Product & Planning

gerardordz96 Bundle

Use when someone wants to set up recurring/automated cadence — build, optimize, or audit a Claude Code Routine (cloud scheduled agent via /schedule), a local hook, a /loop, or a daily-*/weekly-* ritual skill. Triggers on "schedule this", "automate X weekly", "make my AIOS run itself", "wire a recurring job", "attack our cadence gap". Runs a decision gate and Discovery Interview, then a mandatory supervised test before arming anything.

imyourboyroy Bundle

Run the Portable Web Toolkit bundled WCAG accessibility evidence gate (Playwright + axe). Use for a11y audits on toolkit-managed Astro sites. Never resolve AI/wcag-auditor. Ensure Playwright Chromium is installed in the client project first. After every run, open and share the stakeholder dashboard HTML with the user.

imyourboyroy Bundle

Run Portable Web Toolkit discovery-doctor to verify robots, sitemap, llms, humans, security.txt, content APIs, and JSON-LD for toolkit-managed sites. Use before deploy on dist output and after production deploy on the live URL.

jasonlo Skill

Automated weekly skill discovery for GitHub Actions. Runs the shared discovery pipeline against the user profile, filters against installed skills, and opens a GitHub issue with ranked recommendations. Triggers on "weekly discover", "automated discovery", "skill recommendations".

mauriciovieira 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 to review a branch, a PR, work-in-progress changes, or asks to "review since X".

methasit-pun Skill

Turn a one-line feature or system objective into a complete, step-by-step construction plan for a TypeScript DDD clean architecture project. Each step is self-contained so a fresh agent can execute it cold. Use this skill whenever the user says "plan", "blueprint", "roadmap", "how do we build", "design the system for", or describes a feature that spans multiple layers (domain → application → infrastructure → presentation). Also trigger when the user asks to break down a bounded context, design an aggregate, or plan a new module.

assafkip Bundle

PRD creation and PRD execution operating system. Use when the founder asks to turn a rough idea into a PRD, run a Codex review on a PRD or issue, decompose an approved PRD into issue specs, or execute an issue with scope enforcement and receipt-based closeout. Not for general product ideation or casual drafting; this is the formal gated workflow.

assafkip Bundle

Engineering discipline distilled from a forensic read of one model's work. Use when building a feature, fixing a bug, writing tests, hardening a data path, or running any task that spans multiple files, sources, or sessions. Two layers: how to RUN the task (stage it, verify each stage with a check that can fail, write done-criteria) and how to WRITE the code (recon before edit, verify against a copy with a negative self-test, single-writer chokepoints, scar-anchored why-comments). Ships a paired hook that deterministically blocks a test from touching live data, the one habit a machine can enforce.

dividedby Bundle

User-invoked audit that hunts high-leverage improvements in a repo and produces a small set of epics with an ordered roadmap — reconciled against the existing backlog, not filed beside it.

dividedby Bundle

Turn a briefed backlog into a safely-running unattended agent loop.

dividedby Skill

Orchestrates a multi-module design session — prereq self-check, frontend routing stamp, issue clustering, module/seam design via codebase-design, TDD-ready issue rewrite, and batch tracker mutation — for a PRD + published backlog that spans two or more modules. Use when module and seam choices are still implicit after /to-issues has run.

pratikshadake Bundle

Shifts thinking from feature delivery to measurable user or business outcomes. Use before building a feature, during roadmap planning, or while defining success metrics to ensure work ties to real results.

pratikshadake Bundle

Detects unrealistic planning and hidden delivery risks like overcommitment, missing dependencies, resource mismatches, and undefined metrics. Use when reviewing quarterly roadmaps or sprint plans.

pratikshadake Bundle

Reveals hidden disagreements between stakeholders before execution begins. Use when kicking off cross-functional projects, planning launches, or sensing misalignment between teams on goals or priorities.

programmeranthony Skill

使用 tracer-bullet 竖向切片方法把 PRD 转换成多阶段的落地实施计划，并保存为本地 Markdown 文件（存放在 `./plans/`）。适用于用户希望把 PRD 拆分为多个阶段、生成实施计划、从 PRD 推导阶段计划，或提到 “tracer bullets”。

programmeranthony Skill

通过用户访谈、代码库探索与模块设计来编写 PRD（产品需求文档），然后以 GitHub issue 的形式提交。适用于用户希望编写 PRD、创建产品需求文档，或规划一个新功能。

programmeranthony Skill

使用 tracer-bullet 竖向切片法，把 PRD 拆分成彼此独立、可以直接认领的 GitHub issues（并形成对应的实现工单）。适用于用户想把 PRD 转成 issues、创建实现任务，或把 PRD 拆成工作项。

qfeius Bundle

Use when preparing or updating the local Make development environment before development. Triggered by Make 环境安装, Make 环境初始化, 更新 Make 环境. Does not manage Make resources, deploy Apps, or write PRD, DSL, Service, or UI code; use makecli for resource/deploy operations and the owning skills for implementation.

rdoser13 Skill

SEO content strategy assistant for any website or brand. Use when asked to plan, prioritize, or update a content strategy — including mapping blog post ideas to content types, prioritizing posts by funnel stage and keyword intent, auditing a content plan, identifying content gaps, or making strategic decisions about what to write next. Also use when asked about SEO goals, competitor landscape, content clusters, or publishing cadence. Trigger phrases include "content strategy", "what should we write next", "content plan", "SEO roadmap", "content audit", "content gap analysis", "editorial calendar".

