speckit-clarify

name	speckit-clarify
description	Identify underspecified areas in the current feature spec by asking up

Speckit Clarify Skill

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Pre-Execution Checks

Check for extension hooks (before clarification):

• Check if .specify/extensions.yml exists in the project root.
• If it exists, read it and look for entries under the hooks.before_clarify key
• If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
• Filter out hooks where enabled is explicitly false. Treat hooks without an enabled field as enabled by default.
• For each remaining hook, do not attempt to interpret or evaluate hook condition expressions:
  • If the hook has no condition field, or it is null/empty, treat the hook as executable
  • If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementation
• When constructing slash commands from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.
• For each executable hook, output the following based on its optional flag:
  • Optional hook (optional: true):

    ## Extension Hooks
    
    **Optional Pre-Hook**: {extension}
    Command: `/{command}`
    Description: {description}
    
    Prompt: {prompt}
    To execute: `/{command}`
    

  • Mandatory hook (optional: false):

    ## Extension Hooks
    
    **Automatic Pre-Hook**: {extension}
    Executing: `/{command}`
    EXECUTE_COMMAND: {command}
    
    Wait for the result of the hook command before proceeding to the Outline.
    

• If no hooks are registered or .specify/extensions.yml does not exist, skip silently

Outline

Goal: Detect and reduce ambiguity or missing decision points in the active feature specification and record the clarifications directly in the spec file.

Note: 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.

Execution steps:

1. 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:

   • FEATURE_DIR
   • FEATURE_SPEC
   • (Optionally capture IMPL_PLAN, TASKS for future chained flows.)
   • If JSON parsing fails, abort and instruct user to re-run /speckit-specify or verify feature branch environment.
   • 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").

2. 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).

   Functional Scope & Behavior:

   • Core user goals & success criteria
   • Explicit out-of-scope declarations
   • User roles / personas differentiation

   Domain & Data Model:

   • Entities, attributes, relationships
   • Identity & uniqueness rules
   • Lifecycle/state transitions
   • Data volume / scale assumptions

   Interaction & UX Flow:

   • Critical user journeys / sequences
   • Error/empty/loading states
   • Accessibility or localization notes

   Non-Functional Quality Attributes:

   • Performance (latency, throughput targets)
   • Scalability (horizontal/vertical, limits)
   • Reliability & availability (uptime, recovery expectations)
   • Observability (logging, metrics, tracing signals)
   • Security & privacy (authN/Z, data protection, threat assumptions)
   • Compliance / regulatory constraints (if any)

   Integration & External Dependencies:

   • External services/APIs and failure modes
   • Data import/export formats
   • Protocol/versioning assumptions

   Edge Cases & Failure Handling:

   • Negative scenarios
   • Rate limiting / throttling
   • Conflict resolution (e.g., concurrent edits)

   Constraints & Tradeoffs:

   • Technical constraints (language, storage, hosting)
   • Explicit tradeoffs or rejected alternatives

   Terminology & Consistency:

   • Canonical glossary terms
   • Avoided synonyms / deprecated terms

   Completion Signals:

   • Acceptance criteria testability
   • Measurable Definition of Done style indicators

   Misc / Placeholders:

   • TODO markers / unresolved decisions
   • Ambiguous adjectives ("robust", "intuitive") lacking quantification

   For each category with Partial or Missing status, add a candidate question opportunity unless:

   • Clarification would not materially change implementation or validation strategy
   • Information is better deferred to planning phase (note internally)

3. Generate (internally) a prioritized queue of candidate clarification questions (maximum 5). Do NOT output them all at once. Apply these constraints:

   • Maximum of 5 total questions across the whole session.
   • Each question must be answerable with EITHER:
     • A short multiple‑choice selection (2–5 distinct, mutually exclusive options), OR
     • A one-word / short‑phrase answer (explicitly constrain: "Answer in <=5 words").
   • Only include questions whose answers materially impact architecture, data modeling, task decomposition, test design, UX behavior, operational readiness, or compliance validation.
   • 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.
   • Exclude questions already answered, trivial stylistic preferences, or plan-level execution details (unless blocking correctness).
   • Favor clarifications that reduce downstream rework risk or prevent misaligned acceptance tests.
   • If more than 5 categories remain unresolved, select the top 5 by (Impact * Uncertainty) heuristic.

