Product & Planning

ndisisnd Bundle

The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes `/intake`. Owns the requirements interview — fleshes out thin ideas, proactively suggests adjacent ideas, splits compound/hybrid asks and ideas grading C:8 or higher into discrete rows, and grades every idea in a single-turn banded judgment (complexity / token-cost / sequencing). Feeds `plan-pm`, which drafts the PRD. Also owns `--update`: use it when the user says "update that idea", "change the goal on #4", "edit the backlog row about search", or "fix the idea I logged" — it lists the un-shipped rows and edits one in place. And `--delete`: use it when the user says "delete that idea", "remove row #4", "drop that from the backlog", or "I logged that by mistake" — it warns about what the removal breaks, then removes the row on confirmation.

ndisisnd Bundle

Engineering Manager skill. Reads an approved PRD, runs pre-flight checks against AHA.md, GLOSSARY.md and ARCHITECTURE.md, auto-runs plan-review certification inline (no ask), identifies specialist agents to activate (roster approval — the single human gate), spins them up to write engineering sections directly into the PRD, then synthesises the full output. Sizes itself on the PRD's intake grade: a medium PRD runs one fused plan+build wave behind one certification, a large PRD keeps the two-wave path with a certification before each. Runs in --team mode by default (an Opus orchestrator engineer decomposes each wave into file-disjoint, model-tiered packets fanned out to leaf eng subagents) or --solo (one leaf subagent per roster stack). Refuses without a referenced PRD .md path.

ndisisnd Bundle

Principal PM skill — the autonomous PRD writer. Consumes a graded, fleshed-out row from the INTAKE.md backlog (idea, goal, type, grade) and drafts the full PRD solo — feature/acceptance table, edge cases, error handling — saved to features/planned/prd-[n]-[feature-slug]/. The requirements interview lives in /intake now, not here. Pauses ONLY for batched open questions the draft couldn't resolve and for breaking/critical touches. Refuses requests that would skip the PRD stage entirely.

ndisisnd Bundle

The CI gate. Takes a feature branch from "eng says done" to "PR open against staging with green checks". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → open PR. Emits a severity-graded verdict JSON. Absorbs the old /review and /test. Activates on /pre-merge after eng --build.

ndisisnd Bundle

Staff PM contract certifier. Reads an existing PRD and runs a fixed seven-check certification — each check tied to a named downstream consumer (regression authoring, pre-merge's PRD-consistency gate, the safety pauses, eng --build's row/ticket reads). Product tune (--product) runs checks 1/2/3/6; eng tune (--eng) runs 2/4/5/6/7. Auto-selects the tune type from PRD content (no ask), auto-fixes every Critical and Major with a compact terminal table, asks once about Minors, and pauses only for a product-decision finding. Each auto-fixed Critical/Major writes a category-tagged learning to devkit/AHA.md so the next plan-pm draft self-heals. Applies all fixes directly to the PRD file, and logs its findings to one growing report per PRD at reports/review-prd-[n]-[slug].md.

seazhusp Bundle

测试用例评审工具 - 对比现有测试用例与需求文档，找出用例缺失或需要补充的地方。核心能力：支持Excel格式用例与Word/PDF/PRD/图片格式需求文档的比对分析，智能识别功能覆盖缺口，输出用例补充建议。触发场景：评审用例、用例补充、对比需求、检查用例完整性、需求覆盖分析、补充测试点、缺漏用例

seazhusp Bundle

针对 PRD、原型、接口文档、用户故事或已有用例，进行需求分析、全维度测试点提炼、测试用例设计与编写、审核覆盖缺口，并可直接导出带样式/可筛选的 Excel（.xlsx）或 CSV 以导入禅道/TestRail/飞书多维表格。用户要求生成、设计、编写、补充、评审测试用例，或明确要求导出 Excel/xlsx/表格文件、禅道/TestRail 导入时使用。

seazhusp Bundle

This skill should be used when the user submits a requirements document (PRD / BRD / 用户故事 / 技术方案 / 设计文档) or asks to review one for logic flaws, missing edge cases, ambiguous definitions, and business/technical risks before development or testing begins. Triggered by phrases like "审查需求", "审计 PRD", "需求评审", "检查需求缺陷", "这份需求有什么问题", "帮我找需求漏洞". It acts as a strict requirements/logic auditor that outputs a structured, evidence-based defect report in Chinese.

