Product & Planning

luongnv89 Bundle

Scan open GitHub issues for dependencies, priority, parallel work, and staleness. Use to prioritize the backlog or pick what to do next. Don't use for one-issue analysis (/issue-analysis), resolving (/issue-resolver), or creating (/issue-creator).

luongnv89 Bundle

Create an atomic PR closing a GitHub issue end-to-end via a 6-step pipeline. Use to resolve, fix, or implement issue #N. Don't use for analysis without fixing (/issue-analysis), reviewing a PR (/issue-pr-review), or bulk backlog work (/auto-pilot).

mabaeyens Skill

Cross-project snapshot for the Mira project. Invoke explicitly with /mira-status to get git log, server health, and backlog — do NOT auto-invoke at session start.

marsloting Skill

Apply RICE / ICE / WSJF / MoSCoW prioritization frameworks when ranking multiple feature ideas, backlog items, experiments, or initiatives. Use whenever 用户 asks "哪个先做" / "这个值不值得" / "怎么排序" / "优先级排一下" / "rank these" / "should we do X first". Forces explicit scoring on Reach × Impact × Confidence ÷ Effort (RICE) or job size / time-criticality / risk-reduction (WSJF). Stops gut-feel prioritization, forces dimension-by-dimension reasoning, surfaces hidden Confidence assumptions, separates "feels important" from "scores high". Self-contained methodology — no external docs required.

mattpocock Skill

Turn the current conversation context into a PRD and publish it as a GitHub issue that is ready to receive sub-issues from /to-issues-project. Project-local variant of /to-prd, adapted for this repo's PRD-as-parent-issue + sub-issues + agent:implement workflow.

mattpocock Skill

Break a PRD into native GitHub sub-issues attached to the parent PRD. Project-local variant of /to-issues, adapted for this repo's PRD-as-parent + native sub-issues + agent:implement multi-session workflow. Argument is the parent PRD issue number.

mattpocock Skill

Survey the codebase, pick ONE high-leverage deepening opportunity (filtering out anything already proposed), and publish it as a PRD-shaped GitHub issue via /to-prd-project. Designed to run unattended in the daily architecture-review workflow.

rimagination Bundle

Build, debug, and run Google Earth Engine Python and geemap workflows. Use for Earth Engine/geemap authorization, authentication, Cloud project setup, quotas, notebooks, browser map previews, Python scripts, 5,000+ official/community GEE dataset discovery, bilingual dataset selection by id/theme/task, dataset recommendation/comparison/verification, geospatial export, Sentinel/Landsat/MODIS/VIIRS/SAR/population collections, interactive maps, JavaScript-to-Python migration, local GIS integration, remote-sensing AI methods such as detection, segmentation, change detection, pixel regression, SAM, embeddings, vision-language models, QGIS GeoAI, or OpenGeo/opengeos patterns such as GeoAgent, GeoLibre, leafmap, anymap, GEE agents, and catalog-driven assistants. Prefer this skill for reproducible GEE/geemap setup, notebooks, batch exports, map-first AI workflows, GeoAI method execution, and auth/quota/project troubleshooting.

rimagination Skill

Use this skill whenever the user wants to download academic papers, search for research literature, get citations (BibTeX/RIS/EndNote), manage WebVPN institutional proxy for paper access, import .bib files, or batch-download papers. This skill orchestrates the scansci-pdf MCP server which exposes 17 high-level tools covering download (OA/grey/institutional channels), discovery, queue preparation, diagnostics, and login. TRIGGER when: user mentions downloading papers, DOI, arXiv ID, Sci-Hub, paper search, literature review, citation export, WebVPN, institutional access, "帮我下载论文", "搜索文献", "批量下载", "论文下载", "文献检索", or provides a list of DOIs/arXiv IDs. SKIP: user is only discussing papers conceptually without intent to download/search/cite, or user asks about non-academic PDFs (invoices, reports, etc.).

romain-nicod Skill

Produce a weekly market-watch briefing as a PDF: harvest a topic across official sources, keep only what moves a market position, verify every item against a primary source with a confirmed date, and write each entry so it says what it changes for the reader's roadmap. Use when the user asks for a weekly watch, a market briefing, a competitive digest, a "what happened this week in X" recap, or asks to run their standing watch.

romain-nicod Skill

Scan transcripts, meeting notes, chats, or any input for backlog item opportunities, and produce a structured markdown file of candidates with user stories, acceptance criteria and routing for everything screened out. Use when the user says 'backlog scan', 'scan for backlog', 'backlog items', 'find backlog opportunities', 'extract backlog', or provides a transcript or document and asks to identify actionable items for a product backlog.

romain-nicod Skill

Turn a meeting transcript into minutes people act on: decisions separated from the actions that execute them, risks separated from the assumptions the room has settled on, backlog candidates held to an admission test, and a sensitive-content filter run before anything is drafted. Includes a verification pass against the transcript that catches invented product names. Use when the user says 'minutes', 'meeting minutes', 'write up this meeting', 'weekly', or provides a transcript (.vtt, .docx, .odt, .txt) and asks for a write-up.

