Topic · Agent Workflows
Best requirements gathering skills for Claude Code, Codex and other agents.
- skills
- 234
- official
- 5
Requirements gathering skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions | farm-fe/ | 5.6k | 34 repos | ~1.4k | Automated safety check: Pass | MIT | 15 days ago |
| 2 | Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code. | addyosmani/ | 102k | 6 repos | ~3.8k | Automated safety check: Pass | MIT | 3 days ago |
| 3 | 3.Grilling Grill the user relentlessly about a plan, decision, or idea. | bestofjs/ | 3.1k | 30 repos | ~464 | Automated safety check: Pass | MIT | 2 days ago |
| 4 | Interviews you one question at a time about goal, trigger, permissions and data needs, then drafts a single agentic workflow markdown file. | dotnet/ | 4.6k | 2 repos | ~3.5k | Automated safety check: Pass | MIT | today |
| 5 | Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions. | deanpeters/ | 7.2k | 2 repos | ~2.9k | Automated safety check: Pass | Unknown | 1 mo ago |
| 6 | Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output. | MemTensor/ | 12k | — | ~1k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 7 | Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate. | jnMetaCode/ | 8.3k | — | ~1.8k | Automated safety check: Pass | MIT | 3 days ago |
| 8 | Turns a problem you keep running into into a single installable, tested skill, and prepares a GitHub repository only when you ask to share it. | dontbesilent2025/ | 10k | — | ~1.2k | Automated safety check: Pass | Unknown | 9 days ago |
| 9 | Gives an agent a set of working rules for any development task: understand first, surface decisions, verify results, and load deeper reference files per scenario. | shareAI-lab/ | 5.2k | — | ~5.6k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 10 | Explore-first planning that turns a vague or large request into one decision-complete work plan, written only after your approval and executed by a separate worker. | code-yeongyu/ | 70k | — | ~3.9k | Automated safety check: Pass | Unknown | today |
| 11 | Turns an underspecified do-something request into a typed IntentSpec by looking things up, asking only necessary questions or halting, before any planning or coding. | angel291592/ | 928 | — | ~7.9k | Automated safety check: Pass | MIT | 4 days ago |
| 12 | Provides multi-school trading Q&A, chart/OHLCV analysis, annotation, and fresh-market workflows covering ICT/SMC, ChanLun, Wyckoff, Price Action, Order Flow, VSA, and Elliott Wave. | MobiusQuant/ | 695 | — | ~7.2k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 13 | 13.Grill Me A relentless interview to sharpen a plan or design. An agent skill from egma-ai/egma. | egma-ai/ | 144 | 38 repos | ~111 | Automated safety check: Pass | Unknown | 7 days ago |
| 14 | A skill your agent uses when polishing, diagnosing, tailoring, or exporting resumes for LLM, RAG, Agent, Agentic RL, post-training, pretraining, AIGC, search/ranking, multimodal, AI backend, or LLM… | wanyichen06/ | 324 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 15 | Charts a foggy effort into a map of decision tickets on the repo's issue tracker and works through them one per session, producing decisions rather than deliverables. | Yeachan-Heo/ | 40k | — | ~4.1k | Automated safety check: Pass | MIT | today |
| 16 | Runs a guided product-manager interview that classifies each question automatically and produces a Product Requirements Document. | Q00/ | 6.2k | — | ~5.7k | Automated safety check: Pass | MIT | yesterday |
| 17 | Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written. | EveryInc/ | 25k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 18 | A skill your agent uses when starting or reviewing a complex implementation where the user wants an agent to interrogate the plan against docs/source evidence, surface unknown unknowns, and avoid… | nicobailon/ | 219 | — | ~3.5k | Automated safety check: Pass | MIT | 2 mo ago |
| 19 | Turns a one-line product idea into an AI-implementable PRD with 11 chapters, a speed-read card, constraint layers and acceptance criteria, written Chinese-first. | joeseesun/ | 208 | — | ~1.6k | Automated safety check: Pass | MIT | 3 mo ago |
| 20 | Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for… | InditexTech/ | 208 | 4 repos | ~828 | Automated safety check: Warn | Apache-2.0 | 2 days ago |
| 21 | Clarify requirements before implementing. An agent skill from smartfrog/opencode-froggy. | smartfrog/ | 106 | 5 repos | ~681 | Automated safety check: Pass | MIT | 8 days ago |
| 22 | 22.Readout Produce a polished, self-contained HTML "readout" document under ~/.readouts (with an auto-maintained index page), either by snapshotting the findings accumulated in the current conversation or —… | warpdotdev/ | 606 | — | ~2k | Automated safety check: Pass | MIT | 6 days ago |
| 23 | Writes or revises an MVP product requirements document, sized to the product, with observable acceptance criteria and no repeated questions. | KhazP/ | 3.1k | — | ~455 | Automated safety check: Pass | MIT | 3 days ago |
| 24 | Generate professional UI/UX designs as layered PSD-like outputs with transparent layers. | bobbyz1x2c3/ | 117 | — | ~5.4k | Automated safety check: Pass | No licence | 4 mo ago |
| 25 | Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. | meain/ | 285 | 21 repos | ~875 | Automated safety check: Pass | MIT | 1 mo ago |
| 26 | 26.Grill Me Interview the user relentlessly about a plan, design, or topic, checkpointing every answer to a brainstorm file so nothing is lost. | nateherkai/ | 1.6k | — | ~1.8k | Automated safety check: Pass | Unknown | 1 mo ago |
| 27 | Writes a structured specification before any code, moving through gated specify, plan, tasks and implement phases, with an optional capability map for multi-part requests. | addyosmani/ | 102k | 1 repo | ~3.2k | Automated safety check: Pass | MIT | 3 days ago |
