Product & Planning

biomate-ai Skill

Identification of differentially expressed genes and estimation of the False Discovery Rate (FDR) using both the Significance Analysis of Microarrays (SAM) and the Empirical Bayes Analyses of Microarrays (EBAM).

davekilleen Bundle

Report a Dex bug to the Dex team with zero homework — Dex investigates locally, builds a privacy-safe report, shows it to you (or auto-sends if you've chosen that), and tracks the ticket until it's fixed. Use when the user says "report this", "send this to the Dex team", "file feedback", "/feedback", asks "what happened to my bug report", or accepts Doctor's offer to report a Dex bug. Also use when the user describes something in Dex misbehaving in their own words, without asking for a report at all — "the meeting sync is doing something weird", "this keeps breaking", "X stopped working", "that's not what I asked for" — investigate first, then offer. Not for capturing ideas about your own vault or workflow; use the improvements backlog for those. Not for trouble in the user's own notes, calendar or projects, which is never a Dex defect.

davekilleen Skill

Show the AI-ranked backlog of Dex system-improvement ideas. Use when the user says 'show my Dex ideas', 'what's in the backlog', 'what should we build next'. Not for workshopping one idea into a plan; use `dex-improve`. Not for discovering existing features; use `dex-level-up`.

davekilleen Skill

Workshop one improvement idea into an implementation plan. Use when the user says 'let's flesh out idea-X', 'turn this into a plan', 'improve Dex's Y'. Not for ranking the whole backlog; use `dex-backlog`. Not for a PRD for the user's own product; use `product-brief`.

davekilleen Bundle

Groom the open task pool goal by goal: see everything under each quarter goal, confirm doubtful goal links, retire what has gone stale, and mark what gets picked up first when that goal earns week-time. Use when the user says 'groom my backlog', 'what's under this goal', 'my tasks are a swamp', 'clean up my tasks', or when open tasks have piled up untouched. Not for routing new inbox items; use `triage`. Not for setting the week's priorities; use `week-plan`.

davekilleen Skill

Extract a product idea through guided questions and generate a PRD. Use when the user says 'write a PRD', 'spec this feature', 'turn this idea into a brief'. Not for a non-product initiative like hiring or partnerships (use `initiative-kickoff` once shipped); not for checking existing projects' status (use `project-health`).

davekilleen Skill

Define time-horizoned assumptions about your industry (today / 6mo / 12mo) that ground strategic thinking. Use when the user is making roadmap, positioning or investment calls, or says 'what am I assuming about the market'. Also use proactively before a big strategic recommendation. Not for capturing a single decision; use `decision-log`.

davekilleen Bundle

Turn a decision to start something new — a hire, a partnership, a go-to-market push, an internal bet — into a real initiative: the outcome and why now, what success looks like, who's involved, the first concrete steps, and a project page that ladders to your pillars and goals. Use when the user says 'let's kick off X', 'I'm starting a new initiative', 'set up a project for this', or 'we've decided to do Y'. Also use proactively when the user commits to a new effort mid-conversation. Not for spec'ing a product feature or writing a PRD; use `product-brief`. Not for checking the status of projects already underway; use `project-health`.

davekilleen Skill

Turn on local AI-powered semantic (meaning-based) search over the vault, with smart collection discovery. Use when the user says 'enable semantic search', 'search by meaning', 'set up QMD', or search keeps missing obvious matches. Not for scraping the web; use `scrape`.

davekilleen Skill

Review roadmap status, evidence freshness, blockers, and alignment

quantumquirkxyz Skill

Write Product Requirement Documents (PRDs) — problem statement, goals, user stories, acceptance criteria, success metrics, timeline — with stakeholder alignment.

quantumquirkxyz Skill

Design OKR cycles — Objectives, Key Results, initiatives — with measurable outcomes, quarterly cadences, and team alignment.

quantumquirkxyz Skill

Improve professional communication — status updates, stakeholder messages, expectations, and escalation — with clarity and precision.

quantumquirkxyz Skill

Manage professional projects — scope, milestones, risks, dependencies, and stakeholder alignment — with explicit planning and tracking artifacts.