seazhusp Bundle

建立和维护业务知识库的 Skill，适用于需要让大模型理解自身业务以辅助测试的团队。知识库包含需求文档、接口文档、历史缺陷库等结构化内容。支持从多种输入源导入：PRD 文档（docx/pdf/md/图片）、Swagger/OpenAPI 规格、Postman 集合。触发场景包括：建立/初始化知识库、从 PRD 文档导入需求、从 Swagger/Postman 导入接口、添加/更新需求文档、添加/更新接口文档、添加缺陷记录、查询业务知识、根据知识库生成功能测试用例、生成接口自动化脚本、生成UI自动化脚本、更新索引、维护知识库结构。

shreyasbh02 Bundle

Generates comprehensive, structured test cases from feature descriptions, user stories, requirements, or acceptance criteria — and exports them as a formatted Excel (.xlsx) file ready for use in Excel or Google Sheets. Use this skill whenever the user mentions: "write test cases", "generate test cases", "create test scenarios", "test coverage", "QA testing", "test a feature", "test this requirement", "positive/negative test cases", "edge cases", "boundary value testing", or shares a user story / requirement and wants it tested. Also trigger when user says "I need to test X" or pastes a Jira story, BRD, or PRD excerpt expecting test output. Always use this skill for test case creation — even if the request seems simple, a structured Excel output is almost always more useful.

simplerdevelopment Skill

Create, list, inspect, and embed booking pages from the SimplerDevelopment portal. Two flows — (A) embed an existing booking page into a CMS page, deck, or email via the `booking` block (or `booking-menu` for all-services), or (B) author a new booking page via `booking_pages_create` + `booking_pages_update`, which mints an approval URL whose approval flips `active=true` so `/book/<slug>` starts accepting reservations. Returns the public `/book/<slug>` URL. Use when the user says 'add a booking widget to this page', 'embed the discovery call booking', 'create a new booking page', 'set up consulting hours', 'add a calendar to the email'.

stevevitali Bundle

The closeout procedures the tail REC.* tickets invoke — backlog + operational readiness, spec reconciliation, and the integration plan — for a multi-session build. Use it when a build's tickets have landed and the tail rows (from decompose-spec) call 'invoke reconcile-build mode=…', the way P22.x tickets called refresh-repo-docs. Reads the committed build memory (DEFERRALS, ADRs, OPEN FINDINGS, the coverage matrix, BUILD_INDEX) and writes the backlog / reconciliation / integration artifacts. Not a sequencer and not a merge tool.

yaphet2015 Bundle

Use when stress-testing an idea, design, plan, architecture, PRD, or implementation approach before coding.

yishu5 Skill

把需求、原始 PRD、竞品分析、零散笔记或模糊产品想法提炼成可直接发给 Claude Code、Codex 或其他编码 Agent 的精简中文 Markdown PRD。触发：用户说“帮我写一个用来vibe coding的PRD”、要求整理 coding-agent-ready PRD/spec/prompt，或希望从业务/产品材料中抽取实现所需信息。

yishu5 Bundle

将访谈纪要、业务需求、现有 PRD、用户反馈或零散方案整理成写给业务、产品、设计、研发、测试和管理者评审的标准中文 PRD。触发于‘正常 PRD’‘正式 PRD’‘业务 PRD’‘写给人看的 PRD’或要求补全、改版现有 PRD；不用于直接发给编码 Agent 的实现 Spec 或 Vibe Coding PRD。

aai-labs Bundle

Use aai-cli to search and manage Jira issues, Jira Product Discovery ideas, projects, boards, sprints, comments, and attachments.

agenkin Skill

Schema discovery — list every event name firing for the current TelemetryDeck app with 7-day and 30-day counts side by side.

agentic-tend Bundle

Evaluate whether a specific scientific claim or scientific-validity objection is supported by controlling derivation, data, code, figure, manuscript context, or cited-source evidence, and return its support status, scope, and unresolved gaps. Use for claim-validity review, citation-support checks, and claim-level inconsistencies across scientific artifacts. Do not use merely because content is scientific, or for explanation, copyediting, style or notation review, literature discovery, response drafting, or faithful format transfer.

aimeos Bundle

Editorial property theme with image-led layouts, crisp typography, a restrained red accent, and clear property discovery and contact paths.

aimonk2025 Bundle

Strategic GTM tracking planning with product manager expertise. Use when users need to plan tracking strategy, define what metrics to measure, understand business impact of tracking, create tracking specifications, or need guidance on "what should I track?" questions. Asks discovery questions about business goals, maps objectives to events, defines event taxonomy, and creates structured tracking plans. Trigger on - "plan GTM tracking", "what should I track", "create tracking plan", "define measurement strategy", "GTM strategy".

aimonk2025 Bundle

Generates GTM implementation documentation, reporting impact analysis, GA4 report configurations, and stakeholder summaries. Use when users need to "document GTM implementation", "what reports can I build", "create event schema docs", "generate stakeholder summary", "analyze reporting impact", or want to understand business value of tracking data. Creates technical documentation, suggests GA4 explorations, defines remarketing audiences, and translates technical events into business insights.

