repo's schema v2 library/. Use when initializing a library/, ingesting issues, planning features, writing knowledge docs, running drift audits, or moving a completed PRD/IRD to its completed/ tier. Not for QA report authorship (use quality-stinger) or narrative knowledge docs (use knowledge-stinger).

legioncodeinc Bundle

Audits a completed implementation against its source plan document and produces a structured findings report. The report goes in the source plan's `reports/` subfolder (e.g., `library/requirements/{lifecycle}/prd-{###}-{title}/reports/{date}-qa-report.md` or `library/issues/{lifecycle}/ird-{###}-{title}/reports/{date}-qa-report.md`); standalone audits go to `library/requirements/reports/{domain}/{date}-qa-report.md`. Use when the user says \\\"QA this\\\", \\\"audit the implementation\\\", \\\"check the plan against the code\\\", \\\"run quality-worker-bee\\\", \\\"verify the PRD was built\\\", or when `security-worker-bee` has just finished and the loop ends with a QA pass before merge. Produces a markdown findings report with scorecard, severity-tagged findings, and a plan-item traceability table. Does not write code, fix issues, or author plans.

legioncodeinc Bundle

Software estimation and forecasting specialist. Covers relative-sizing frameworks (story points, Fibonacci, T-shirt sizing, Planning Poker), the NoEstimates movement and its evidence base, the planning-fallacy literature explaining why estimates are systematically wrong, and cycle-time / throughput-based probabilistic forecasting (Monte Carlo simulation, percentile-based delivery predictions). Invoke when the user says \\\"our story points mean nothing\\\", \\\"should we use NoEstimates?\\\", \\\"how do I do T-shirt sizing for a roadmap?\\\", \\\"we need a 90% confidence delivery date\\\", \\\"explain Monte Carlo to my PM\\\", \\\"why are our estimates always wrong\\\", or any question about sizing, forecasting, or the NoEstimates debate. Do NOT invoke for sprint cadence design, Jira/Linear tool configuration, or team-capacity math -- those belong to the team's agile process or tooling domains.

legioncodeinc Bundle

'Scrum methodology specialist: sprints, ceremonies (Sprint Planning, Daily Scrum, Sprint Review, Retrospective, Backlog Refinement), roles (Scrum Master, PO, Developers), estimation (Fibonacci, Planning Poker, #NoEstimates), Definition of Done templates by maturity, anti-pattern catalog (Scrum-but, Zombie Scrum, HiPPO PO, velocity gaming), framework selection (Scrum vs ScrumBan vs Kanban vs Shape Up), and the \\\"is this actually Scrum?\\\" honesty audit. Use when the user says \\\"audit our Scrum process\\\", \\\"is this Scrum?\\\", \\\"Sprint Planning help\\\", \\\"write our DoD\\\", \\\"retrospective format\\\", \\\"should we switch to Kanban\\\", \\\"Scrum anti-patterns\\\", or when `agile-scrum-worker-bee` is invoked. Do NOT use for project management tooling configuration (Jira, ClickUp), code review (security-worker-bee, react-worker-bee), or general project management without a Scrum context.'

legioncodeinc Bundle

The Svelte 5 + SvelteKit UI enforcement and implementation skill for the OSPRY SvelteKit apps (portal, web, wl). Owns shadcn-svelte 1.x (built on Bits UI v2 + Melt UI), Tailwind v4, the @theme token bridge to the existing PRD-071 design tokens, and the white-label brand contract. Use whenever a PR touches a .svelte file's markup or styling, when adding a shadcn-svelte component, when wiring Tailwind v4 utilities, when bridging an existing CSS custom property into @theme, when verifying an agency brand flows through a component, or when the user says \\\"add a Button\\\", \\\"copy in this shadcn-svelte component\\\", \\\"convert this bespoke style to Tailwind\\\", \\\"does the white-label still work\\\", or \\\"is this on-brief\\\". Do NOT use for the React ux-ui-svelte-stinger's domain (apps/cms Payload chrome) or for bootstrapping a brand-new design system from scratch.