daemon-blockint-tech Bundle

Guides creation of AI token and cost improvement plans—baseline audits, spend attribution, optimization initiative backlog (prompt, context, model routing, RAG, agents), impact estimates, quality guardrails, measurement KPIs, and phased rollout with owners. Use when building a token reduction roadmap, cost optimization program, LLM unit-economics improvement plan, or executive brief on cutting inference spend without breaking evals—not for hands-on context layout implementation (ai-context-engineer), single-prompt rewrites (prompt-engineer), RAG pipeline build (ai-engineer), or AI ops cadence and vendor governance (ai-lead-ops). For end-to-end commercial/enterprise AI solution architecture before cost programs, use applied-ai-architect-commercial-enterprise. Empirical token studies and ablations: research-engineer-scientist-tokens.

daemon-blockint-tech Bundle

Guides product management for human data platforms—annotation and labeling products, workforce workflows, task design, quality systems (gold sets, adjudication, inter-annotator agreement), customer ML-team project delivery, contributor experience, and privacy-safe handling of human-generated training data. Use when prioritizing roadmap for labeling/RLHF/eval data platforms, writing PRDs for annotation or QA features, defining success metrics for throughput and quality, scoping enterprise customer workflows, or balancing cost-quality-speed tradeoffs—not for hands-on model training (data-scientist), warehouse/analytics pipelines (data-warehouse-engineer), generic BRD workshops without product lens (business-analyst), AI solution architecture for copilots (applied-ai-architect-commercial-enterprise), or control implementation for audits (compliance-engineer). UX flows: product-designer. Eval harnesses: prompt-engineer-agent-prompts-evals. Pricing/packaging for platform: product-management-monetization.

daemon-blockint-tech Bundle

Guides engineering managers leading teams that own agent prompts, tool schemas, golden eval suites, judge programs, and prompt regression CI—org design, hiring, roadmap with PM/risk, release governance, and team KPIs for eval quality and prompt stability. Use when managing prompt/eval engineers, prioritizing eval backlogs, staffing harness and judge programs, or governing prompt releases—not for writing prompts or harnesses (prompt-engineer-agent-prompts-evals), vertical AI squad management (engineering-manager-vertical-ai-products), or AI platform SRE (ai-lead-ops).

daemon-blockint-tech Bundle

Guides engineering managers leading vertical AI product teams—industry or domain-specific copilots and AI features (not horizontal platform)—org design, hiring, roadmap with PM and GTM, vertical launch governance (eval, safety, cost), squad capacity, and escalation across shared AI platform and domain experts. Use when managing engineers shipping vertical AI products, prioritizing domain AI backlogs, staffing vertical squads, or aligning AI feature GA with sales and compliance—not for AI architecture ADRs (applied-ai-architect-commercial-enterprise), hands-on RAG/agents (ai-engineer), AI platform SRE and model rollout ops (ai-lead-ops), analytics marts (analytics-data-engineering-manager-product), or generic TPM programs (technical-program-manager). For agent prompt and eval harness work (not people management), use prompt-engineer-agent-prompts-evals. For managing the prompt/eval function (hiring, golden CI policy, judge program), use engineering-manager-agent-prompts-evals.

daemon-blockint-tech Bundle

Guides managers of product-embedded analytics engineering teams—org design, hiring and levels, roadmap and prioritization with product managers, analytics data product delivery, squad alignment, stakeholder forums, team KPIs, and escalation paths for metric and mart quality. Use when leading analytics engineers on product domains, planning analytics roadmaps per product area, resolving prioritization across squads, or defining how marts and metrics ship with features—not for hands-on dbt/SQL (analytics-data-engineer), enterprise data platform ADRs (data-architect), company-wide data governance ops (data-manager), or dashboard UX (bi-analyst). For vertical copilot/RAG product engineering management, use engineering-manager-vertical-ai-products—not analytics-data-engineering-manager-product.

daemon-blockint-tech Bundle

Guides applied AI solution architecture for commercial (B2B SaaS, multi-tenant product) and enterprise (internal copilots, regulated corp data) contexts—reference patterns for RAG, agents, and copilots, platform and model selection, data boundaries, identity, observability, cost at scale, and POC-to-production hardening with security and governance gates. Use when designing customer-facing AI features, enterprise knowledge assistants, vendor LLM integration architecture, AI ADRs for commercial or IT stakeholders, or mapping AI components to SSO/DLP/residency requirements—not for implementing RAG code (ai-engineer), generic multi-service ADRs without AI (senior-system-architecture), AI policy registers (ai-risk-governance), or contract redlines (commercial-counsel). For engineering management of vertical AI product squads (hiring, roadmap, launch governance), use engineering-manager-vertical-ai-products. Labeling PM: product-management-human-data-platform—not this skill.