an0099 Bundle

How to add a new skill to this system, once the decision to build one is already made. Naming convention, required section shape, a sizing target and split ceiling, and the integration and pre-publish checklists a new skill runs through before it counts as live. Does not decide whether a recurring need is worth a skill in the first place (see skill-discovery) or check a skill file's prose against content-quality standards (see document-standards, which still governs SKILL.md and CHANGELOG.md as generated documents).

an0099 Bundle

Open a working day with a dashboard of where the tree actually stands. Reads the standing files, verifies carry-over work against the working trees rather than trusting the last session's closing report, then presents project state, ranked todos, roadmap, and the decisions waiting on the human. Invoke at the start of a working session. The mirror of session-close, which writes what this reads; it does not capture session residue, and it does not begin the work it lists.

an0099 Bundle

How a recurring need gets recognized as worth turning into a skill, and how an existing skill in this system gets located once built. Covers the worthiness test and the discovery process itself, not what happens inside a skill once it's triggered (each skill's own frontmatter description handles that) or how to structure a new skill file (see skill-creation).

alexhagemeister Skill

GNADD workflow orientation: GitHub issues as backlog, describe-vs-track file rule, and which GNADD skill handles each workflow step. Use when the user asks about GNADD, agent-driven development workflow, project context files, tasks.md versus issues, startup guidance, how to set up work, or how to install, update, or refresh the GNADD skills themselves. Do not use for routine coding unless the question is workflow-shaped.

alexhagemeister Skill

Write or revise a project's VISION.md through an interview: the user brain-dumps an idea, the agent sorts it by commitment level (Core, Possibility space, Open tensions) in the user's own confirmed words, and writes the file in the shape GNADD.md defines. Rerunning on an existing VISION.md revises it in conversation and preserves what the user does not change. Use when the user wants to write a vision, capture the intent behind a new project, start VISION.md, or revise the one they have. Never produces a plan, roadmap, or spec.

alexhagemeister Skill

Draft GitHub issues from natural language descriptions. Use when the user describes new work, asks to capture a backlog item, or needs a behavior-focused GitHub issue; interviews for requirements as needed, confirms the draft, and creates the issue via GitHub CLI after approval.

ap6pack Skill

Post-credential enumeration workflows for validated live keys — AWS IAM enum, GitHub PAT scope/repo enum, Slack workspace enum, JWT triage, Postman PMAK workspace enum, Anthropic/OpenAI usage enum. Requires validator confirmation first.

ap6pack Bundle

Router for the Offensive OSINT arsenal. Dispatches to focused sub-skills by task type. Covers the full external red-team surface: asset discovery, web enumeration, identity/SSO, secrets/dorks, post-credential workflows, cloud/infra, people/breach intel, and analysis/reporting. Companion to osint-methodology. Use for any authorized external recon, bug bounty, or ASM engagement.

ap6pack Skill

48-pattern secret regex catalog, 70 dork corpus across 9 categories, GitHub code-search dorks, and 9 read-only credential validators for authorized secret discovery and verification.

ap6pack Skill

Breach data lookup, HudsonRock infostealer intel, email-pattern inference, email harvest, Slack/Discord discovery, package registry leaks, and vulnerability prioritization endpoints.

ap6pack Skill

Subdomain enumeration, CT logs, DNS record catalog, WHOIS/RDAP, and passive reconnaissance for authorized external recon.

decebals Bundle

Triage and categorize GitHub issues with priority labels. Use when user says "triage issues", "check issues", "review open issues", or during regular maintenance of GitHub issue backlog.

incu-tech Bundle

Use for product feature work that explicitly needs discovery, a PRD, gated implementation planning, or stakeholder approval before code changes. Trigger for ambiguous, cross-cutting, client-requested, or high-risk functionality changes. Do not trigger for small direct code edits, routine refactors, bug fixes, security scans, documentation-only work, or questions about existing code.

incu-tech Bundle

Use to build a small, focused threat model for the current work or new code — a feature, a service, an API, or the changes on the current branch. Decomposes the system into assets, entry points, and trust boundaries, enumerates threats with STRIDE, and records mitigations and residual risk in a traceable report with a data-flow diagram. Invoke standalone to threat-model a component, or from another flow (incu-way-development after the PRD/plan, incu-way-bugs for a security-relevant fix) to surface threats before code is written or shipped. Especially important for new external surfaces, auth/payment/PII flows, or trust-boundary changes.

instantx-research Bundle

Generate structured Product Requirements Documents (PRDs) via guided conversation. Defaults to a lean MVP PRD. Use --full for the complete version with additional depth. Collects context in up to 2 rounds of Q&A, drafts each section for user confirmation, then assembles the final PRD. Supports export in Markdown, Confluence wiki, Feishu/Lark, and HTML formats. Triggers on: "create a PRD", "write PRD", "write requirements", "product requirements document".