legioncodeinc Bundle

Designs, reviews, and heals vector and embedding storage - schema/column design, index selection (HNSW vs IVFFlat, distance operators), hybrid lexical+vector search, migrations, dataset versioning. Neon plus pgvector plus Drizzle is the primary option for this stack; Deep Lake and Qdrant / managed services remain documented alternatives with a selection matrix. Use when the user says \\\"design this vector table\\\", \\\"which index should this use\\\", \\\"pgvector or Deep Lake or Qdrant\\\", \\\"is this HNSW config right\\\", \\\"wire pgvector into this Drizzle schema\\\", \\\"we need a new embedding column\\\", \\\"how do we heal a missing column\\\", \\\"vector or hybrid search here\\\", or when `vector-store-worker-bee` is invoked. Do NOT use for PRD authoring (library-worker-bee), TypeScript data-access consumption (typescript-node-worker-bee), security audits (security-worker-bee), or recall / embedding retrieval pipelines (retrieval-worker-bee, embeddings-runtime-worker-bee).

legioncodeinc Bundle

Outbound sales specialist for founders running cold email. Covers Apollo / Clay / Smartlead / Instantly / Lemlist tool selection, email deliverability and domain warmup, multi-touch sequence design (3-5 steps), AI personalization without slop (Clay Claygent SKIP rule), reply classification and disqualification, and list hygiene. Use when the user says "set up cold outreach", "my cold email is landing in spam", "write a cold email sequence", "set up Clay personalization", "Apollo vs Instantly", "my reply rate is below 2%", "cold email warmup", "build a list in Apollo", or when cold-outreach-worker-bee is invoked. Do NOT use for inbound SDR workflows, CRM architecture (db-worker-bee), AE discovery call scripts, paid acquisition, or LinkedIn content strategy.

legioncodeinc Bundle

Equips retrospective-worker-bee to run retrospectives that actually change behavior: format selection (Start/Stop/Continue, 4Ls, sailboat, mad/sad/glad, DAKI, Starfish, and more), psychological safety pre-check (Edmondson scale), facilitation playbooks, async retro design, and action-item follow-through discipline. Use when the user says \\\"run a retro\\\", \\\"plan our retrospective\\\", \\\"which retro format should we use\\\", \\\"our retros produce no change\\\", \\\"help with action items from the retro\\\", \\\"how do we do an async retro\\\", or \\\"our team needs better retrospectives\\\". Do NOT use for incident postmortems (different cadence and audience), sprint planning, OKR-setting, or daily standup facilitation.

legioncodeinc Bundle

Designs, reviews, and heals the Hivemind Deep Lake data layer - the 7-table ColumnDef schema, USING deeplake DDL, FLOAT4[] embeddings, additive schema healing, append-only version-bump writes, deeplake_index / vector / hybrid search, DeeplakeApi querying, SQL guards, dataset versioning, and BYOC storage. Use when the user says "design this table", "review this ColumnDef", "is this index right?", "should this be a JSONB column or a tensor?", "we need a new NOT NULL column on the memory table", "how do we heal a missing column?", "vector or hybrid search here?", "which storage backend?", or when `deeplake-dataset-worker-bee` is invoked. Do NOT use for PRD authoring (library-worker-bee), TypeScript data-access consumption (typescript-node-worker-bee), security audits of creds / PII / token handling (security-worker-bee), or recall / embedding retrieval pipelines (retrieval-worker-bee for recall, embeddings-runtime-worker-bee for the embedding model).