ghosteken Skill

Writes a plain-prose, start-to-finish narrative of a feature's or project's flow, one throughline per actor (user, admin, buyer, supplier, etc.), grounded in real docs/code/session history — not an engineering spec or PRD, a story a non-technical stakeholder can read end to end. Use when asked to "explain the whole flow", "tell the story of how this works", "walk through this from the user's and admin's perspective", or for a narrative/human-readable walkthrough of a feature or project section.

ghosteken Skill

Writes product-facing feature PRDs grounded in project context or docs you provide — Problem/Solution/Impact framing, user personas, user stories with Given/When/Then acceptance criteria, functional and non-functional requirements, and explicit out-of-scope — either for every feature it identifies in that context, or for one named feature, always keeping a single index of every feature doc produced. Use when asked to "write a PRD for this feature", "break down this project/doc into feature PRDs", or "product requirements" for a feature, before an engineering spec exists.

ghosteken Skill

Provide comprehensive techniques for testing REST, SOAP, and GraphQL APIs during bug bounty hunting and penetration testing engagements. Covers vulnerability discovery, authentication bypass, IDOR exploitation, and API-specific attack vectors.

ghosteken Skill

Maps an unfamiliar codebase into seven evidence-backed documents (stack, structure, architecture, conventions, integrations, testing, concerns) instead of a single freeform summary. Use when asked to map, document, or onboard into an existing codebase — "map this codebase," "document this architecture," "onboard me to this repo." Not for routine feature implementation, bug fixes, or narrow edits unless repository-level discovery is explicitly requested.

ghosteken Skill

Turns a feature PRD into a technical implementation plan — system architecture across frontend/API/business-logic/data/infrastructure layers, database schema, API design, frontend component hierarchy, and security/performance considerations, in prose and diagrams only (no real code). Use when a feature PRD or spec exists and needs a technical design before task breakdown, or when asked for an "implementation plan", "technical design for this feature", or to "turn this PRD into an architecture doc".

ghosteken Skill

Semantic + keyword search and connection-discovery across the user's own Apple Notes via the apple-notes MCP server. Use when the user wants to find, recall, or synthesize something from their notes, or surface non-obvious bridges/related notes. macOS, on-device.

unboundcompute Skill

Turn a security patch or version diff into fresh findings: infer the fixed vulnerability from what the fix changed, reconstruct the pre-patch bug, then hunt the paths the fix did not cover and the same bug in code it never touched. Use when you have a fix commit, a vague advisory with a linked diff, a version bump, or a "security release" and want to know what it silently fixed and what it missed. Covers reading a fix as a treasure map, incomplete-fix analysis, and variant discovery in the same tree and its forks.

vibesec-advisory Bundle

Use when renewal risk signals from usage, support, CRM, stakeholder notes, or commercial context need safe intake and confidence grading.

vibesec-advisory Bundle

Use when renewal save-plan options must stay evidence-based, reviewable, and free of unauthorized discounts, credits, roadmap promises, or custom work.

vibesec-advisory Bundle

Use when redacted discovery notes, transcripts, or meeting fragments need to become structured facts, assumptions, open questions, and internal-only notes.

vibesec-advisory Bundle

Use when an AE needs a pre-call discovery brief from public, CRM-safe, and approved context before a buyer conversation.

vibesec-advisory Bundle

Use when an AE needs a cautious buyer-facing follow-up from reviewed discovery notes without adding unsupported commitments or sensitive internal context.

lamm-mit Skill

Use when predicting molecular structures (proteins, nucleic acids, small molecules, and complexes) with the Chai-1 foundation model via local inference or the Chai Discovery API.

lamm-mit Bundle

Agentic materials discovery and DFT simulation framework using ASE, Quantum ESPRESSO, and Claude LLMs via LangGraph.

lamm-mit Bundle

Access 1000+ scientific tools from Harvard's ToolUniverse — bioinformatics, drug discovery, genomics, clinical research, and more

lamm-mit Bundle

ToolUniverse workflow — Binder Discovery