[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C1JSXJF4EWCS0AKPPMBMXA":3,"skill-same:01M6C1JSXJF4EWCS0AKPPMBMXA":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":61},"01M6C1JSXJF4EWCS0AKPPMBMXA","speckit-clarify",null,"Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.","analitiq-ai\u002Fanalitiq-engine","analitiq-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F165009794?v=4","01M6C1J1DMQTT58651Q74T214Q","Analitiq","01M6C1J1J5ADQH6M1A6E4AJVPK",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspeckit-clarify\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"speckit clarify","clarify","directory","spec","github","project structure","encoding","specify","templates","2026-11-10 10:12:30",false,"---\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.\"\nargument-hint: \"Optional areas to clarify in the spec\"\ncompatibility: \"Requires spec-kit project structure with .specify\u002F directory\"\nmetadata:\n  author: \"github-spec-kit\"\n  source: \"templates\u002Fcommands\u002Fclarify.md\"\nuser-invocable: true\ndisable-model-invocation: false\n---\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- Check if `.specify\u002Fextensions.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, do not skip silently: tell the user that `.specify\u002Fextensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then 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\u002Fempty, 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` → `\u002Fspeckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n  - **Optional hook** (`optional: true`):\n    ```\n    ## Extension Hooks\n\n    **Optional Pre-Hook**: {extension}\n    Command: `\u002F{command}`\n    Description: {description}\n\n    Prompt: {prompt}\n    To execute: `\u002F{command}`\n    ```\n  - **Mandatory hook** (`optional: false`):\n    ```\n    ## Extension Hooks\n\n    **Automatic Pre-Hook**: {extension}\n    Executing: `\u002F{command}`\n    EXECUTE_COMMAND: {command}\n\n    Wait for the result of the hook command before proceeding to the Outline.\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\u002Fsession (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `\u002Fskill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n- If no hooks are registered or `.specify\u002Fextensions.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 `\u002Fspeckit-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\u002Fscripts\u002Fbash\u002Fcheck-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode \u002F `-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 `\u002Fspeckit-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\u002Fmemory\u002Fconstitution.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 \u002F Partial \u002F 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 \u002F personas differentiation\n\n   Domain & Data Model:\n   - Entities, attributes, relationships\n   - Identity & uniqueness rules\n   - Lifecycle\u002Fstate transitions\n   - Data volume \u002F scale assumptions\n\n   Interaction & UX Flow:\n   - Critical user journeys \u002F sequences\n   - Error\u002Fempty\u002Floading states\n   - Accessibility or localization notes\n\n   Non-Functional Quality Attributes:\n   - Performance (latency, throughput targets)\n   - Scalability (horizontal\u002Fvertical, limits)\n   - Reliability & availability (uptime, recovery expectations)\n   - Observability (logging, metrics, tracing signals)\n   - Security & privacy (authN\u002FZ, data protection, threat assumptions)\n   - Compliance \u002F regulatory constraints (if any)\n\n   Integration & External Dependencies:\n   - External services\u002FAPIs and failure modes\n   - Data import\u002Fexport formats\n   - Protocol\u002Fversioning assumptions\n\n   Edge Cases & Failure Handling:\n   - Negative scenarios\n   - Rate limiting \u002F 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 \u002F deprecated terms\n\n   Completion Signals:\n   - Acceptance criteria testability\n   - Measurable Definition of Done style indicators\n\n   Misc \u002F Placeholders:\n   - TODO markers \u002F 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   - The item is specifically about implementation method, tech-stack comparison, or task breakdown (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 \u002F short‑phrase answer (explicitly constrain: \"Answer in \u003C=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\u002Fruntime matrix (FR-023)` is INVALID — it is a label, not a question.\n       - After the `?`, the only permitted suffix is an optional parenthesized requirement\u002Fquestion id. Exact format: `**Question:** \u003Cinterrogative>?` or `**Question:** \u003Cinterrogative>? (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\u002Foptions.