rudra-ravi Bundle

Plan Frida instrumentation across Android, iOS, native libraries, desktop processes, Gadget, agents, setup, discovery, hook strategy, tracing, and skill routing.

rudra-ravi Bundle

Discover Frida hook points with frida-trace, class and method enumeration, module/export/import/symbol discovery, stack traces, Stalker, and probe narrowing.

santos-sanz Bundle

Build MECE issue trees for complex business problems. Use when you need rigorous problem decomposition, branch prioritization, and a decision-ready analysis backlog.

traderspost Skill

Build a spec-to-file widget system where users describe a widget in natural language and Claude scaffolds a working React component into the project. Use when the user wants to add an "AI-generate this UI panel" feature, an extensible plug-in system using filesystem discovery, or wants users of their app to author components without touching code.

vaibhav0806 Bundle

Run evidence-backed B2B lead routing, account qualification, discovery, pilots, pipeline hygiene, forecasting, and follow-up. Use when a founder needs to research or qualify accounts, prepare or document sales calls, define stages, inspect a pipeline, or produce a forecast; use partnerships-channel for referral, reseller, SI, co-sell, or white-label motions.

vaibhav0806 Bundle

Diagnose a startup's current non-engineering bottleneck and route founder requests to focused strategy, discovery, metrics, marketing, launch, sales, fundraising, hiring, operations, customer-success, or governance workflows. Use for broad or cross-functional startup operating questions; invoke a focused skill directly for a clearly bounded domain task.

vaibhav0806 Bundle

Make evidence-backed startup choices about markets, ICP, category, moat, business model, pricing logic, strategic priorities, and roadmap economics. Use when founders must choose where to compete or what to validate next; use customer-discovery for gathering missing buyer evidence and brand-positioning for market-facing messaging.

vaibhav0806 Bundle

Design and synthesize customer interviews, problem research, evidence ledgers, and validation experiments. Use when founders need to learn whether a real customer has an urgent problem or test a risky assumption; do not use it to manufacture testimonials, pitch during research, or replace product analytics.

vermapragya Bundle

Analyzes A/B test results with significance testing, confidence intervals, sample ratio mismatch check, guardrail evaluation, and a stakeholder-ready readout. Use when the user mentions A/B test results, experiment readout, test analysis, lift, significance, p-value, treatment vs control, or asks "did the experiment work."

vermapragya Bundle

Structures a stakeholder-ready analysis writeup with TL;DR, evidence, decision, and next steps. Use when the user asks for a readout, analysis writeup, insight doc, exec summary, "share this with the team", "make this stakeholder-friendly", or "summarize the findings."

wjgoarxiv Bundle

Configure, diagnose, and prove language-server support through Copilot CLI native LSP surfaces, including root discovery, semantic operations, and graceful failure cases.

capitalone Bundle

Turn an open-ended idea into a PRD plus a runnable definition of done. Use when a developer wants to start a new feature, "file a PRD", "spec out" or "scope" an idea, think through what to build, or kick off the harness for a piece of work. Produces prds/<feature>/prd.md + an executable prds/<feature>/run-prd-test.sh on a prd/<author-slug>/<feature> branch. The one human-attentive skill in the chain.

capitalone Bundle

Reads a PRD (`prds/<feature>/prd.md`) plus its executable `run-prd-test.sh` (and any helper artifacts under `prds/<feature>/`), grounds them in codebase research, and produces `specs/<feature>/mainspec.md` plus dependency-ordered slices. Encodes the runner as a slice success criterion so implementation completion implies `./prds/<feature>/run-prd-test.sh` exits 0. Touches `specs/<feature>/.planning-done` as its final committed action. Agent-first — no human-in-the-loop.

capitalone Bundle

Respond to an automated reviewer's findings on the current feature PR — a narrow, headless responder. Triages each reviewer finding into Clear / Ambiguous / Complex / Out-of-PRD-Scope, then acts — fixes the cause and pushes (diff-only) for Clear, posts one in-thread reply for the rest. Skips findings it already handled. Invoked headless by the dispatcher's feedback gate; the dispatcher owns the round counter and the STUCK escalation. Triggers - address-feedback, address review comments, respond to PR review, handle reviewer findings, PR feedback loop (project)

clawdotnet Skill

Extract structured insight briefs from community research transcripts or notes. Produces pain points, stakeholder needs, opportunity maps, risks, and follow-up questions. Requires human review before publication.

dennisonbertram Bundle

This skill should be used when the user asks to "walk the issues", "work through github issues", "groom and implement issues", "tackle the issue backlog", "start the issue loop", "go through tickets", "work all open issues", "clear the backlog", "process all tickets", or "close out open issues". Orchestrates an end-to-end workflow: groom all open GitHub issues with subagents, then loop through them one-by-one - branching, researching, implementing with swarms, testing, committing, merging, and creating PRs until all issues are complete.

devantler-tech Skill

Repository maintenance for devantler-tech/platform — issue triage, manifest/Helm/Flux investigation & fixes, Helm chart + Actions version bumps, Kustomize cleanup, stale-PR nudges. Static validation only — never runs a cluster. Use when performing autonomous or on-request maintenance of this repo.