Product & Planning

pproenca Skill

This skill should be used when the user asks to "start a story", "start item 3", "run the squad", "advance the story", "continue the pipeline", "kick off the backlog item", or wants work executed through the story stages. It starts a backlog item as a story and drives it stage by stage through the role agents, pausing at every approval gate.

pproenca Bundle

This skill should be used when the user asks to "add a backlog item", "slice this into stories", "turn this doc into stories", "break down this design", "import the vision doc", "load the backlog", or hands over an architecture document, RFC or PRD and wants it turned into work the squad can execute. It slices intent into INVEST-sized items and writes them to .squad/backlog/ without starting any of them.

pproenca Bundle

This skill should be used when the user mentions "the squad", "squad pipeline", "swarmforge", ".squad/", a "story stage", a "story gate", "advance the story", "who owns this artifact", or asks how backlog items become stories and which role writes what. It carries the pipeline contract - stage order, profiles, gates, on-disk state, and role ownership - that the squad-init, squad-backlog, squad-start, squad-status, and squad-approve skills all depend on.

pproenca Bundle

Audit surfaces across a two-sided marketplace to find places that could be personalised but aren't, or design the personalisation approach for a named surface from scratch. Use when asking "where should we personalise next?", "how should we personalise the onboarding flow?", "what could we do beyond the listing feed?", "our paywall is static — how would we personalise it?", "give me a backlog of personalisation opportunities ranked by impact", or "design a personalisation approach for the abandoned-browse email". Covers every surface where a two-sided marketplace can deploy personalisation beyond the obvious listing feed — onboarding branches, paywall timing and copy, trust-copy variants, abandoned-browse re-engagement, saved search alerts, landing hero, first-stay paths for new suppliers, review ordering, zero-result fallback, related listings, messaging templates, push timing, profile-completion nudges, seasonal campaigns, and more. Grounds every recommendation in the research-based marketplace-personalisat

rongxinzy Skill

Plan and execute enterprise technical discovery, outcome-led demos, POCs, solution architectures, competitive responses, and evaluation closeout. Use when a sales opportunity needs technical qualification or evidence for a customer decision.

fudesign2008 Bundle

Queue orchestrator over child engines (goal-driven / solve / opsx-solve / jira-fix / opsx-jira-fix). Triggers when the user says「goal 批量」「跑队列」「任务队列」「无人值守队列」「把需求加入队列」「空闲时段跑任务」/ goal-driven-queue, goal-driven-batch, goal batch, run queue, unattended task queue. Each conversation auto-isolates its backlog under .goal-driven/queues/; intake pre-approval, serial consumption, caps, acceptance. Jira lists enqueue here (also via jira-fix-queue / opsx-jira-fix-queue; legacy triggers jira-fix-batch / opsx-jira-fix-batch). Use to enqueue now and run later, or to start/inspect/review this conversation's queue. Do NOT use for a single ad-hoc long run (goal-driven-workflow), a single Jira issue (jira-fix-workflow / opsx-jira-fix-workflow), or setting up cron/schedulers themselves.

jaygptpro Skill

Optimize a listing for Amazon's AI shopping assistants (Rufus on the web, Alexa+ on devices, and the COSMO ranking layer behind them). Rewrites bullets as question answers, completes the Attributes section, models voice query anatomy, and reinforces with review-language. Use when a user asks about Rufus, Alexa+, AI shopping, AI-driven search, COSMO, conversational shopping, question-style queries, voice shopping, voice search, smart speaker discovery, or conversational query optimization. Trigger phrases. "Rufus", "Alexa+", "AI shopping", "AI search", "COSMO", "conversational query", "question answering", "voice shopping", "Alexa search", "voice query", "smart speaker", "conversational shopping". Works with zero tools.

orkas-ai Bundle

Product Test

orkas-ai Bundle

Product UI

fdiblen Bundle

Covers discovering the research landscape around a topic or project: finding relevant publications (OpenAlex, arXiv, Zenodo, JOSS, Semantic Scholar, Google Scholar) and finding related software - libraries, packages, tools, platforms and competitor or alternative projects - across software registries, archives, package indexes, public forges and curated awesome lists. Use when the user asks what exists on a topic, wants related work, prior art, alternatives or competitors surveyed, needs a state-of-the-field picture for a paper or proposal, or is about to build something whose neighbors are unknown. (RSD-based reuse suggestions with bundled snapshots are rseng-software-reuse; adoption vetting is rseng-dependency-management; verifying found references is rseng-citation-hygiene.)