\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] - \u003Creasoning>`\n       - Then render all options as a Markdown table:\n\n       | Option | Description |\n       |--------|-------------|\n       | A | \u003COption A description> |\n       | B | \u003COption B description> |\n       | C | \u003COption C description> (add D\u002FE as needed up to 5) |\n       | Short | Provide a different short answer (\u003C=5 words) (Include only if free-form alternative is appropriate) |\n\n       - After the table, add: `You can reply with the option letter (e.g., \"A\"), accept the recommendation by saying \"yes\" or \"recommended\", or provide your own short answer.`\n    - For short‑answer style (no meaningful discrete options):\n       - Provide your **suggested answer** based on best practices and context.\n       - Format as: `**Suggested:** \u003Cyour proposed answer> - \u003Cbrief reasoning>`\n       - Then output: `Format: Short answer (\u003C=5 words). You can accept the suggestion by saying \"yes\" or \"suggested\", or provide your own answer.`\n    - After the user answers:\n       - If the user replies with \"yes\", \"recommended\", or \"suggested\", use your previously stated recommendation\u002Fsuggestion as the answer.\n       - Otherwise, validate the answer maps to one option or fits the \u003C=5 word constraint.\n       - If ambiguous, ask for a quick disambiguation (count still belongs to same question; do not advance).\n       - Once satisfactory, record it in working memory (do not yet write to disk) and move to the next queued question.\n    - Stop asking further questions when:\n       - All critical ambiguities resolved early (remaining queued items become unnecessary), OR\n       - User signals completion (\"done\", \"good\", \"no more\"), OR\n       - You reach 5 asked questions.\n    - Never reveal future queued questions in advance.\n    - If no valid questions exist at start, immediately report no critical ambiguities.\n\n6. Integration after EACH accepted answer (incremental update approach):\n    - Maintain in-memory representation of the spec (loaded once at start) plus the raw file contents.\n    - For the first integrated answer in this session:\n       - Ensure a `## Clarifications` section exists (create it just after the highest-level contextual\u002Foverview section per the spec template if missing).\n       - Under it, create (if not present) a `### Session YYYY-MM-DD` subheading for today.\n    - Append a bullet line immediately after acceptance: `- Q: \u003Cquestion> → A: \u003Cfinal answer>`.\n    - Then immediately apply the clarification to the most appropriate section(s):\n       - Functional ambiguity → Update or add a bullet in Functional Requirements.\n       - User interaction \u002F actor distinction → Update User Stories or Actors subsection (if present) with clarified role, constraint, or scenario.\n       - Data shape \u002F entities → Update Data Model (add fields, types, relationships) preserving ordering; note added constraints succinctly.\n       - Non-functional constraint → Add\u002Fmodify measurable criteria in Success Criteria > Measurable Outcomes (convert vague adjective to metric or explicit target).\n       - Edge case \u002F negative flow → Add a new bullet under Edge Cases \u002F Error Handling (or create such subsection if template provides placeholder for it).\n       - Terminology conflict → Normalize term across spec; retain original only if necessary by adding `(formerly referred to as \"X\")` once.\n    - If the clarification invalidates an earlier ambiguous statement, replace that statement instead of duplicating; leave no obsolete contradictory text.\n    - Save the spec file AFTER each integration to minimize risk of context loss (atomic overwrite).\n    - Preserve formatting: do not reorder unrelated sections; keep heading hierarchy intact.\n    - Keep each inserted clarification minimal and testable (avoid narrative drift).\n\n7. Validation (performed after EACH write plus final pass):\n   - Clarifications session contains exactly one bullet per accepted answer (no duplicates).\n   - Total asked (accepted) questions ≤ 5.\n   - Updated sections contain no lingering vague placeholders the new answer was meant to resolve.\n   - No contradictory earlier statement remains (scan for now-invalid alternative choices removed).\n   - Markdown structure valid; only allowed new headings: `## Clarifications`, `### Session YYYY-MM-DD`.\n   - Terminology consistency: same canonical term used across all updated sections.\n\n8. Write the updated spec back to `FEATURE_SPEC`.\n\n9. **Re-validate Spec Quality Checklist** (if it exists):\n   - Check if `FEATURE_DIR\u002Fchecklists\u002Frequirements.md` exists.\n   - If it does NOT exist, skip this step silently.\n   - If it exists:\n     1. Read the checklist file.