roman-pinchuk Skill

Use when operating Cloudflare through the technical-preview `cf` CLI, including authentication, account or zone context, API resources, local resources, command discovery, and JSON output.

sanqi-cd Bundle

根据学习目标、当前基础、时间约束和应用场景，设计从入门到实际运用的个性化学习路径，并交付可勾选、可保存进度的单文件 HTML 成长地图。适用于“规划学习路线”“从零掌握一项技能”“备考证书”“规划转岗学习”等请求。Use when a learner needs a personalized, executable roadmap with milestones, practice tasks, evidence, and review loops rather than a generic resource list or schedule.

sgomez Bundle

Orchestrates unattended spec delivery — loops over a spec's child issues in dependency order, dispatching dispatcher (complexity triage), code-author (implement), and diff-reviewer (review) workers per sub-issue, with a review→fix cycle until CLEAN, then merging per the repo's merge policy. Tracker- and host-agnostic — issues and changes live wherever docs/agents/issue-tracker.md and docs/agents/code-host.md say (GitHub via gh is the factory default). Factory defaults are parallel execution and manual merge; repo defaults live in docs/agents/developer-defaults.md and per-run flags (--parallel/--sequential, --auto-merge/--no-auto-merge) override them. Use when user says "/developer", "deliver this spec" (or "deliver this PRD"), "deliver this sub-issue", or wants the build→review→fix pipeline.

varunk130 Skill

Structured competitive teardown for product discovery - surface the 4-6 dimensions buyers actually weigh, score every competitor on each, and identify exploitable gaps. Use when: competitive analysis, competitor teardown, market positioning, where do we win, where do we lose, competitive gap analysis, competitor audit.

varunk130 Skill

Triages a backlog of raw customer feedback into a ranked list of opportunities scored on reach, severity, strategic fit, and confidence. Outputs a prioritized list with explicit "do not act" callouts for vocal-minority signals. Use when: triage feedback, prioritize feature requests, customer feedback backlog, what should we build next, opportunity scoring, RICE feedback, feedback synthesis.

vignesh-s7 Skill

Core Product Owner orchestration. Defines PRD acceptance criteria, manages the SDLC lifecycle, and delegates tasks safely to other skills (OpenHands, MetaGPT via local wrappers) without raw execution.

vignesh-s7 Skill

Convert a one-page PRD into a full SDLC artifact set — architecture, DB schema, code skeleton, eval harness, and deploy config — by routing through MetaGPT / OpenHands / Promptfoo with PO-grade guardrails baked in (Y-Score readiness, regulated-AI checks, anti-hallucination patterns).

vignesh-s7 Skill

Score a PRD or pilot against the 7-dimension Y-Score launch-readiness rubric (problem clarity, target user, success metric, constraints, compliance, eval plan, rollback). Returns a 0-100 score plus per-dimension findings and a go / no-go recommendation. Use when a PO is deciding whether a pilot is ready to launch, especially in BFSI / healthcare / regulated domains.

vinayakkulkarni Bundle

Nuxt agent-readiness guidelines for making a site operable by autonomous AI agents — not just cited by them. Covers the isitagentready.com standards: Markdown content negotiation, RFC 8288 Link headers, RFC 9727 API catalogs, Agent Skills discovery indexes, WebMCP browser tools, MCP Server Cards, OAuth/OIDC agent auth discovery, and DNS-AID. Triggers on tasks involving agent-ready, isitagentready, MCP, WebMCP, model context protocol, agent skills, API catalog, well-known discovery, agent auth, DNS-AID, A2A, or agentic commerce.

carbonshow Bundle

Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written spec.

cdatasoftware Skill

Use when writing Java (or other JVM language — Kotlin, Scala) application code that connects to a data source through a CData driver, after the connection and SQL have been validated with the cdata-cli discovery skill. Covers the CData JDBC Driver edition: reusing the same jar cdata-cli already downloaded and activated, putting it on the classpath (or adding it as a Maven/Gradle dependency), and connecting via JDBC (DriverManager, the jdbc:<source>: URL, PreparedStatement). This is the JVM build-phase companion to cdata-cli.

cdatasoftware Skill

Use when writing application code in Node.js / JavaScript / TypeScript — or any non-JVM language (Go, PHP, Ruby, Rust, C/C++) — that connects to a data source through a CData driver, after the connection and SQL have been validated with the cdata-cli discovery skill. Covers the CData ODBC Driver edition: confirming the system-installed driver, configuring a DSN or a DSN-less connection string, and connecting via the language's ODBC bindings (e.g. the Node `odbc` package). This is the cross-language build-phase companion to cdata-cli — the fallback for any environment that speaks ODBC.