4. Sequential questioning loop (interactive):

   • Present EXACTLY ONE question at a time.

   • For multiple‑choice questions:

     • Analyze all options and determine the most suitable option based on:
       • Best practices for the project type
       • Common patterns in similar implementations
       • Risk reduction (security, performance, maintainability)
       • Alignment with any explicit project goals or constraints visible in the spec
     • Present your recommended option prominently at the top with clear reasoning (1-2 sentences explaining why this is the best choice).
     • Format as: **Recommended:** Option [X] - <reasoning>
     • Then render all options as a Markdown table:

     Option	Description
     A
     B
     C	(add D/E as needed up to 5)
     Short	Provide a different short answer (<=5 words) (Include only if free-form alternative is appropriate)

     • 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.

   • For short‑answer style (no meaningful discrete options):

     • Provide your suggested answer based on best practices and context.
     • Format as: **Suggested:** <your proposed answer> - <brief reasoning>
     • Then output: Format: Short answer (<=5 words). You can accept the suggestion by saying "yes" or "suggested", or provide your own answer.

   • After the user answers:

     • If the user replies with "yes", "recommended", or "suggested", use your previously stated recommendation/suggestion as the answer.
     • Otherwise, validate the answer maps to one option or fits the <=5 word constraint.
     • If ambiguous, ask for a quick disambiguation (count still belongs to same question; do not advance).
     • Once satisfactory, record it in working memory (do not yet write to disk) and move to the next queued question.

   • Stop asking further questions when:

     • All critical ambiguities resolved early (remaining queued items become unnecessary), OR
     • User signals completion ("done", "good", "no more"), OR
     • You reach 5 asked questions.

   • Never reveal future queued questions in advance.

   • If no valid questions exist at start, immediately report no critical ambiguities.

5. Integration after EACH accepted answer (incremental update approach):

   • Maintain in-memory representation of the spec (loaded once at start) plus the raw file contents.
   • For the first integrated answer in this session:
     • Ensure a ## Clarifications section exists (create it just after the highest-level contextual/overview section per the spec template if missing).
     • Under it, create (if not present) a ### Session YYYY-MM-DD subheading for today.
   • Append a bullet line immediately after acceptance: - Q: <question> → A: <final answer>.
   • Then immediately apply the clarification to the most appropriate section(s):
     • Functional ambiguity → Update or add a bullet in Functional Requirements.
     • User interaction / actor distinction → Update User Stories or Actors subsection (if present) with clarified role, constraint, or scenario.
     • Data shape / entities → Update Data Model (add fields, types, relationships) preserving ordering; note added constraints succinctly.
     • Non-functional constraint → Add/modify measurable criteria in Success Criteria > Measurable Outcomes (convert vague adjective to metric or explicit target).
     • Edge case / negative flow → Add a new bullet under Edge Cases / Error Handling (or create such subsection if template provides placeholder for it).
     • Terminology conflict → Normalize term across spec; retain original only if necessary by adding (formerly referred to as "X") once.
   • If the clarification invalidates an earlier ambiguous statement, replace that statement instead of duplicating; leave no obsolete contradictory text.
   • Save the spec file AFTER each integration to minimize risk of context loss (atomic overwrite).
   • Preserve formatting: do not reorder unrelated sections; keep heading hierarchy intact.
   • Keep each inserted clarification minimal and testable (avoid narrative drift).

6. Validation (performed after EACH write plus final pass):

   • Clarifications session contains exactly one bullet per accepted answer (no duplicates).
   • Total asked (accepted) questions ≤ 5.
   • Updated sections contain no lingering vague placeholders the new answer was meant to resolve.
   • No contradictory earlier statement remains (scan for now-invalid alternative choices removed).
   • Markdown structure valid; only allowed new headings: ## Clarifications, ### Session YYYY-MM-DD.
   • Terminology consistency: same canonical term used across all updated sections.