\n     2. Identify all GitHub task-list checkbox lines — lines matching `- [ ]`, `- [x]`, or `- [X]` (case-insensitive, tolerant of leading whitespace for nested items) outside of code fences. Ignore all other content (headings, notes, non-checkbox bullets, metadata).\n     3. For each checkbox line, record its current marker state (checked or unchecked) and item text into a before-snapshot list.\n     4. Re-evaluate each checkbox item against the **updated** spec (the version just saved in step 7).\n     5. For each checkbox item, update only if the checked\u002Funchecked state actually changes:\n        - If the item now passes and was unchecked: change `[ ]` to `[x]`.\n        - If the item now fails and was checked: change `[x]`\u002F`[X]` to `[ ]`.\n        - If the state is unchanged: leave the marker as-is (preserve existing case to avoid cosmetic diffs).\n     6. Save the updated checklist file. **Only toggle the `[ ]`\u002F`[x]` marker portion of checkbox lines whose state changed.** All other file content — headings, metadata, notes, line ordering, whitespace — must remain unchanged to avoid noisy diffs.\n     7. Compare the before-snapshot with the current state to compute three lists for the Completion Report:\n        - **Newly passing**: items that changed from unchecked to checked.\n        - **Regressions**: items that changed from checked to unchecked.\n        - **Still unchecked**: items that remain unchecked.\n     8. Record the before\u002Fafter pass counts as checked\u002Ftotal checkbox items (e.g., \"12\u002F16 → 15\u002F16 items passing\").\n\nBehavior rules:\n\n- If no meaningful ambiguities found (or all potential questions would be low-impact), respond: \"No critical ambiguities detected worth formal clarification.\" and suggest proceeding.\n- If spec file missing, instruct user to run `\u002Fspeckit-specify` first (do not create a new spec here).\n- Never exceed 5 total asked questions (clarification retries for a single question do not count as new questions).\n- Avoid speculative tech stack questions unless the absence blocks functional clarity.\n- Respect user early termination signals (\"stop\", \"done\", \"proceed\").\n- If no questions asked due to full coverage, output a compact coverage summary (all categories Clear) then suggest advancing.\n- If quota reached with unresolved high-impact categories remaining, explicitly flag them under Deferred with rationale.\n\nContext for prioritization: $ARGUMENTS\n\n## Mandatory Post-Execution Hooks\n\n**You MUST complete this section before reporting completion to the user.**\n\nCheck if `.specify\u002Fextensions.yml` exists in the project root.\n- If it does not exist, or no hooks are registered under `hooks.after_clarify`, skip to the Completion Report.\n- If it exists, read it and look for entries under the `hooks.after_clarify` key.\n- If the YAML cannot be parsed or is invalid, do not skip silently: tell the user that `.specify\u002Fextensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then continue to the Completion Report.\n- Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.\n- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:\n  - If the hook has no `condition` field, or it is null\u002Fempty, treat the hook as executable\n  - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation\n- When constructing command invocations from hook command names, replace dots (`.`) with hyphens (`-`). For example, `speckit.git.commit` → `\u002Fspeckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n  - **Mandatory hook** (`optional: false`) — **You MUST emit `EXECUTE_COMMAND:` for each mandatory hook**:\n    ```\n    ## Extension Hooks\n\n    **Automatic Hook**: {extension}\n    Executing: `\u002F{command}`\n    EXECUTE_COMMAND: {command}\n    ```\n    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent\u002Fsession (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `\u002Fskill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n  - **Optional hook** (`optional: true`):\n    ```\n    ## Extension Hooks\n\n    **Optional Hook**: {extension}\n    Command: `\u002F{command}`\n    Description: {description}\n\n    Prompt: {prompt}\n    To execute: `\u002F{command}`\n    ```\n\n## Completion Report\n\nReport completion (after questioning loop ends or early termination):\n- Number of questions asked & answered.\n- Path to updated spec.\n- Sections touched (list names).\n- Spec quality checklist status (if `FEATURE_DIR\u002Fchecklists\u002Frequirements.md` was re-validated): show before\u002Fafter pass counts (e.g., \"Spec Quality Checklist: 12\u002F16 → 15\u002F16 items passing\") and list any items that changed state — both newly checked (unchecked → checked) and any regressions (checked → unchecked). If any items remain unchecked, list them as areas needing attention.