legioncodeinc Bundle

OKR methodology specialist for writing, grading, and iterating on Objectives and Key Results. Enforces the output-vs-input discipline, diagnoses sandbagged vs. ambitious goal-setting, calibrates quarterly cadence and check-in rituals, contextualizes OKRs against KPIs and MBOs, and adapts the framework for small teams and startups. Activate when the user says "write OKRs", "audit our OKRs", "are these KRs measurable?", "set up a quarterly goal cycle", "OKR vs KPI", "OKR for small team", "grade our OKRs", or when configuring OKR fields in Lattice, 15Five, Weekdone, or Notion. Do NOT activate for company strategy authorship (executives own that), engineering roadmap planning (domain Angels own that), or project management tooling beyond OKR-specific configuration.

legioncodeinc Bundle

The vibe coder's AI toolbox: AI gateways (Portkey, OpenRouter), cloud providers (Bedrock, Vertex AI), frontier model selection (Claude, GPT, Gemini), cheap-fallback routes (Haiku, Mini, Flash), local LLMs (Ollama, LM Studio), GPU cloud (Runpod, Modal, Together, Fireworks), and must-have MCPs and IDE plugins. Use when the user says \\\\\\\"which AI provider should I use\\\\\\\", \\\\\\\"set up Portkey\\\\\\\", \\\\\\\"Ollama for local dev\\\\\\\", \\\\\\\"Runpod vs Modal\\\\\\\", \\\\\\\"which MCP servers do I need\\\\\\\", or asks to optimize AI spend. Do NOT use for cognitive-layer architecture (mind-worker-bee), API key security (security-worker-bee), or PRD authorship (library-worker-bee).

legioncodeinc Bundle

Continuous product discovery coach — Teresa Torres interview cadence, Opportunity Solution Trees, Jobs-to-be-Done interviews, prototype testing, and the "build less, learn more" loop. Use when the user says "run a discovery session", "build an OST", "write an interview script", "map our assumptions", "design a prototype experiment", "weekly discovery summary", or when a team is unsure what to build next and needs to run discovery before planning. Do NOT use for shipped-feature usability testing (quality-worker-bee), UI design decisions (ux-ui-worker-bee), PRD authorship (library-worker-bee), or analytics result interpretation.

legioncodeinc Bundle

Customer-feedback-to-roadmap loop specialist — Userback, Canny, Featurebase, Productboard, Frill, Productlane — platform selection decision tree, in-app-widget vs portal vs voting-board taxonomy, de-duplication discipline, RICE/ICE prioritization, status-transition policy, public vs private roadmap playbook, and CRM/issue-tracker integration wiring. Use when the user says "set up a feedback system", "which feedback tool should I use", "Canny vs Featurebase", "our feature requests are a mess", "set up a public roadmap", "RICE scoring for our backlog", "Productlane + Linear", "voting board for our SaaS", or when product-feedback-roadmap-worker-bee is invoked. Do NOT use for the React UI of an embedded widget (react-worker-bee), the database schema for a custom-built feedback store (db-worker-bee), marketing copy on the public roadmap page (seo-aeo-worker-bee), or billing integration for premium feedback tiers (payments-worker-bee).

latestaiagents Skill

Implement Agent-to-Agent (A2A) communication for cross-framework interoperability. Use this skill when building multi-agent communication, implementing agent protocols, connecting agents across frameworks, or standardizing agent interfaces. Activate when: agent to agent, A2A, agent communication, agent protocol, cross-framework agents, agent interoperability, MCP, agent discovery.

mrciphersmith Skill

Use by default for project navigation and file discovery before broad raw search, especially when the user asks where something is, what files are related, what might be affected, or needs implementation, review, refactoring, debugging, architecture, dependency, module relationship, import cycle, or orphan-file context.

mrciphersmith Bundle

Generates PRD or Implementation Plan constrained by decisions registry, architecture doc, and best practices. Does NOT invent new architectural decisions. Use when: dispatched by gproject-orchestrator Phase 4. NOT for: direct user invocation.