fdiblen Bundle

Covers running user support as an operation for research software: triaging and answering support requests, converting recurring questions into documentation and FAQ entries, office hours and support channels, forum gardening, and feeding support signals into the roadmap. Use when support questions arrive faster than they are answered, when the same question keeps being answered by hand, when the user asks how to organize support, office hours or a helpdesk for their software, or when support load is invisible to planning.

fdiblen Bundle

Covers discovering and reusing existing research software instead of rebuilding it, using Research Software Directory (RSD) instances such as research-software-directory.org and helmholtz.software. Use PROACTIVELY when a research project is about to implement functionality that likely already exists - data readers, converters, solvers, analysis tools, domain libraries - and when the user asks whether a tool already exists, wants to find research software for a domain, or mentions the RSD. Ships bundled catalog snapshots (data/*.json) for offline candidate suggestions. (Broad prior-art surveys across publications and all sources: rseng-discovery; vetting a chosen candidate: rseng-dependency-management.)

fdiblen Bundle

Covers checking research code and data against data-protection and AI regulation: GDPR obligations in code (personal data discovery, minimization, pseudonymization vs anonymization, retention, data-subject rights, DPIA triggers), the EU AI Act (risk tiers, research carve-out, transparency duties), and similar regimes. Use PROACTIVELY when person-level or sensitive data is evident in the project, and when a project processes personal or sensitive data, trains or ships AI/ML systems, when the user asks about GDPR, the AI Act, DPIAs, consent or anonymization, or before publishing datasets or models derived from people. (Secrets hygiene and protective controls: rseng-security; sensitive-data stewardship: rseng-data-management; AI-use disclosure: rseng-ai-declaration.)

tuya Bundle

该技能专门直接输出小程序面板 PRD、面板需求文档与完整 Markdown 模板。只有当用户是在写小程序面板、小程序设备面板或小程序端需求文档时才使用本技能；用户只要提到小程序面板、面板 PRD、需求文档、完整 Markdown 需求文档、完整 Markdown 模板、章节和表格搭出来、空白模板、产品总览、产品基本信息、DP 点说明、四、小程序功能说明、页面功能说明、附件清单，或要求按模板填写、补全、整理、润色、只写某一章、产出可给产品和研发评审的文档，就必须使用本技能。对于通用 PRD、Web、H5、官网、管理后台、中后台、App、桌面端或其他非小程序面板项目，不要使用本技能，也不要影响这些需求文档的正常编写流程。

ticruz38 Bundle

Natural language to SQL query agent with schema discovery and XML result export. Use when an agent needs to (1) discover and interpret database schemas, (2) convert natural language questions into SQL queries using LLM, (3) execute queries securely, and (4) export results as XML to configurable storage (Google Drive, S3, local, etc.). Fully configurable via environment variables.

swestash Bundle

Review a built project's execution health before a milestone — scope alignment, roadmap / execution-plan adherence, implementation maturity (what's production-ready vs stub/deferred), and the evidence it actually works (tests, coverage, validation results, changelog). Use strategic-review for vision/positioning/market; technical-debt-review for a pure code-health audit.

swestash Bundle

Define OKRs, KPIs, success metrics, and engineering health metrics (DORA). Triggers: OKR, KPI, metrics, success metrics, key results, objectives, measure success, DORA metrics, engineering metrics, velocity, cycle time, deployment frequency, how do we measure, what should we track.

swestash Bundle

Write lightweight project proposals for budget approval and go/no-go decisions — problem, business case, scope, rough estimates, risks, success criteria. Triggers: project proposal, project brief, business case, budget estimate, should we build this, go/no-go, risk assessment, cost-benefit, ROI, justify this project, stakeholder approval.

swestash Bundle

Review a project's strategic position before going public, launching, or raising — vision, mission, value proposition, scope positioning, the defensible wedge, and a live competitive / market comparative analysis. Use project-review for execution/roadmap/implementation health; delegates deep market scans to deep-research.

swestash Bundle

Strategic codebase health assessment — identify hotspots, categorize debt, produce remediation roadmap.

ma08 Skill

Use local read-only iMessage, WhatsApp, and LinkedIn channel access wrappers for raw message discovery, sample exports, and CRM provenance workflows.