| 28 | Pulls a GitHub issue's description, comments, labels, assignees, milestone and linked pull requests into one markdown report so the agent can plan a fix. | jumppad-labs/ | 263 | — | ~958 | Automated safety check: Pass | MPL-2.0 | 6 days ago |
| 29 | 29.Grill Me Interview the user about a plan or design until reaching shared understanding, resolving each branch of the decision tree. | Effect-TS/ | 782 | 1 repo | ~504 | Automated safety check: Pass | MIT | 2 mo ago |
| 30 | Moves a design-grilling interview from the terminal to a local web page, where each question, recommendation and discussion thread can be handled in any order. | jasonku09/ | 246 | — | ~7.9k | Automated safety check: Pass | MIT | yesterday |
| 31 | Reads human-written spec documents and produces per-epic requirement files with proof obligations plus behavior scenarios with stable IDs, using parallel chunked extraction. | prime-radiant-inc/ | 181 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | 4 mo ago |
| 32 | Ask clarifying questions to users via interactive TUI. An agent skill from paulp-o/ask-user-questions-mcp. | paulp-o/ | 147 | — | ~496 | Automated safety check: Pass | MIT | 3 mo ago |
| 33 | Researches an app idea or settles product and technical uncertainties before a design is fixed, and saves the findings with a handoff for the next stage. | KhazP/ | 3.1k | — | ~473 | Automated safety check: Pass | MIT | 3 days ago |
| 34 | 34.Conductor A skill your agent uses when a complex task needs dependency-aware interactive branches, subagents, or AI coding threads while keeping the master session context clean through explicit branch… | Jinghao67/ | 102 | — | ~3.9k | Automated safety check: Pass | MIT | 3 mo ago |
| 35 | Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. | sanity-io/ | 6.4k | 40 repos | ~151 | Automated safety check: Pass | MIT | today |
| 36 | Manages SPEC documents for MoAI-ADK development, with GEARS or EARS requirement notation, acceptance criteria and a link into the Plan-Run-Sync workflow. | modu-ai/ | 1.2k | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | today |
| 37 | Turns a vague feature request into a written spec with scope, phases, acceptance criteria and do-not-do limits that a coding agent can follow without guessing. | tryproduck/ | 511 | — | ~5.3k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 38 | 38.Planning Interview-driven planning methodology that produces implementation-ready plans. | markmdev/ | 186 | — | ~1.3k | Automated safety check: Pass | No licence | 7 mo ago |
| 39 | A skill your agent uses when creating, auditing, or updating project documentation. | TheAngryByrd/ | 150 | — | ~915 | Automated safety check: Pass | MIT | 4 days ago |
| 40 | Guides a product discovery conversation and writes product-brief.md with the problem, evidence, scope, decisions and the next open question, for existing, client or own ideas. | open-mercato/ | 221 | — | ~3k | Automated safety check: Pass | MIT | 2 days ago |
| 41 | Guides the agent from a vague objective to a written goal package under goals/, using a confirmed restatement, a browser interview, a fact sheet and a codebase pass. | backnotprop/ | 9.2k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 42 | 42.Ad Deepen Surface deepening opportunities in the codebase using the Ousterhout/Feathers vocabulary from WORKFLOW §8 (Module / Interface / Depth / Seam / Adapter / Leverage / Locality). | alexandremendoncaalvaro/ | 755 | 1 repo | ~2k | Automated safety check: Pass | Unknown | 2 mo ago |
| 43 | Runs a short design conversation before coding: aligns on terms, works through the decisions that matter and ends with a plan you confirm. | jsmastery-pro/ | 216 | — | ~1.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 44 | Headless grilling pass that challenges an approved implementation plan against the existing codebase and domain model, then writes an ADR draft and a PRD draft into the Foreman feature directory. | VisionForge-OU/ | 444 | — | ~1.6k | Automated safety check: Pass | Unknown | 3 mo ago |
| 45 | 45.Create PR Create or update a GitHub pull request for the current branch from the repository's fixed PR template (.github/PULLREQUESTTEMPLATE.md) and the branch changes. | javierbrea/ | 997 | — | ~2.3k | Automated safety check: Pass | MIT | 2 days ago |
| 46 | Interview the user for the raw material their posts are made of. | sergebulaev/ | 4.3k | 1 repo | ~2.1k | Automated safety check: Pass | MIT | today |
| 47 | A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions | Houseofmvps/ | 123 | — | ~2.2k | Automated safety check: Pass | MIT | 3 mo ago |
| 48 | 48.Grill Me Interview the user to clarify requirements, architecture, design, and business rules before implementation. | kipperacademy/ | 113 | — | ~962 | Automated safety check: Pass | No licence | today |
Questions, answered from the data.
What is the best requirements gathering skill?
Using Superpowers from farm-fe/farm ranks first of the 234 requirements gathering skills listed here, with the highest score: its repository has 5.6k GitHub stars, 34 other GitHub owners carry a copy, its SKILL.md loads about 1.4k tokens and it passes the automated safety check with no findings. Next come Interview Me and Grilling.
Which requirements gathering skills are official?
5 of the 234 requirements gathering skills are official, published by the vendor's own GitHub organization: Agentic Workflow Designer, Grill Me, SageMaker Deployment Planner, Google Cloud Database Onboarding and Azv Sketch To Diagram.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.
Explore related skills
Category
More topics in Agent Workflows
- MCP servers2,017
- Subagents1,015
- Agent instruction files737
- Agent memory507
- Multi-agent orchestration504
- Skill authoring502
- Planning495
- Brainstorming467
- Hooks and plugins363
- Autonomous loops325
- Context engineering297
- Session handoff262
- Task breakdown232
- Skill management205
- Human-in-the-loop approvals203
- Codebase knowledge for agents186
- Verification before completion169
- Agent evaluation and testing131