Product & Planning

carlheath Bundle

Meta-skill for creating structured documents using proven templates. [VAD] Creates PRDs, RFCs, ADRs, project briefs, proposals, specs, meeting notes. Template-based document generation with quality checklists. [NÄR] Use when: create document, new document, document template, write PRD, create RFC, write ADR, project brief, proposal, specification [EXPERTISE] Document architecture, structured formats, stakeholder communication

danielleit241 Bundle

Use OpenAI Codex CLI (GPT-5.5 + gpt-image-2): second-opinion code review, GitHub PR audit, plan/spec auditing, edge-case discovery, style/persona prompting, and subscription-billed image generation for visual assets, banners, infographics. Activate on 'codex', 'second opinion', 'audit plan', 'review PR with codex', 'generate image', or 'create banner/illustration/visual asset'.

danielleit241 Bundle

Fast codebase scouting using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal (Explore) agents by default, with an opt-in external Gemini CLI path (consent-gated, off by default).

danielleit241 Bundle

Generate short handoff reports from Git branches, remote refs, worktrees, unfinished plans, and roadmap docs. Surfaces priority-ranked next steps with checkbox progress and rationale. Use when the user asks what's in flight, wants progress/next steps, is in a fresh worktree or detached checkout, or needs end-of-session status.

danielleit241 Bundle

STRIDE + OWASP-based security audit with optional red-team persona discovery loop, lightweight secret/vulnerability pattern scan, and guarded auto-fix. Scans code for vulnerabilities from multiple attacker perspectives (auth attacker, supply chain, insider, infrastructure), categorizes by severity, and can iteratively fix findings with a regression guard.

danielleit241 Bundle

Target a real Google Chrome profile for browser automation through Chrome DevTools MCP. Provides the chrome-profile CLI, profile discovery, live DevTools probing guidance, setup playbooks, and URL-anchor tab selection.

brandonburrus Skill

This skill should be used when breaking a spec, plan, PRD, or feature into work units for an issue tracker such as GitHub Issues, Jira, Rally, or Linear. It applies when the user says "break this down into tickets", "create issues from this spec", "slice this into stories", "decompose into work units", "turn this plan into tasks", or "create the epics and stories". It should not be used for a single-session implementation plan you will execute yourself right now (use create-code-plan) or for writing the spec being decomposed (use spec).

brandonburrus Skill

This skill should be used when a request, idea, topic, or direction is unclear, underspecified, or likely bigger than it first sounds, and must be understood from every angle before any work starts. It flips the script: the agent relentlessly questions the user until everything discovered is explicitly in scope, out of scope, or deferred, ending in a user-confirmed scope contract. It also applies when a mostly defined request carries just a couple of load-bearing unknowns; a lightweight mode asks only the 2-3 targeted questions those need. It applies when the user says "interrogate me", "grill me", "interview me", "question me until you get it", "clarify this", "refine this idea", "stress-test my thinking", "poke holes in my idea", "define the scope", or "am I missing something". It should not be used for writing the resulting PRD or tech spec (use spec), or for single-fact ambiguities that one direct question resolves.

brandonburrus Bundle

This skill should be used to test whether a product or business idea is worth building before committing to build it: identify the riskiest assumption, design the cheapest experiment that could falsify it, run it, and turn the evidence into a go/pivot/kill decision. It applies when the user says "validate my idea", "should I build this", "is there real demand", "test this before I build it", "design an experiment to test X", "customer interviews", "user research questions", "the Mom Test", "users say they want it but don't buy", "smoke test", "concierge MVP", "pretotype", or "riskiest assumption". It should not be used for sizing a market or reading the competitive landscape from desk research (use research-market), for refining a vague idea's intent before any test exists (use interrogate), for choosing between solution approaches (use research-solutions), or for writing the PRD once the idea is validated (use spec).

brandonburrus Skill

This skill should be used when triaging incoming issues, bug reports, or feature requests on any tracker (GitHub Issues, Jira, Rally, Linear), including evaluating new issues, requesting missing information, marking work ready for implementation, or closing out-of-scope requests. It applies when the user says "triage the backlog", "what needs my attention", "look at issue #42", or "prep these issues for agents". It should not be used for creating work breakdowns from specs (use decompose), for fixing the bug itself (use fix), or for prioritization roadmapping across quarters.

brandonburrus Skill

This skill should be used to decide what to build next and in what order from a set of candidate features, bets, epics, or backlog items. It applies when the user says "prioritize the roadmap", "what should we build next", "rank these features", "what's the priority", "RICE these", "value vs effort", "sequence the backlog", "what do we cut", or "what's most important to ship this quarter". The deliverable is a ranked and sequenced list with the reasoning and the explicit cut pile. It should not be used for defining what one feature is (use spec), for breaking a chosen item into tasks (use decompose), for triaging individual incoming issues (use triage-backlog), or for choosing among technical approaches to one problem (use research-solutions).

