Product & Planning

loopyluci Skill

Use when prioritizing product roadmaps.

loopyluci Skill

Use when applying drug discovery troubleshooting.

loopyluci Skill

Use when applying biomarker discovery troubleshooting.

loopyluci Skill

Use when implementing OKR frameworks.

dvcrn Bundle

PIV workflow orchestrator - Plan, Implement, Validate loop for systematic multi-phase software development. Use when building features phase-by-phase with PRPs, automated validation loops, or multi-agent orchestration. Supports PRD creation, PRP generation, codebase analysis, and iterative execution with validation.

dvcrn Bundle

Search B2B leads and companies, find/validate emails via Generect Live API. Use when the user needs to find people by job title/company/industry, search companies by ICP, generate business emails from name+domain, or validate email addresses. Covers lead generation, prospecting, enrichment, and email discovery workflows.

dvcrn Bundle

Crypto trading: swap, perps, transfer, pay, deposit (credit card / crypto), withdraw, AI chat, market discovery, x402 payment, autopilot. Built-in wallet via Minara CLI. EVM + Solana.

dvcrn Bundle

Kanban Workflow is a TypeScript skill for a stage-based agentic co-worker that integrates PM platforms via CLI-first adapters (CLIs or small wrapper scripts). It provides setup + verbs (show/next/start/update/ask/complete/create) around a canonical stage set (backlog/blocked/in-progress/in-review), plus polling/diffing foundations and automation hooks.

dvcrn Skill

Complete multi-agent collaboration workflow for product-driven development loops. Covers the full lifecycle from product discovery through architecture design, parallel coding, testing, to marketing. Includes 6 specialized agents (Product, Core Dev, Dev, Test, Marketing, Research) with defined roles, communication protocols, and shared file conventions. This skill should be used when setting up or understanding the DevLoop agent collaboration system, configuring agent workflows, troubleshooting inter-agent communication, resolving agent responsibility questions, or customizing agent behavior through SOUL.override.md and MEMORY.md.

dvcrn Bundle

Skill for Amazon product research, market validation, competitor analysis, ASIN review, pricing guidance, and product opportunity discovery. It turns ecommerce data into structured seller workflows such as category evaluation, product discovery, competitor comparison, and research reporting. It uses APIClaw (apiclaw.io) as its data source. This skill requires one credential, `APICLAW_API_KEY`, used only for requests to the APIClaw API. Triggers on requests like "Amazon product research", "find products", "analyze competitors", "analyze this ASIN", "pricing strategy", "market validation", and "is this niche worth entering".

dvcrn Bundle

Operate Alibaba Cloud DataWorks through dynamic API discovery and official SDKs (Node.js, Python, Java). Covers data development, workflow operations, data integration, data quality, metadata lineage, workspace management, and more. APIs are discovered at runtime from official docs and OpenAPI metadata — no hardcoded list.

dvcrn Bundle

Universal AI-powered web scraper for any platform. Scrape data from Instagram, Facebook, TikTok, YouTube, Google Maps, Google Search, Google Trends, Booking.com, and TripAdvisor. Use for lead generation, brand monitoring, competitor analysis, influencer discovery, trend research, content analytics, audience analysis, or any data extraction task.

tomevault-io Bundle

Leveraging fuzzing to assist LLM agents with IoT firmware vulnerability discovery Use when this capability is needed.

teqfocusadmin Skill

docs (living docs people share, comment on and edit; use only when the user asks for one: names a doc, document, page, memo, spec, PRD, runbook or write-up, asks for somewhere to share or keep editing something, or says yes to your doc offer; a plan, comparison, summary or notes asked in chat stays in chat (at most a one-line doc offer); a report, status update, recap or "something I can send them" with no form named → ask first: reply, doc or file?; tabs hold tables and live charts too; a pasted claude.ai/code/artifact/… link may be a doc: check with docs tools first; not HTML pages, apps or plain chat answers; a .docx/.pptx/.xlsx/PDF asked for by name → that format's skill): asked for one → no docs-connector instructions in context? call the docs connector's `guide` with topic.instructions first, then create the doc (headings only, no body) before any search, file read or plan, even with files attached. Documenting code means docstrings or repo docs, not a doc.

teqfocusadmin Bundle

Teqfocus Presales Agent skill. Use this skill whenever a sales rep, AE, SDR, or BDR needs: first-call preparation, offering match, competitive wedge, proof point retrieval, discovery question frameworks, objection handling, pitch drafts, or deal-stage guidance — for any Teqfocus prospect conversation. Also triggers when someone asks "what do we pitch," "what's our angle," "how do we position against [competitor]," "do we have a case study for X," "how should I open this call," "draft me a follow-up email," or "what's the next step for this deal." This skill governs the first 60% of any prospect conversation. When the ask is bigger than chat-grade (full proposal, RFP response, UI mockup), this skill routes to the correct workshop tool: proposal-creator skill for single-shot proposals, Cowork pipeline for formal RFPs. Always load this skill before writing any presales or first-call asset.