\n- Coverage summary table listing each taxonomy category with Status: Resolved (was Partial\u002FMissing and addressed), Deferred (exceeds question quota, or remaining item is specifically implementation method, tech-stack comparison, or task breakdown), Clear (already sufficient), Outstanding (still Partial\u002FMissing but low impact).\n- If any Outstanding or Deferred remain, recommend whether to proceed to `\u002Fspeckit-plan` or run `\u002Fspeckit-clarify` again later post-plan.\n- Suggested next command.\n\n## Done When\n\n- [ ] Spec ambiguities identified and clarifications integrated into spec file\n- [ ] Spec quality checklist re-validated against updated spec (if `FEATURE_DIR\u002Fchecklists\u002Frequirements.md` exists)\n- [ ] Extension hooks dispatched or skipped according to the rules in Mandatory Post-Execution Hooks above\n- [ ] Completion reported to user with questions answered, sections touched, checklist status, and coverage summary\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- Check if `.specify\u002Fextensions.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, do not skip silently: tell the user that `.specify\u002Fextensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then 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\u002Fempty, 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` → `\u002Fspeckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n  - **Optional hook** (`optional: true`):\n    ```\n    ## Extension Hooks\n\n    **Optional Pre-Hook**: {extension}\n    Command: `\u002F{command}`\n    Description: {description}\n\n    Prompt: {prompt}\n    To execute: `\u002F{command}`\n    ```\n  - **Mandatory hook** (`optional: false`):\n    ```\n    ## Extension Hooks\n\n    **Automatic Pre-Hook**: {extension}\n    Executing: `\u002F{command}`\n    EXECUTE_COMMAND: {command}\n\n    Wait for the result of the hook command before proceeding to the Outline.\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\u002Fsession (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `\u002Fskill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n- If no hooks are registered or `.specify\u002Fextensions.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 `\u002Fspeckit-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\u002Fscripts\u002Fbash\u002Fcheck-prerequisites.sh --json --paths-only` from repo root **once** (combined `--json --paths-only` mode \u002F `-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 `\u002Fspeckit-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\u002Fmemory\u002Fconstitution.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 \u002F Partial \u002F 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 \u002F personas differentiation\n\n   Domain & Data Model:\n   - Entities, attributes, relationships\n   - Identity & uniqueness rules\n   - Lifecycle\u002Fstate transitions\n   - Data volume \u002F scale assumptions\n\n   Interaction & UX Flow:\n   - Critical user journeys \u002F sequences\n   - Error\u002Fempty\u002Floading states\n   - Accessibility or localization notes\n\n   Non-Functional Quality Attributes:\n   - Performance (latency, throughput targets)\n   - Scalability (horizontal\u002Fvertical, limits)\n   - Reliability & availability (uptime, recovery expectations)\n   - Observability (logging, metrics, tracing signals)\n   - Security & privacy (authN\u002FZ, data protection, threat assumptions)\n   - Compliance \u002F regulatory constraints (if any)\n\n   Integration & External Dependencies:\n   - External services\u002FAPIs and failure modes\n   - Data import\u002Fexport formats\n   - Protocol\u002Fversioning assumptions\n\n   Edge Cases & Failure Handling:\n   - Negative scenarios\n   - Rate limiting \u002F 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 \u002F deprecated terms\n\n   Completion Signals:\n   - Acceptance criteria testability\n   - Measurable Definition of Done style indicators\n\n   Misc \u002F Placeholders:\n   - TODO markers \u002F 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   - The item is specifically about implementation method, tech-stack comparison, or task breakdown (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 \u002F short‑phrase answer (explicitly constrain: \"Answer in \u003C=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\u002Fruntime matrix (FR-023)` is INVALID — it is a label, not a question.\n       - After the `?`, the only permitted suffix is an optional parenthesized requirement\u002Fquestion id. Exact format: `**Question:** \u003Cinterrogative>?` or `**Question:** \u003Cinterrogative>? (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\u002Foptions.