mrciphersmith Bundle

Project documentation orchestrator — builds PRDs, specs, and implementation plans through a phased pipeline of specialized subagents. Use when: "Create project documentation", "Write PRD for...", "Plan project...", "Document how to implement...", "Spec out feature...", "Project planning", "gproject", "Создай документацию проекта", "Напиши PRD". Make sure to use this skill whenever the user mentions PRD, project planning, technical specification, implementation plan, feature spec, architecture document, project documentation, or wants to plan any software project from scratch or document a new feature in an existing codebase — even if they don't explicitly say "PRD" or "spec". Also trigger on: "how should I build...", "plan out...", "what's the best approach to build...", "document the approach for...", "create a roadmap for...", "spec this out", "write requirements for...". NOT for: code implementation (use job-orchestrator), code review (use code-review skills).

mrciphersmith Bundle

Defines core problems, goals, non-goals, and success metrics from discovery data. Use when: dispatched by gproject-orchestrator Phase 1. NOT for: direct user invocation.

mrciphersmith Bundle

Validates PRD/Implementation Plan against decisions registry, architecture doc, and best practices constraints. Catches contradictions, gaps, and violations. Use when: dispatched by gproject-orchestrator Phase 5. NOT for: direct user invocation.

mrciphersmith Bundle

Researches best practices per technology in the chosen stack and defines application architecture patterns. Produces constraints that PRD must follow. Use when: dispatched by gproject-orchestrator Phase 3. NOT for: direct user invocation.

mrciphersmith Bundle

Use when reviewing or verifying a Metaproject requirements package under docs/requirements for completeness, versioning, README/PRD/spec consistency, schema references, roadmap updates, unsupported claims, and implementation-status accuracy. Usually dispatched by docpack-orchestrator. Not for reviewing autodoc-generated current-codebase documentation.

mrciphersmith Bundle

Use when creating or updating a Metaproject requirements package under docs/requirements: PRD, specification, README, policies/protocols/schemas, roadmap updates, verification, and package review. Use for requests like 'create requirements package', 'prepare module documentation', 'write PRD/spec for module', or 'оформи пакет документации'. Not for reverse-engineering current codebase documentation; use autodoc-orchestrator for that.

alexe-ev Bundle

Build a launch plan including readiness criteria, timeline, channels, and stakeholder coordination. Use this skill when a team is preparing to launch a product, feature, or major update.

alexe-ev Bundle

Distill raw observations and research data into meaningful, actionable product insights. Use this skill when a team has research data and needs to move from observations to insights that can drive decisions.

alexe-ev Bundle

Plan, structure, and synthesize user interviews to generate reliable qualitative insights. Use this skill when a team needs to understand user behaviors, motivations, and problems through direct conversation.

alexe-ev Bundle

Apply the Jobs-to-be-Done framework to understand what job users are hiring a product to do and why. Use this skill when a team needs to understand user motivation at a level deeper than features or demographics.

alexe-ev Bundle

Write clear, complete product requirements documents and user stories. Use this skill when a team is ready to define what needs to be built for a prioritized initiative.

alexe-ev Bundle

Design a metric alerting system with thresholds, alert logic, and escalation paths so teams can detect performance issues before they become serious. Use this skill when a product needs proactive monitoring rather than reactive discovery.

alexe-ev Bundle

Build and validate user personas and segment definitions grounded in real research data. Use this skill when a team needs to define who they are building for with enough specificity to guide product decisions.

alexe-ev Bundle

Structure a technical discovery process to surface feasibility constraints, architectural options, and engineering unknowns before committing to a product initiative. Use this skill when a product bet has significant technical uncertainty.

alexe-ev Bundle

Define the scope, goals, and methods for a product discovery research initiative. Use this skill before running any discovery research to ensure the team is investigating the right questions with the right methods.

alexe-ev Bundle

Turn raw insights into well-structured opportunity statements ready for prioritization or experiment design. Use this skill when a team has research insights and needs to frame them as actionable product opportunities.