teqfocusadmin Bundle

Teqfocus Solution Design skill. Use this skill whenever a technical solution design document is needed for any Teqfocus engagement — across any technology: Salesforce, Snowflake, Databricks, AWS, Azure, GCP, Anthropic Claude API, MCP agents, custom application builds, or data transformation. Triggers include: "create a technical design", "write the solution architecture", "build the technical spec", "design the solution", "map the requirements to components", "write the tech design for this deal", or any request for a deliverable architecture document a delivery team or technical stakeholder can act on. This skill is Agent 6 in the Cowork proposal pipeline. It fires after scope is confirmed, produces a reviewable technical design, then routes it through the escalation framework. FLOW: Create the design first. Then escalate for review. Never escalate an empty brief.

tinyc0der Skill

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a capability map, and when deciding whether that map stays on one Feature track or an Epic parent with child tracks.

datnt-cell Bundle

Shared protocol and First Contact Checklist for the Unity Skills plugin — REST server discovery, operating mode, schema layers, batch execution, dryRun gate, surface profile, and error codes. Every other unity-* skill in this plugin (scene-authoring, rendering, ui, scripting, networking, etc.) depends on this protocol. Read this FIRST, before the first REST call in a session, whenever the user wants to actually operate the Unity Editor from chat. Not needed for conceptual Unity Q&A that touches no Editor state. 当用户要从对话里实际操作 Unity 编辑器时，先读本协议，任何语言均可触发。

teqfocusadmin Bundle

Sales enablement skill for Teqfocus — a Salesforce Summit Partner and full-stack Data, AI, and Application transformation company. Use this skill whenever the user wants to create any asset that helps the sales team sell more effectively or move deals forward. This includes: sales decks, vertical pitch decks, one-pagers, battlecards, competitive positioning guides, objection-handling guides, discovery question frameworks, proposal templates, case study sell sheets, SDR call scripts, and meeting follow-up templates. Also trigger when the user mentions sales collateral, deal support, pitch preparation, competitive intel, handling objections, or building a sales kit. Always use this skill before writing any Teqfocus sales enablement asset — do not attempt from memory alone.

jrudman25 Skill

Perform a thorough codebase review covering code quality, security vulnerabilities, performance, and architecture. Use this skill whenever the user asks to "review the codebase", "check the code", "audit the repo", "look for issues", "do a code review", or any similar request — even if phrased casually like "can you look over this?" For requests about launch, deployment, shipping, or production-readiness verdicts, use `production-ready` instead. Also trigger when the user asks about specific problem areas like "are there any security issues?" or "is the architecture solid?". If the user specifies a focus area, apply only the relevant lenses and note explicitly that the rest of the codebase was out of scope. Update or create TODO.md with unresolved findings, but ask before modifying application code or infrastructure. Output is a priority-ordered action list grouped by severity. Do not use for agent skill discovery, comparison, or auditing; use `find-skills` instead.

teqfocusadmin Skill

Structured decision-support frameworks for Teqfocus GTM calls that are judgment calls, not asset production. Use whenever the user needs to decide between options, diagnose why something failed, prioritize competing work, navigate a stakeholder conflict, or run a post-mortem, rather than draft a piece of content. Trigger on phrases like "should we kill this," "which wedge for this account," "help me decide between Tier X and Tier Y," "why did this deal stall," "what's our angle here," "run a post-mortem on," "we have too much competing for this week," or "walk me through the trade-offs." This is a governance/thinking tool, not a content skill, pairs with but does not replace campaign-designer, abm-intelligence, or the production skills. Always loads teqfocus-gtm context (wedges, tiers, CTAs, defaults) before running any framework here.

helius-labs Bundle

Build Solana trading and intelligence applications combining OKX DEX aggregation with Helius infrastructure. Integration-only layer — describes when and how to compose OKX tools with Helius tools for swaps, token discovery, smart money signals, meme token analysis, and portfolio intelligence.

scdenney Skill

Runs several language models as independent coders on the same labeling or discovery task and reads their disagreement as data — panel assembly for model diversity, keeping votes independent, consensus rules, agreement statistics (Cohen's and Fleiss kappa, Krippendorff's alpha), the correlated-errors caveat that stops agreement being mistaken for validity, human validation beyond the panel, and reporting. Use when the user asks about a council, panel, ensemble, or jury of models, asks how to combine several models' labels, or asks what kappa or alpha to report for model coders. Single-model codebook and validation work goes to text-classification, per-item confidence to llm-calibration-logprobs.