\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] - \u003Creasoning>`\n       - Then render all options as a Markdown table:\n\n       | Option | Description |\n       |--------|-------------|\n       | A | \u003COption A description> |\n       | B | \u003COption B description> |\n       | C | \u003COption C description> (add D\u002FE as needed up to 5) |\n       | Short | Provide a different short answer (\u003C=5 words) (Include only if free-form alternative is appropriate) |\n\n       - After the table, add: `You can reply with the option letter (e.g., \"A\"), accept the recommendation by saying \"yes\" or \"recommended\", or provide your own short answer.`\n    - For short‑answer style (no meaningful discrete options):\n       - Provide your **suggested answer** based on best practices and context.\n       - Format as: `**Suggested:** \u003Cyour proposed answer> - \u003Cbrief reasoning>`\n       - Then output: `Format: Short answer (\u003C=5 words). You can accept the suggestion by saying \"yes\" or \"suggested\", or provide your own answer.`\n    - After the user answers:\n       - If the user replies with \"yes\", \"recommended\", or \"suggested\", use your previously stated recommendation\u002Fsuggestion as the answer.\n       - Otherwise, validate the answer maps to one option or fits the \u003C=5 word constraint.\n       - If ambiguous, ask for a quick disambiguation (count still belongs to same question; do not advance).\n       - Once satisfactory, record it in working memory (do not yet write to disk) and move to the next queued question.\n    - Stop asking further questions when:\n       - All critical ambiguities resolved early (remaining queued items become unnecessary), OR\n       - User signals completion (\"done\", \"good\", \"no more\"), OR\n       - You reach 5 asked questions.\n    - Never reveal future queued questions in advance.\n    - If no valid questions exist at start, immediately report no critical ambiguities.\n\n6. Integration after EACH accepted answer (incremental update approach):\n    - Maintain in-memory representation of the spec (loaded once at start) plus the raw file contents.\n    - For the first integrated answer in this session:\n       - Ensure a `## Clarifications` section exists (create it just after the highest-level contextual\u002Foverview section per the spec template if missing).\n       - Under it, create (if not present) a `### Session YYYY-MM-DD` subheading for today.\n    - Append a bullet line immediately after acceptance: `- Q: \u003Cquestion> → A: \u003Cfinal answer>`.\n    - Then immediately apply the clarification to the most appropriate section(s):\n       - Functional ambiguity → Update or add a bullet in Functional Requirements.\n       - User interaction \u002F actor distinction → Update User Stories or Actors subsection (if present) with clarified role, constraint, or scenario.\n       - Data shape \u002F entities → Update Data Model (add fields, types, relationships) preserving ordering; note added constraints succinctly.\n       - Non-functional constraint → Add\u002Fmodify measurable criteria in Success Criteria > Measurable Outcomes (convert vague adjective to metric or explicit target).\n       - Edge case \u002F negative flow → Add a new bullet under Edge Cases \u002F Error Handling (or create such subsection if template provides placeholder for it).\n       - Terminology conflict → Normalize term across spec; retain original only if necessary by adding `(formerly referred to as \"X\")` once.\n    - If the clarification invalidates an earlier ambiguous statement, replace that statement instead of duplicating; leave no obsolete contradictory text.\n    - Save the spec file AFTER each integration to minimize risk of context loss (atomic overwrite).\n    - Preserve formatting: do not reorder unrelated sections; keep heading hierarchy intact.\n    - Keep each inserted clarification minimal and testable (avoid narrative drift).\n\n7. Validation (performed after EACH write plus final pass):\n   - Clarifications session contains exactly one bullet per accepted answer (no duplicates).\n   - Total asked (accepted) questions ≤ 5.\n   - Updated sections contain no lingering vague placeholders the new answer was meant to resolve.\n   - No contradictory earlier statement remains (scan for now-invalid alternative choices removed).\n   - Markdown structure valid; only allowed new headings: `## Clarifications`, `### Session YYYY-MM-DD`.\n   - Terminology consistency: same canonical term used across all updated sections.\n\n8. Write the updated spec back to `FEATURE_SPEC`.\n\n9. **Re-validate Spec Quality Checklist** (if it exists):\n   - Check if `FEATURE_DIR\u002Fchecklists\u002Frequirements.md` exists.\n   - If it does NOT exist, skip this step silently.\n   - If it exists:\n     1. Read the checklist file.\n     2. Identify all GitHub task-list checkbox lines — lines matching `- [ ]`, `- [x]`, or `- [X]` (case-insensitive, tolerant of leading whitespace for nested items) outside of code fences. Ignore all other content (headings, notes, non-checkbox bullets, metadata).