Best requirements gathering skills, page 4

Docs-anchored grilling session — challenges a plan against the project's existing language (CONTEXT.md) and recorded decisions (docs/adr/), and updates those files inline as terminology and…

alirezarezvani/claude-skills

Disciplined diagnosis loop for hard bugs and performance regressions per WORKFLOW §15.

alexandremendoncaalvaro/CorridorKey-Runtime

Convert a rough sketch or drawing of an Azure architecture into a professional Draw.io diagram using Azure-specific shapes.

Azure/AZVerify

Explores intent, constraints and alternative approaches before any planning, working through questions one at a time and saving an approved design for later steps.

first-fluke/oh-my-agent

Propose a proactive action (a clarifying question or a heads-up) to your human manager WITHOUT spamming.

Prismer-AI/PrismerCloud

Interrogate the brief before a line is built — ask only the questions whose answers change the work, and put every unasked decision on the record as a stated assumption.

plugin87/ux-ui-agent-skills

围绕计划、decision 或 idea 持续追问用户。适用于用户想对自己的思路做压力测试，或使用任何 “grill” 触发措辞时。

vinvcn/mattpocock-skills-zh-CN

A relentless interview to sharpen a plan or design — one question at a time until every branch of the decision tree is resolved.

rengwu/wayfinder-maps

对用户的计划、决策或想法进行层层盘问。当用户想要压力测试自己的思考，或使用任何 'grill' 触发短语时使用. An agent skill from AUTO-MAS-Project/AUTO-MAS.

AUTO-MAS-Project/AUTO-MAS

Five-phase pipeline (triage → clarify → research → PRD → plan) that turns a raw idea into four linked files: clarifying questions, deep research, a PRD with non-goals and metrics, and a phased…

sickn33/agentic-awesome-skills

Asks clarifying questions in multiple rounds before starting ambiguous tasks.

sickn33/agentic-awesome-skills

A skill your agent uses when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture choices, contract changes, or when grilling/pressure-testing a…

GanyuanRan/Aegis

针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。

feiskyer/claude-code-settings

Turn fuzzy intent into shared understanding and acceptance criteria — specification as a conversation, run one question at a time, before any story is split or planned.

citypaul/.dotfiles

Find warm leads by searching LinkedIn for pain-language posts — the frustrations, complaints, and operational struggles your ICP talks about publicly.

gooseworks-ai/goose-skills

Generate targeted clarifying questions (2-3 max) that challenge vague requirements and extract missing context.

alirezarezvani/claude-cto-team

Structured clarification form for unresolved material requirements.

nexu-io/open-design

Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review.

waybarrios/opencode-power-pack

Working under AUTONOMOUS MODE — a pinned task the session must drive to a written definition of done without asking the user anything.

dxos/dxos

Interview me relentlessly about every aspect of this plan until we reach a shared understanding.

vechain/x-app-template

Relentless one-question-at-a-time interview that sharpens a vague plan or design into shared understanding before any build.

SethGammon/Citadel

Adversarially review an existing written artifact — stories, plans, acceptance criteria, specs, or design mocks — to surface missing states, unhandled edge cases, unstated assumptions, unverifiable…

citypaul/.dotfiles

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree one at a time.

open-octo/octo-agent

Write a new issue from scratch by grilling the user to clarify requirements, creating the issue on GitHub via the gh cli, and utilizing the triage skill to apply the correct label and add an agent…

yamcodes/arkenv

A skill your agent uses when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways.

aiming-lab/MetaClaw

Clarify a standalone idea or check assumptions before feature or fix planning.

kdlbs/kandev

Interview user about a spec file and write detailed requirements.

kv0906/pm-kit

A skill your agent uses when the user says Interview me before you start as a standalone command, explicitly asks to be questioned before work begins, or needs an adaptive, consent-based interview…

asimons81/hermes-field-kit

Triage the team's open GUS backlog — propose closing done-but-open work items (with code/test citations), flag under-specified items for grilling, catch wrong-epic / orphan / unpointed / dead-link…

forcedotcom/salesforcedx-vscode

Adversarial plan interview before implementation. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Build MATLAB apps from requirements to working code. An agent skill from matlab/matlab-agentic-toolkit.

matlab/matlab-agentic-toolkit

Interviews you in stages, then turns a vague research idea into a structured JSON query, a readable brief and a checklist for a deep research run.

fivetaku/gptaku-plugins-codex

Common mistake — proceeding with assumptions about ambiguous requirements instead of asking a clarifying question first.

aiming-lab/MetaClaw

Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where $map-plan would force premature decomposition.

azalio/map-framework

Adversarially challenge research assumptions, mechanisms, and arguments in writing.

flonat/flonat-research

Structured conversational interview to formalise a research idea or extension into a concrete specification with hypotheses and empirical strategy.

brycewang-stanford/Auto-Empirical-Research-Skills

Self-driving version of grill-me. An agent skill from TheOrcDev/skills.

TheOrcDev/skills

Pressure-test a captured idea against an objective rubric and write a structured analysis back into the source file.

grandamenium/cortextos

Align on the shape of a change through an interview, then implement it.

tobihagemann/turbo

Scaffold a new Dart or Flutter project from a Very Good CLI template, covering the flutterapp, dartpackage, flutterpackage, flutterplugin, dartcli, flamegame, and docssite templates, inferring the…

VeryGoodOpenSource/vgv-ai-flutter-plugin

The four Karpathy behavioral principles — think before coding, simplicity first, surgical changes, goal-driven execution — adapted to Flowfile's working norms (the skill-first lookup habit, the…

Edwardvaneechoud/Flowfile

Creates and reviews executable implementation plans grounded in repository evidence, with vertical slices, explicit decisions, and verification criteria.

mblode/agent-skills

Use after initial design context is gathered, before brainstorming - resolves contradictions in requirements, disambiguates terminology, clarifies scope boundaries, and verifies assumptions to…

ed3dai/ed3d-plugins

A skill your agent uses when you have a rough product idea and want a complete PRD without sitting through an interactive grilling.

TheCraigHewitt/skills

Produce a complete backend technical design document from a PRD or feature description — understand, explore the codebase, grill on decisions, write, and self-review.

open-octo/octo-agent

Triage GitHub issues through a label-based state machine with interactive grilling sessions.

sammcj/agentic-coding

Translate natural-language requirements or structured specification documents into formal temporal logic properties (LTL, CTL, safety/liveness properties).

ArabelaTso/Skills-4-SE

Stress-tests a plan via Socratic questioning down each decision branch.

softspark/ai-toolkit