brandonburrus Skill

This skill should be used when handling code-review feedback received on your own pull request or change: triaging reviewer comments, deciding what to accept versus push back on, implementing the accepted fixes, and replying to reviewers. It applies when the user says "address the review comments", "respond to the PR feedback", "the reviewer asked for changes", "handle the CodeRabbit comments", or pastes reviewer feedback to act on. It should not be used for reviewing someone else's PR (use review-pull-request), for working an issue tracker (use triage-backlog), or for creating the PR itself (use pr).

brandonburrus Skill

This skill should be used when responding to a live production incident or outage: a service is down, users are blocked, an alert is firing, data is at risk, or someone declares a SEV. It applies when the user says "prod is down", "we have an outage", "the site is down", "users can't log in", "sev1", "sev2", "page the team", "mitigate this now", or "stabilize the system". The skill drives stabilization, severity classification, and stakeholder communication during the incident, then hands the rest off. It should not be used for the internal engineering RCA after the fix is validated (use write-post-mortem), for debugging the root cause itself (use fix), or for pre-release deploy preparation (use prepare-for-deploy).

brandonburrus Skill

This skill should be used to turn raw product feedback into themes, the pain behind each, and the opportunities they point to. It applies to user interviews, support tickets, app reviews, survey free-text, sales notes, or churn comments, and when the user says "synthesize the feedback", "what are users saying", "themes in this feedback", "go through these support tickets", "what are the top pain points", "make sense of these reviews", or "cluster this feedback". The deliverable is signal-ranked themes grounded in quoted evidence. It should not be used for quantitative analysis of a dataset (use analyze-data), for code-review feedback on your own PR (use review-pr-feedback), for writing the spec a theme leads to (use spec), or for deciding build order across themes (use prioritize-roadmap).

brandonburrus Skill

This skill should be used when writing educational or tutorial content that teaches from first principles, including concept explainers, how-to guides, onboarding docs, and API walkthroughs. It applies when the user says "write a tutorial for", "explain X in a doc", "a how-to for", "onboarding doc", or "walk readers through X". It should not be used for persuasive documents where the goal is stakeholder buy-in rather than reader understanding (use write-proposal).

product-on-purpose Bundle

Audits the boundary judgments that silently define a problem frame. For each of four sources, who benefits, who decides, whose knowledge counts, who has standing, it contrasts the descriptive is boundary against the normative ought boundary, names the gaps, and lists the affected-but-excluded parties who have no voice in the frame, producing a boundary-judgment audit rather than a stakeholder round-up. Use when a plan, metric, or proposal already encodes who matters and who does not and the risk is solving a tidy problem for the people inside the line while pushing harm onto people outside it, when an improvement claim rests on an unexamined judgment about whose improvement, or on contested, value-laden, multi-party situations.

product-on-purpose Bundle

Generates several genuinely different framings of an ambiguous problem by varying altitude, stakeholder, and goal-versus-implementation, then selects the most useful one to solve and produces a reframed problem statement with How Might We angles. Use when a problem is vague, arrived as a symptom or a pre-baked solution, or before committing significant work to solving the wrong thing.

product-on-purpose Bundle

Produces a stock-flow map by separating a quantity that accumulates from the inflows and outflows that change it, then reasoning about the stock's trajectory from the net flow rather than the direction of any single flow. Use when a problem involves an accumulation (cash, debt, backlog, headcount, customer base, technical debt, emissions) and intuition about whether it is rising or falling may be wrong.

willakins Bundle

Create Croft Airtable tasks with defaults for Will Akins in Eng Backlog Current Sprint, low priority, and a current-sprint-by-assignee view hint. Use when Codex needs to create a new Airtable task and the caller provides the task name, with optional overrides for assignee, status, priority, pipeline, table, or other task fields.

willakins Bundle

Compare recent GitHub pull requests against Croft Airtable task records and decide which PRs already map to tasks, which PRs need new Airtable tasks, and which matched tasks should be updated. Use when Codex is preparing an Airtable sync, checking backlog coverage for recent coding work, or auditing whether recent PR activity is represented in task tracking.

willakins Bundle

Query and summarize Croft Airtable task tables with defaults for Will Akins in Eng Backlog Current Sprint while excluding In Staging and In Prod. Use when Codex needs to look up tasks by assignee, status, search text, alternate Croft task tables, or semantic Airtable views such as "By assignee" or "Current Sprint".