\n     3. For each checkbox line, record its current marker state (checked or unchecked) and item text into a before-snapshot list.\n     4. Re-evaluate each checkbox item against the **updated** spec (the version just saved in step 7).\n     5. For each checkbox item, update only if the checked\u002Funchecked state actually changes:\n        - If the item now passes and was unchecked: change `[ ]` to `[x]`.\n        - If the item now fails and was checked: change `[x]`\u002F`[X]` to `[ ]`.\n        - If the state is unchanged: leave the marker as-is (preserve existing case to avoid cosmetic diffs).\n     6. Save the updated checklist file. **Only toggle the `[ ]`\u002F`[x]` marker portion of checkbox lines whose state changed.** All other file content — headings, metadata, notes, line ordering, whitespace — must remain unchanged to avoid noisy diffs.\n     7. Compare the before-snapshot with the current state to compute three lists for the Completion Report:\n        - **Newly passing**: items that changed from unchecked to checked.\n        - **Regressions**: items that changed from checked to unchecked.\n        - **Still unchecked**: items that remain unchecked.\n     8. Record the before\u002Fafter pass counts as checked\u002Ftotal checkbox items (e.g., \"12\u002F16 → 15\u002F16 items passing\").\n\nBehavior rules:\n\n- If no meaningful ambiguities found (or all potential questions would be low-impact), respond: \"No critical ambiguities detected worth formal clarification.\" and suggest proceeding.\n- If spec file missing, instruct user to run `\u002Fspeckit-specify` first (do not create a new spec here).\n- Never exceed 5 total asked questions (clarification retries for a single question do not count as new questions).\n- Avoid speculative tech stack questions unless the absence blocks functional clarity.\n- Respect user early termination signals (\"stop\", \"done\", \"proceed\").\n- If no questions asked due to full coverage, output a compact coverage summary (all categories Clear) then suggest advancing.\n- If quota reached with unresolved high-impact categories remaining, explicitly flag them under Deferred with rationale.\n\nContext for prioritization: $ARGUMENTS\n\n## Mandatory Post-Execution Hooks\n\n**You MUST complete this section before reporting completion to the user.**\n\nCheck if `.specify\u002Fextensions.yml` exists in the project root.\n- If it does not exist, or no hooks are registered under `hooks.after_clarify`, skip to the Completion Report.\n- If it exists, read it and look for entries under the `hooks.after_clarify` key.\n- If the YAML cannot be parsed or is invalid, do not skip silently: tell the user that `.specify\u002Fextensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then continue to the Completion Report.\n- Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.\n- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:\n  - If the hook has no `condition` field, or it is null\u002Fempty, treat the hook as executable\n  - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation\n- When constructing command invocations from hook command names, replace dots (`.`) with hyphens (`-`). For example, `speckit.git.commit` → `\u002Fspeckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n  - **Mandatory hook** (`optional: false`) — **You MUST emit `EXECUTE_COMMAND:` for each mandatory hook**:\n    ```\n    ## Extension Hooks\n\n    **Automatic Hook**: {extension}\n    Executing: `\u002F{command}`\n    EXECUTE_COMMAND: {command}\n    ```\n    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent\u002Fsession (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `\u002Fskill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n  - **Optional hook** (`optional: true`):\n    ```\n    ## Extension Hooks\n\n    **Optional Hook**: {extension}\n    Command: `\u002F{command}`\n    Description: {description}\n\n    Prompt: {prompt}\n    To execute: `\u002F{command}`\n    ```\n\n## Completion Report\n\nReport completion (after questioning loop ends or early termination):\n- Number of questions asked & answered.\n- Path to updated spec.\n- Sections touched (list names).\n- Spec quality checklist status (if `FEATURE_DIR\u002Fchecklists\u002Frequirements.md` was re-validated): show before\u002Fafter pass counts (e.g., \"Spec Quality Checklist: 12\u002F16 → 15\u002F16 items passing\") and list any items that changed state — both newly checked (unchecked → checked) and any regressions (checked → unchecked). If any items remain unchecked, list them as areas needing attention.\n- Coverage summary table listing each taxonomy category with Status: Resolved (was Partial\u002FMissing and addressed), Deferred (exceeds question quota, or remaining item is specifically implementation method, tech-stack comparison, or task breakdown), Clear (already sufficient), Outstanding (still Partial\u002FMissing but low impact).