{"slug":"dceoy-speckit-clarify","name":"speckit-clarify","description":"Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.","long_description":"---\nname: \"speckit-clarify\"\ndescription: \"Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.\"\ncompatibility: \"Requires spec-kit project structure with .specify/ directory\"\nmetadata:\n author: \"github-spec-kit\"\n source: \"templates/commands/clarify.md\"\n---\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou **MUST** consider the user input before proceeding (if not empty).\n\n## Pre-Execution Checks\n\n**Check for extension hooks (before clarification)**:\n\n- Check if `.specify/extensions.yml` exists in the project root.\n- If it exists, read it and look for entries under the `hooks.before_clarify` key\n- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally\n- Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.\n- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:\n - If the hook has no `condition` field, or it is null/empty, treat the hook as executable\n - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation\n- When constructing command invocations from hook command names, replace dots (`.`) with hyphens (`-`). For example, `speckit.git.commit` → `/speckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n - **Optional hook** (`optional: true`):\n\n ```text\n ## Extension Hooks\n\n **Optional Pre-Hook**: {extension}\n Command: `/{command}`\n Description: {description}\n\n Prompt: {prompt}\n To execute: `/{command}`\n ```\n\n - **Mandatory hook** (`optional: false`):\n\n ```text\n ## Extension Hooks\n\n **Automatic Pre-Hook**: {extension}\n Executing: `/{command}`\n EXECUTE_COMMAND: {command}\n\n Wait for the result of the hook command before proceeding to the Outline.\n ```\n\n After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `/skill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n- If no hooks are registered or `.specify/extensions.yml` does not exist, skip silently\n\n## Outline\n\nGoal: Detect and reduce ambiguity or missing decision points in the active feature specification and record the clarifications directly in the spec file.\n\nNote: This clarification workflow is expected to run (and be completed) BEFORE invoking `/speckit-plan`. If the user explicitly states they are skipping clarification (e.g., exploratory spike), you may proceed, but must warn that downstream rework risk increases.\n\nExecution steps:\n\n1. Run `.specify/scripts/bash/check-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode / `-Json -PathsOnly`). Parse minimal JSON payload fields:\n - `FEATURE_DIR`\n - `FEATURE_SPEC`\n - (Optionally capture `IMPL_PLAN`, `TASKS` for future chained flows.)\n - If JSON parsing fails, abort and instruct user to re-run `/speckit-specify` or verify feature branch environment.\n - For single quotes in args like \"I'm Groot\", use escape syntax: e.g 'I'\\''m Groot' (or double-quote if possible: \"I'm Groot\").\n\n2. **IF EXISTS**: Load `.specify/memory/constitution.md` for project principles and governance constraints.\n\n3. Load the current spec file. Perform a structured ambiguity & coverage scan using this taxonomy. For each category, mark status: Clear / Partial / Missing. Produce an internal coverage map used for prioritization (do not output raw map unless no questions will be asked).\n\n Functional Scope & Behavior:\n - Core user goals & success criteria\n - Explicit out-of-scope declarations\n - User roles / personas differentiation\n\n Domain & Data Model:\n - Entities, attributes, relationships\n - Identity & uniqueness rules\n - Lifecycle/state transitions\n - Data volume / scale assumptions\n\n Interaction & UX Flow:\n - Critical user journeys / sequences\n - Error/empty/loading states\n - Accessibility or localization notes\n\n Non-Functional Quality Attributes:\n - Performance (latency, throughput targets)\n - Scalability (horizontal/vertical, limits)\n - Reliability & availability (uptime, recovery expectations)\n - Observability (logging, metrics, tracing signals)\n - Security & privacy (authN/Z, data protection, threat assumptions)\n - Compliance / regulatory constraints (if any)\n\n Integration & External Dependencies:\n - External services/APIs and failure modes\n - Data import/export formats\n - Protocol/versioning assumptions\n\n Edge Cases & Failure Handling:\n - Negative scenarios\n - Rate limiting / throttling\n - Conflict resolution (e.g., concurrent edits)\n\n Constraints & Tradeoffs:\n - Technical constraints (language, storage, hosting)\n - Explicit tradeoffs or rejected alternatives\n\n Terminology & Consistency:\n - Canonical glossary terms\n - Avoided synonyms / deprecated terms\n\n Completion Signals:\n - Acceptance criteria testability\n - Measurable Definition of Done style indicators\n\n Misc / Placeholders:\n - TODO markers / unresolved decisions\n - Ambiguous adjectives (\"robust\", \"intuitive\") lacking quantification\n\n For each category with Partial or Missing status, add a candidate question opportunity unless:\n - Clarification would not materially change implementation or validation strategy\n - Information is better deferred to planning phase (note internally)\n\n4. Generate (internally) a prioritized queue of candidate clarification questions (maximum 5). Do NOT output them all at once. Apply these constraints:\n - Maximum of 5 total questions across the whole session.\n - Each question must be answerable with EITHER:\n - A short multiple‑choice selection (2–5 distinct, mutually exclusive options), OR\n - A one-word / short‑phrase answer (explicitly constrain: \"Answer in <=5 words\").\n - Only include questions whose answers materially impact architecture, data modeling, task decomposition, test design, UX behavior, operational readiness, or compliance validation.\n - Ensure category coverage balance: attempt to cover the highest impact unresolved categories first; avoid asking two low-impact questions when a single high-impact area (e.g., security posture) is unresolved.\n - Exclude questions already answered, trivial stylistic preferences, or plan-level execution details (unless blocking correctness).\n - Favor clarifications that reduce downstream rework risk or prevent misaligned acceptance tests.\n - If more than 5 categories remain unresolved, select the top 5 by (Impact * Uncertainty) heuristic.\n\n5. Sequential questioning loop (interactive):\n - Present EXACTLY ONE question at a time.\n - **Question writing quality (applies to every question, MC or short-answer):**\n - Lead with `**Question:**` followed by a full interrogative that ends with `?`. The question text before the `?` must make sense on its own.\n - NEVER use a topic label, section heading, or requirement id as the question itself. For example, `Acceptance device/runtime matrix (FR-023)` is INVALID — it is a label, not a question.\n - After the `?`, the only permitted suffix is an optional parenthesized requirement/question id. Exact format: `**Question:** ?` or `**Question:** ? (FR-023)`. Never put the id before the `?`, and never use the id (alone or with a topic label) as the whole prompt.\n - Immediately after the question line, add one plain-language \"Why it matters\" sentence (the stake for acceptance or shipping) before the recommendation/options.\n - Use everyday wording; introduce jargon only if defined in the same sentence. Self-check: a reader who does not know Spec Kit must be able to answer from the Question line alone. Terse is fine; cryptic labels are not.\n - For multiple‑choice questions:\n - **Analyze all options** and determine the **most suitable option** based on:\n - Best practices for the project type\n - Common patterns in similar implementations\n - Risk reduction (security, performance, maintainability)\n - Alignment with any explicit project goals or constraints visible in the spec\n - Present your **recommended option prominently** at the top with clear reasoning (1-2 sentences explaining why this is the best choice).\n - Format as: `**Recommended:** Option [X] - `\n - Then render all options as a Markdown table:\n\n \n\n | Option | Description |\n | ------ | --------------------------------------------------------------------------------------------------- |\n | A |