involvex Skill

Current Ethereum development tools, frameworks, libraries, RPCs, and block explorers. What actually works today for building on Ethereum. Includes tool discovery for AI agents — MCPs, abi.ninja, Foundry, Scaffold-ETH 2, Hardhat, and more. Use when setting up a dev environment, choosing tools, or when an agent needs to discover what's available.

kirodotdev Bundle

Use when the user hands over a goal too large for one session ("clear the flaky-test backlog", "take this feature from design to PRs", "push these N PRs green") and wants the fleet's state to be readable rather than inferred. Own a long-horizon goal end to end while tracking it in the work ledger - decompose it into items, stand up one session per item, read each worker's reported status as structured data rather than as a transcript, verify claims with the acceptance evaluator, and decide each next round until the goal is met or a stop condition fires.

kirodotdev Bundle

Use when a security conductor session is being seeded, or when inspecting/debugging one. Operating procedure for the kirocrew-security-conductor agent - run proactive vulnerability discovery on one target as a supervised fleet. Decompose the target into attack surfaces, dispatch one auditor per surface behind the rules of engagement, dispatch an independent verifier per finding whose job is rejecting false positives, adjudicate severity, hold the two human gates, run a retrospective that proposes lessons, and report upward.

drn Skill

Generate an implementation plan from a PRD, tech spike, or feature spec and save it to context/plans/. Use for planning work, breaking down a PRD, or creating an implementation plan from a spec.

drn Skill

Analyze a spec, PRD, or codebase to identify missing skills and agents, propose them, then write them. Use for skill gap analysis, agent gap analysis, bootstrapping agent capabilities from a spec, or equipping a project with skills.

drn Skill

RICE-scored backlog prioritization. Use for sprint planning, feature prioritization, or backlog grooming.

servosity Bundle

Every Zammad ticket, article, and Knowledge Base operation as one CLI and MCP server - plus a team-management layer (agent load, customer health, aging backlog, escalation triage, churn risk, feedback mining) the Zammad API can't answer in a single call. Trigger phrases: `who is overloaded in support`, `which customers are at risk`, `what tickets are open too long`, `who should we escalate`, `what feedback are we getting`, `search zammad tickets`, `use zammad`, `run zammad`.

servosity Bundle

The first MSPbots tool anywhere - readable filters, alias-named resources, full exports, and the KPI history MSPbots itself doesn't keep. Trigger phrases: `pull the open tickets dataset from MSPbots`, `export MSPbots data to CSV`, `snapshot our MSPbots KPIs`, `is our ticket backlog up or down this week`, `what columns does this MSPbots dataset have`, `use mspbots`, `run mspbots-cli`.

irahardianto Skill

Session bootstrap + workflows for Pathfinder semantic navigation tools. Covers: discovery protocol, tool chaining patterns (explore, impact, audit, debug), search optimization, LSP degraded mode, and error recovery.

irahardianto Skill

Feature flag patterns ONLY when PRD/arch requires. Flag evaluation, lifecycle, testing, infrastructure. Do NOT load speculatively.

kirodotdev Skill

Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes and no verification happen here.

muxammadmamajonov Skill

Run founder/business discovery at project start, before specs or code. Use for 'start a project', 'scope an idea', or vague requirements — produces the discovery-answers artifact.

muxammadmamajonov Bundle

Classify the project into type(s), pick a matching preset, and surface cross-cutting concerns — after discovery, before stack selection. Use at project start or for 'which preset should we use'.

muxammadmamajonov Skill

Turn discovery and classification into testable functional/non-functional requirements with acceptance criteria. Use before architecture/build, or when a feature needs verifiable specs.

r-irbe Bundle

USE FOR: per-question Lean 4 research — picking a research method (Mathlib grep / Web / repo grep / sub-agent), running the discovery ladder for Mathlib/Loogle/Reservoir/GitHub/literature lookups, choosing depth (Shallow / Standard / Deep / Exhaustive), emitting a findings + recommended-strategy + Zettel triple, integrating with the Rumsfeld epistemic matrix and the review council, running a typed protocol (M / T / L / S / D / X / E). DO NOT USE FOR: full council convocation (use @research-council); synthesis emission (use @research-synthesis-engine); package adoption or Lake dependency decisions (use @lean-package-research); proof writing (use @lean-proof); review (use @lean-review-council). TRIGGERS: research, mathlib lookup, find lemma, theorem search, Loogle, Moogle, Reservoir, package search, literature search, web search, what does X mean, typed research, M protocol, T protocol, L protocol.