Clarificar
Use for a GRILLING SESSION — a relentless interview that turns diffuse intent into shared understanding before building. It walks the decision tree ONE question at a time, resolving dependencies between choices, always with a recommended answer; it explores the codebase/docs instead of asking when the answer already exists. Ideal at the spec gate (testable ACs / Definition of Ready) and the design gate (hard-to-reverse decision). It produces an understanding summary that feeds product.md/design.md/spec.md. Called by /nova-feature, /kickoff, /roadmap, and /validar, or trigger directly with /cla
Install
npx skills add adriannoes/awesome-agentic-ai --skill clarificargit clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai.git /tmp/awesome-agentic-ai
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-agentic-ai/cursor-claude-codex/skills/igoruehara-spec-driven/skills/clarificar ~/.claude/skills/clarificarPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
> **Translation note:** Originally authored in Portuguese (pt-BR) by Igor Uehara ([igoruehara/spec-driven](https://github.com/igoruehara/spec-driven), MIT). Translated to English by this hub to keep the repository language consistent. Original content unchanged in meaning; see the upstream repo for the pt-BR source. # Skill: Clarify (plan/spec grilling) A relentless interview to **sharpen a plan, a spec, or a design** before building. The target is **shared understanding**: no ambiguity that turns into rework or `SPEC_DEVIATION` later. Inspired by the *grilling* technique — adapted to the pipeline's vocabulary (testable ACs, tier, hard-to-reverse decision → ADR, ubiquitous language). > **When to use this and not "short batches":** the rest of the pipeline asks in **batches** > (`AskUserQuestion`) for **independent** choices. The grilling is the opposite and the complement: > for a **decision tree with dependencies**, where answer 3 only makes sense after answers 1 and 2. > Use when the ambiguity is **deep and branched**, not when the options are orthogonal. ## Principles (the engine) - **One question at a time.** Ask the question, **wait for the answer**, and only then the next one. Several questions at once confuse and prevent each answer from refining the next. - **Walk the tree.** Each answer opens/closes branches. Resolve **dependencies in order**: don't ask "how" before "whether", nor the detail before the boundary.
Details
- Skill name
clarificar- Repository
- adriannoes/awesome-agentic-ai
- Path
cursor-claude-codex/skills/igoruehara-spec-driven/skills/clarificar/SKILL.md- License
- MIT
- Repo updated
- 2 November 2026
FAQ
What does the Clarificar skill do?
Use for a GRILLING SESSION — a relentless interview that turns diffuse intent into shared understanding before building. It walks the decision tree ONE question at a time, resolving dependencies between choices, always with a recommended answer; it explores the codebase/docs instead of asking when the answer already exists. Ideal at the spec gate (testable ACs / Definition of Ready) and the design gate (hard-to-reverse decision). It produces an understanding summary that feeds product.md/design.md/spec.md. Called by /nova-feature, /kickoff, /roadmap, and /validar, or trigger directly with /cla
How do I install the Clarificar skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add adriannoes/awesome-agentic-ai --skill clarificar. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Clarificar popular?
It lives in adriannoes/awesome-agentic-ai, which has 100 GitHub stars and 27 forks, and is included in 2 curated skill lists.
Related skills
Browserstack
100adriannoes/awesome-agentic-ai
Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".
Coverage
100adriannoes/awesome-agentic-ai
Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".
Fix
100adriannoes/awesome-agentic-ai
Fix failing or flaky Playwright tests. Use when user says "fix test", "flaky test", "test failing", "debug test", "test broken", "test passes sometimes", or "intermittent failure".
Investigating Insider Threat Indicators
100adriannoes/awesome-agentic-ai
Investigates insider threat indicators including data exfiltration attempts, unauthorized access patterns, policy violations, and pre-departure behaviors using SIEM analytics, DLP alerts, and HR data correlation. Use when SOC teams receive insider threat referrals from HR, detect anomalous data movement by employees, or need to build investigation timelines for potential insider threats.
AI Stock Report Generator
43yangchunyi0814/ai-stock-report-generator
台股「一鍵財務模型 + 投資簡報」生成器。使用者輸入任何台股代號(如 6116、2330、0050)並加上 //ai-stock-report-generator,或沿用舊觸發詞 //model-up,或說「建立財務模型」「Excel 財務模型」「估值模型」「幫我做 XXXX 的估值和簡報」「XXXX 財務模型整理成 PPT」「model up XXXX / ai stock report XXXX」時,必須立即使用此技能。技能會即時搜尋最新公開財務數據與近期日線資料,產出核心檔案:(1) 完整 Excel 財務模型(假設可調、三情境預測、P/B 與 P/S 估值、敏感度表、財務指標、KD/MACD 技術指標、K 線型態資料、風險矩陣,全部以公式或可稽核計算連動、零公式錯誤);(2) 投資分析 PPTX(有數據、有圖表:歷史財務、營運動能、成長動能、估值、KD/MACD、K 線型態、風險、結論);必要時另附可下載的 K 線 HTML/PNG 圖表。即使使用者只丟出「代號 //ai-stock-report-generator」也必須執行完整流程,不得僅用文字回覆。
Investigating Ransomware Attack Artifacts
100adriannoes/awesome-agentic-ai
Identify, collect, and analyze ransomware attack artifacts to determine the variant, initial access vector, encryption scope, and recovery options.
Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.