ai-marketplace

Use when a development task is unclear, multi-step, risky, or needs coordinated gates for shared understanding, research, parallel lanes, workflow artifacts, and verification. For a single concern, use the matching gate skill if available; for tiny mechanical changes, skip unless the user asks.

Use when development work has independent lanes for research, codebase exploration, inventory, validation, review, or non-overlapping implementation that can run in subagents, parallel tool calls, or separately owned workstreams.

Use when development work is large, risky, multi-session, multi-agent, interrupted, or needs durable plan/handoff memory for continuity across coding agents.

Use when development work depends on current or external facts: latest docs/APIs, library or platform behavior, security guidance, unfamiliar errors, migrations, comparisons, best practices, prior art, or known fixes.

Use when a development request is vague, exploratory, conflicted, under-specified, or the user says they are unsure, wants to be grilled, wants assumptions challenged, or needs goal, scope, constraints, and success criteria clarified before planning or implementation.

Use before saying development work is done, or when choosing project-shaped tests/checks to prove code behavior, bug fixes, refactors, config, infrastructure, or UI changes.

Pi-only web research workflow for environments that have pi-9router-ext and a subagent extension such as @tintinweb/pi-subagents configured. Use this skill when the user explicitly asks to use 9router, pi-9router-ext, ninerouter tools, or a 9router route/combo for web research, or when project/user instructions state that 9router-web-researcher is the preferred research stack. Do NOT use for ordinary web research in standard shared-mcp-only or non-Pi clients; use web-researcher instead. This skill always delegates research lanes to subagents and then synthesizes compact cited findings.

Pressure-tests any idea, plan, or decision through direct decision sparring until every branch is resolved — whether the question is "is this worth pursuing?" or "how do I execute this?" Activate when the user says things like "decision sparring", "spar with this decision", "interrogate my plan", "interrogate my idea", "stress-test this", "drill into this", "poke holes in it", "help me think through whether to pursue this", "I've decided to do X, help me think it through", "help me decide", or similar. Works on any domain - career moves, product launches, hiring plans, technical architecture, business decisions.

Performs intelligent web research by routing queries to the best available search tool — Brave for broad discovery, Exa for semantic/technical/entity-heavy queries, and Tavily for content extraction and deepening. Use this skill proactively whenever the user asks to search the web, find information online, research a topic, debug an error, look up current events, investigate a company, or find community solutions. MUST BE USED for any task requiring up-to-date information from the web. Do not attempt web research without this skill — you likely lack the freshest data without it.

This skill should be used when the user asks to "review my code", "review this branch", "review my changes", "check my diff", "review before merge", "code review", or needs a structured code review analyzing correctness, security, reliability, maintainability, and scalability of git diff changes against a base branch. Use this proactively whenever the user is working on a feature branch and mentions wanting feedback on their changes before merging or opening a PR.

Analyze credit card statement CSV files, categorize transactions, and produce a markdown spending report with month-over-month comparison. Activate when the user says "analyze my credit card statement", "analyze cc statement", "spending analysis for YYYY-MM", "categorize my transactions", "credit card report", "analyze-cc-statements", or provides a month argument like "2026-03" in the context of credit card or transaction analysis.

A sparring partner that pressure-tests raw ideas through natural conversation, then produces a concise Idea Brief. Activate when the user says things like "pressure-test my idea", "idea refinery", "sparring partner", "challenge this idea", "gut-check this idea", "I have an idea", "is this worth doing", "should I pursue this", or "help me decide".

On-demand thinking partner for navigating tricky human dynamics at work. Activate when the user says things like "office politics coach", "help me navigate this situation", "I need a thinking partner for non-technical things", or "I'm dealing with a difficult situation at work".

This skill should be used when the user asks to "write an ADR", "create an ADR", "document an architecture decision", "write an Architecture Decision Record", "document a technology choice", "compare database options", "document why we chose X over Y", or needs to record a specific architectural or technology decision with alternatives and trade-offs (1-3 pages). Use when capturing a decision that needs to be justified and preserved for future reference.

This skill should be used when the user asks to "write a one-pager", "create a one-pager proposal", "draft a one-pager", "write a proposal doc", "create a feature proposal", "write a proposal for sign-off", or needs a concise stakeholder approval document (1-3 pages). Produces focused proposal documents with problem statement, goal, proposed solution, alternatives, and risks.

This skill should be used when the user asks to "write a POC document", "document a proof of concept", "write a POC report", "document an experiment", "write an experiment report", "document technical evaluation results", "write a Go/No-Go recommendation", "capture POC findings", or needs to document hypothesis validation, technology evaluation, or feasibility study results with a clear Go/No-Go decision (3-8 pages).

This skill should be used when the user asks to "write an RFC", "create an RFC", "draft an RFC", "write a Request for Comments", "write a design proposal for cross-team review", "document a complex architecture change", or needs a detailed design document covering architecture, implementation phases, migration, and rollback planning (5-15 pages). Use for complex multi-service changes requiring thorough cross-team review.

This skill should be used when the user asks to "write a TSD", "create a TSD", "write a Technical Specification Document", "document an API", "spec out an API", "write an API spec", "document a data model", "write a technical spec", "create interface documentation", or needs a comprehensive technical specification covering API endpoints, data models, interface contracts, error handling, and versioning (5-20 pages).

Create validated Mermaid diagrams (sequence, architecture, flowchart) with automatic syntax checking and self-healing. Use when users request diagrams, visualizations of API flows, system architecture, or process documentation. All diagrams are validated with mermaid-cli before delivery.

Generate project management plan Excel workbooks (.xlsx) with automated Gantt charts, team charters, budget tracking, and RAID logs. Use when users request a "project management plan", "PM plan", "program plan", "project tracker", "project plan excel", "project plan spreadsheet", or need to create a structured project planning workbook. Follows an interactive 3-phase workflow: brainstorm with the user, get plan approval, then generate the workbook.