athola Bundle

Autonomous orchestrator for manifest work items through the development lifecycle. Use when running egregore to process a backlog automatically.

athola Bundle

Curate the web-capture index. Use when the capture backlog grows, captures sit unprocessed at seedling/pending, or to surface stored research during work.

athola Bundle

Scores backlog items with RICE/WSJF/Kano and files GitHub issues for top candidates. Use when triaging a roadmap or prioritizing features for a sprint.

athola Bundle

Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review. Use when packaging tribal knowledge. Do not use for one skill.

northraystudio Skill

Evaluate code quality across five pillars (Architecture, Reliability, Observability, Security, DX) and produce a 1-10 scorecard with a strategic improvement roadmap. Use when you want a comprehensive quality review of a directory or module. Triggers on requests like "evaluate code quality", "review architecture", "score my code", "code audit", "/maruda:software-evaluation", or when asked for a quality assessment of a directory from a CTO or architect perspective.

maiconsouza89 Bundle

Classifies how urgent an issue or ticket is as p0, p1, p2 or backlog from the impact signals in its text, and justifies the level. Use when "what priority is this issue", "is this a p0 or a p1" or "triage the priority of this ticket". Do NOT use for sizing the work (use mass-issue-complexity) or for writing a pull request description (use mass-pr-description).

moltis-org Skill

BluOS CLI (blu) for discovery, playback, grouping, and volume.

amornsit Bundle

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants the changes since a fixed point reviewed, or when another skill hands finished work off for review.

holmesrm88 Bundle

Estimate story points for unpointed Jira stories ahead of a grooming session, calibrated against how the team's past work actually went rather than against generic heuristics. Also runs in calibration-only mode to learn a team's pointing patterns from completed stories and surface where estimates and reality diverge. Use when preparing for grooming, backlog refinement, or sprint planning — "point the backlog", "estimate these stories", "prep for grooming", "how long will this take", "calibrate the estimator". Do NOT use to evaluate people's performance or throughput; this skill operates at team level only and refuses individual analysis.

dgusoff Bundle

Use when a manager or senior engineer wants to capture what they know so others can use it — "create a brief", "build a brief on", "capture what I know about", "brain dump", "let me dictate my thinking", "onboarding guide for my team", "document how we actually do this", "write up the tribal knowledge", "knowledge transfer for my project", "make a one-pager on this process" — or when someone asks a question against an existing brief ("what does the brief say about"), asks to update one, or submits a document to be checked against one. Do not use for meeting or transcript summaries (use meeting-intel), for status updates to stakeholders (use stakeholder-comms), for engineering review comment matrices or backchecks (use comment-disposition-build or comment-backcheck), or for formatting an existing document with no knowledge capture involved.

tetef Bundle

Flash and test Cortex-M firmware on real Cloudhil benches over HTTPS. Use when the user writes, debugs, or benchmarks STM32, LPC, ARM embedded C, DSP, TinyML, NPU latency, Nucleo, Discovery, or bare-metal ELF — and when you would otherwise say you cannot run it on hardware.

lbachelotcapitalb Bundle

Passer une session de travail Claude Code d'une machine à une autre via git, ET piloter une roadmap autonome multi-steps sur le VPS avec auto-continuation. Utilise-le quand l'utilisateur veut : déléguer/reprendre le travail ailleurs (« reprends sur le VPS », « bascule sur ma machine ») ; lancer une roadmap autonome sur le VPS depuis le desktop (« lance la roadmap sur le VPS », « exécute ces steps en autonomie », session visible dans code.<ton-domaine>) ; ou faire un état des lieux des sessions Claude du VPS (« montre-moi les sessions du VPS », « tableau des sessions »). Softcodé via .claude/handoff.json — marche pour tout couple de machines partageant le même remote.

kikakikakikakika Bundle

Use this skill whenever a designer or researcher describes a design problem, product challenge, or research question and wants help choosing a research method or planning research. Trigger when someone says things like "I need to research...", "we want to understand users better", "how should I validate this", "what research should I do for...", "I'm working on [problem] and need to find out...", or describes a design stage (discovery, ideation, validation, post-launch) alongside a question. Also trigger when someone describes a habit-driven method choice ("I was going to do user interviews") and you should challenge whether that's the right fit. This skill guides Claude to first recommend the right research method, then generate a ready-to-use research draft (discussion guide, survey, test plan, etc.) tailored to the problem.