cdatasoftware Skill

Use when writing C# / .NET application code (also VB.NET, F#) that connects to a data source through a CData driver — after the connection and SQL have been validated with the cdata-cli discovery skill. Covers mapping the language to the CData ADO.NET Data Provider edition, adding the provider from NuGet (CData.<Source>), activating its license, and connecting via the ADO.NET classes (<Source>Connection / <Source>Command). This is the .NET build-phase companion to cdata-cli; invoke it whenever the target application runs on .NET.

cdatasoftware Skill

Use when writing Python application code that connects to a data source through a CData driver — after the connection and SQL have been validated with the cdata-cli discovery skill. Covers mapping the language to the CData Python Connector edition, downloading the connector wheel from CData's Python repository, activating its license, and connecting via DB-API 2.0 (cdata.<source>.connect). This is the Python build-phase companion to cdata-cli; invoke it whenever the target application language is Python (Salesforce, Snowflake, Jira, Gmail, etc.).

chalosalvador Bundle

Summarize what got done in a date window from git history, in plain language. Covers every configured repo (and, for a monorepo, each workstream), collapses squash-merged PR duplicates into one item per feature, groups by repo and day, and flags repos or days with no commits. Supports one-liner, short-paragraph, or day-grouped-bullet output, a fixed three-section standup draft (Yesterday / Today / Blockers, keyword-led bullets, derived blockers) — or renders a Slidev slide deck for a stakeholder update, from a bundled generic template and stylesheet. Use when asked "what was done today / yesterday / this week", for a daily standup draft or commit summary, a Friday rollup, "give me a one-liner of today's work", or a weekly-update deck / slides / status deck.

christianmerkwirth Bundle

Applies TRIZ in Agile workflows for morphological backlog refinement and prototype effects extraction.

ckrough Bundle

Ethical analysis through COMPASS persona. Evaluates stakeholder impact, assesses long-term reputation risks, applies moral frameworks including Rawls' veil of ignorance. Use when considering values alignment, regulatory trajectory, second-order consequences, or determining whether something should be done beyond whether it can be done.

cobuchan Bundle

Execute the NEXT (or a named) story in a PRD tracker file end-to-end — read the story spec from the JSON, mark in_progress, decide spawn-vs-inline based on complexity, run required gates, update the tracker with completed_date and implementation_notes. Companion to `prd-creation`. Use when the user says "continue with <story-id>", "next PRD story", "execute <story>", "step through the PRD", "what's next on the PRD", or "let's do the next one". This skill governs execution once a PRD tracker JSON exists, however it originated — whether created directly by `prd-creation` or handed off from some other planning process. Batching multiple PRD stories in one session, when the user opts in, is a legitimate variant of this same mechanism, not a different one.

cobuchan Skill

Standard format and workflow for creating PRDs with JSON stories. Includes schema, complexity rules, agent selection, and completion checklist. Use when creating product requirements, writing user stories, or planning feature work with structured tracking.

codealive-ai Bundle

Deep research over the Semantic Scholar Graph API. Covers endpoints missing from allenai's lookup skill — paper references (backward citations), recommendations, batch paper lookup (up to 500 IDs), snippet search, and multi-hop citation graph traversal (BFS forward/backward). Use when the user asks to build a citation graph, expand a literature seed, find related work, run a reference network traversal, explore what a paper cites or what cites it beyond simple lookup, or batch-resolve many DOI/arXiv/S2 IDs. For multi-step research questions, delegate to the deep-paper-researcher subagent to keep the main context clean. Not for single paper-by-ID lookups (use semantic-scholar-lookup) or topical discovery (use web_search_advanced_exa).

tanstack Bundle

Retrieve machine-readable context with tanstack libraries, tanstack doc, tanstack search-docs, tanstack create --list-add-ons --json, and --addon-details for agent-safe discovery and preflight validation.

tanstack Bundle

Generate, update, and version a complete skill tree (collection of SKILL.md files) for any JavaScript or TypeScript library. Produces core skills (framework-agnostic) and framework skills (React, Solid, Vue bindings) with dependency linking. Activate when producing skill files from a domain map, updating existing skills after a library version change, or auditing skill accuracy. Takes domain_map.yaml and skill_spec.md from domain-discovery as primary inputs.

tanstack Bundle

Analyze library documentation and source code, then interview maintainers to discover capability domains and task-focused skills for AI coding agents. Activate when creating skills for a new library, organizing existing documentation into skill categories, or when a maintainer wants help deciding how to structure their library's agent-facing knowledge. Produces a domain_map.yaml and skill_spec.md that feed directly into the tree-generator skill.

technomaton Skill

Create a new backlog item (Initiative / Epic / Feature / Story / Defect / Event / Risk) — V2 local-first. ID allocated from id_counters.yaml, parent hierarchy validated by MCP edpa_item_create, YAML written under .edpa/backlog/, auto-committed. No GitHub calls at create time; PR-derived signals arrive separately via the contribution-sync workflow.