kinhluan Bundle

Use when validating that a real-world problem exists before defining JTBD or writing code. Triggers on "is there demand for this?", "how do I validate this idea?", "should we build this?", or before any MVP scope decision. Combines multiple signal sources to produce a Problem Statement with confidence level.

l4ci Bundle

Use when the user wants to rank a backlog of product initiatives or features by expected value per unit of effort using Intercom's RICE model. Calibrates the goal, the Reach time window, the Impact scale, the Confidence levels, and the Effort unit first, then estimates each initiative in parallel, one subagent per initiative, before computing RICE = (Reach × Impact × Confidence) / Effort, ranking, running a sensitivity check on Confidence and Effort, and recommending a roadmap order in a markdown report. Triggers include "RICE", "RICE score", "RICE prioritization", "prioritize the backlog", "rank these features", "what should we build first", "score our roadmap", "reach impact confidence effort".

l4ci Bundle

Use when the user wants a stakeholder analysis or stakeholder map of a project, change, or decision, or asks who they need on board and how to engage them. Identifies the stakeholders, then fans out one analyst subagent per stakeholder in parallel to assess power, interest, current stance, interests and fears, and how to engage them, then synthesizes a power-interest grid, a per-quadrant engagement plan, the supporter coalition, the set of blockers, and the highest-leverage relationships to shift, in a detailed markdown report. Triggers include "stakeholder analysis", "stakeholder mapping", "power-interest grid", "power/interest matrix", "Mendelow", "stakeholder management", "who do we need on board".

l4ci Bundle

Use when the user wants to assess an organization's digital maturity across strategy, customer experience, technology, data, operations, people and culture, and innovation, scoring each on a five-level scale and producing a gap analysis and roadmap. Fans out parallel assessor subagents per dimension, then synthesizes the maturity profile, the binding gaps, and a sequenced roadmap in a detailed markdown report. Triggers include "digital maturity", "digital maturity assessment", "how digitally mature are we", "digital transformation readiness", "maturity model".

phuc-nt Bundle

Fast codebase scouting using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal (Explore) and external (Gemini/OpenCode) agents.

phuc-nt Bundle

Generate short handoff reports from Git branches, remote refs, worktrees, unfinished plans, and roadmap docs. Surfaces priority-ranked next steps with checkbox progress and rationale. Use when the user asks what's in flight, wants progress/next steps, is in a fresh worktree or detached checkout, or needs end-of-session status.

robsonrung Bundle

Create, audit, improve, or package SKILL.md workflows and their supporting resources. Use for skill authoring, discovery problems, or workflow simplification. For project instruction files, use agents-md-craft.

robsonrung Bundle

Turn a settled decision record into a PRD for user approval. Use after interview-me or a settled product discussion; to-tasks consumes the approved PRD.

robsonrung Skill

Break an approved PRD into reviewable vertical slices and publish the approved task queue. Use when planning implementation tasks; implement-tasks handles model approval and execution.

robsonrung Bundle

Settle feature and design choices through interview rounds of up to five questions. Use --auto for a bounded two-role evidence-based interview; otherwise ask the user before a PRD.

timlai666 Bundle

This skill MUST be used when research, analysis, evaluation, diagnosis, discovery, insight, or study-design tasks require deciding between qualitative, quantitative, or mixed-methods approaches, and SHOULD be used whenever the user does not specify a method or the work needs both measurement and explanation.

timlai666 Skill

This skill MUST be used when designing, analyzing, teaching, or facilitating service design tools — especially the Ecosystem Map (生態系地圖) and Service Blueprint (服務藍圖). Trigger on requests involving 服務設計、服務藍圖、生態系地圖、前台後台分析、利害關係人地圖、服務流程優化、服務旅程、接觸點、 service blueprint, ecosystem map, stakeholder mapping, service design workshop, CJM to blueprint, or any request to diagram/analyze/teach service delivery systems. SHOULD also be used when someone uploads a service blueprint PDF or asks to turn a service journey into a blueprint structure.

vigneshbarani24 Skill

Use when performing SAP Basis or system administration tasks — transport management, user administration, background jobs, system monitoring, HANA administration, support pack maintenance, or system landscape management across DEV/QAS/PRD.

vigneshbarani24 Skill

Use when the user wants a pre-built, industry-aware solution package for a common SAP end-to-end process. Accelerators provide 60% pre-filled deliverables, pre-mapped process flows, known gap patterns, and proven configuration sequences — cutting weeks of discovery into hours.

vigneshbarani24 Skill

Use when releasing transport requests through the SAP transport landscape. Enforces pre-release checks, dependency validation, and proper CTS workflow — DEV → QAS → PRD with quality gates at each stage.