\n- If any Outstanding or Deferred remain, recommend whether to proceed to `\u002Fspeckit-plan` or run `\u002Fspeckit-clarify` again later post-plan.\n- Suggested next command.\n\n## Done When\n\n- [ ] Spec ambiguities identified and clarifications integrated into spec file\n- [ ] Spec quality checklist re-validated against updated spec (if `FEATURE_DIR\u002Fchecklists\u002Frequirements.md` exists)\n- [ ] Extension hooks dispatched or skipped according to the rules in Mandatory Post-Execution Hooks above\n- [ ] Completion reported to user with questions answered, sections touched, checklist status, and coverage summary\n",{"name":5,"metadata":33,"description":7,"argument-hint":36,"compatibility":37,"user-invocable":38,"disable-model-invocation":29},{"author":34,"source":35},"github-spec-kit","templates\u002Fcommands\u002Fclarify.md","Optional areas to clarify in the spec","Requires spec-kit project structure with .specify\u002F directory",true,"main","e8d61cef4fce79478ff3d353e79ede07aa86d0da",".claude\u002Fskills\u002Fspeckit-clarify",0,"https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine","https:\u002F\u002Fanalitiq.ai","https:\u002F\u002Fgithub.com\u002Fanalitiq-ai","www.analitiq.ai","AI and LLM Tools for Data Management","2026-10-15 14:24:05",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":38},[51,54,57],{"tool":52,"command":53},"npx","npx skills add analitiq-ai\u002Fanalitiq-engine --skill speckit-clarify",{"tool":55,"command":56},"bunx","bunx skills add analitiq-ai\u002Fanalitiq-engine --skill speckit-clarify",{"tool":58,"command":59},"pnpm","pnpm dlx skills add analitiq-ai\u002Fanalitiq-engine --skill speckit-clarify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fspeckit-clarify\u002FSKILL.md",[],[63,75,85,102,112,129],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":28},"01M6C1M7HGCX2H6M4D08F7CGKW","speckit-grill-with-docs","Exhaustively clarify a feature specification and persist canonical domain knowledge before planning.","https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fgrill\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-grill-with-docs\u002FSKILL.md",[],[70,71,72,21,22,24,73,26,74,20],"docs","grill with docs","speckit grill with docs","planning","knowledge",{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":28},"01M6C1M4EK5A5ZDKTYEV7ZR2BG","speckit-grill-me","Exhaustively resolve specification ambiguities and decisions before planning.","https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fgrill\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-grill-me\u002FSKILL.md",[],[82,83,21,22,24,73,26,84],"grill me","speckit grill me","decisions",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":28},"01M6C1M1JHQ3Y6SR1FCBMYWWR6","speckit-critique-run","Perform a dual-lens critical review of the specification and plan from both product strategy and engineering risk perspectives before implementation.","https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fcritique\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-critique-run\u002FSKILL.md",[],[92,93,94,95,96,97,98,99,24,26,21,100,22,101],"speckit critique run","critique","run","plan","engineering","perspectives","risk","strategy","review","product",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":28},"01M6C1KYZ10FP83K1CPNHM41RC","speckit-assess-shape","Shape a concept: solution options, scope, appetite, and trade-offs (no implementation design)","https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fassess\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-assess-shape\u002FSKILL.md",[],[109,110,21,22,24,111,26],"speckit assess shape","design","core",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":123,"publishedAt":28},"01M6C1KWDHPN2YPEVJEZAR38EC","speckit-assess-research","Gather evidence — users, market, prior art, and data — to support or challenge the idea","https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fassess\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-assess-research\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[124,125,126,21,22,127,24,111,26,128],"speckit assess research","research","data","support","challenge",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":28},"01M6C1KSNZ87KZ458Q5QQ17TH6","speckit-assess-intake","Capture and normalize a raw idea (text, URL, ticket, or codebase pointer) into an intake note","https:\u002F\u002Fgithub.com\u002Fanalitiq-ai\u002Fanalitiq-engine\u002Fblob\u002Fmain\u002F.specify\u002Fextensions\u002Fassess\u002F.specify-dev\u002Fagent-commands\u002Fclaude\u002Fspeckit-assess-intake\u002FSKILL.md",[],[136,137,22,24,111,26,138,139,21],"speckit assess intake","intake","text","capture"]