7. Write the updated spec back to FEATURE_SPEC.

8. Report completion (after questioning loop ends or early termination):

   • Number of questions asked & answered.
   • Path to updated spec.
   • Sections touched (list names).
   • Coverage summary table listing each taxonomy category with Status: Resolved (was Partial/Missing and addressed), Deferred (exceeds question quota or better suited for planning), Clear (already sufficient), Outstanding (still Partial/Missing but low impact).
   • If any Outstanding or Deferred remain, recommend whether to proceed to /speckit-plan or run /speckit-clarify again later post-plan.
   • Suggested next command.

Behavior rules:

• If no meaningful ambiguities found (or all potential questions would be low-impact), respond: "No critical ambiguities detected worth formal clarification." and suggest proceeding.
• If spec file missing, instruct user to run /speckit-specify first (do not create a new spec here).
• Never exceed 5 total asked questions (clarification retries for a single question do not count as new questions).
• Avoid speculative tech stack questions unless the absence blocks functional clarity.
• Respect user early termination signals ("stop", "done", "proceed").
• If no questions asked due to full coverage, output a compact coverage summary (all categories Clear) then suggest advancing.
• If quota reached with unresolved high-impact categories remaining, explicitly flag them under Deferred with rationale.

Context for prioritization: $ARGUMENTS

Post-Execution Checks

Check for extension hooks (after clarification): Check if .specify/extensions.yml exists in the project root.

• If it exists, read it and look for entries under the hooks.after_clarify key
• If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
• Filter out hooks where enabled is explicitly false. Treat hooks without an enabled field as enabled by default.
• For each remaining hook, do not attempt to interpret or evaluate hook condition expressions:
  • If the hook has no condition field, or it is null/empty, treat the hook as executable
  • If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementation
• When constructing slash commands from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.
• For each executable hook, output the following based on its optional flag:
  • Optional hook (optional: true):

    ## Extension Hooks
    
    **Optional Hook**: {extension}
    Command: `/{command}`
    Description: {description}
    
    Prompt: {prompt}
    To execute: `/{command}`
    

  • Mandatory hook (optional: false):

    ## Extension Hooks
    
    **Automatic Hook**: {extension}
    Executing: `/{command}`
    EXECUTE_COMMAND: {command}
    

• If no hooks are registered or .specify/extensions.yml does not exist, skip silently

Timing — keep .spec-context.json honest

These rules apply to every Companion profile command. The extension records lifecycle timing with its own scripts wherever it can; these rules keep anything you append consistent with that and accurate for any dispatcher (terminal, IDE chat, or the GUI). The model is finish-only: each task and each substep records a single finish event, and its duration is the gap to the previous finish (or the step's start). Never a start+complete pair for a task or substep — a pair stamped at one instant is what produces 0s ticks and bursts.

• Never hand-edit .spec-context.json. Record every finish by running the writer script, never by editing the JSON file yourself — a hand-authored edit is what corrupts the file (a duplicated status key). The script stamps the real clock, writes atomically, and is idempotent. The commands below are the only way you touch timing.

• Self-close — but not specify or implement. When your own work for plan, tasks, clarify, or analyze ends, record the step finish (feature dir from .specify/feature.json):

  python3 .specify/extensions/companion/scripts/write-context.py --feature-dir <feature_dir> --step <this step> --finish --by ai
  

  --finish appends a single step-level complete and touches nothing else (it leaves status/currentStep to the lifecycle hooks). Do NOT self-close specify or implement: the extension closes those itself (specify from its own command, implement from the end-of-step hook), so an ai complete there would duplicate it.

• Substeps — one finish each, via the script. For each substep boundary (plan: research, design; tasks: generate), the moment that substep ends, run:

  python3 .specify/extensions/companion/scripts/write-context.py --feature-dir <feature_dir> --step <step> --substep <name> --finish --by ai
  

  One call per substep, each stamped with its own real clock at the moment it finishes — never two substeps in one batch, never a separate start. The delta between consecutive finishes is each substep's duration.

• Implement — finishing a task is logging it (finish-only). Recording a task's finish is the closing action of that task, done the instant its work is complete and before you start the next one — not a bookkeeping pass you batch at the end of a phase. The closing action is a single append (feature dir from .specify/feature.json):

  python3 .specify/extensions/companion/scripts/write-context.py --feature-dir <feature_dir> --task <TaskID> --kind complete --by ai --did "<one-line summary of what this task did>" --files "<comma,separated,files,touched>" --append
  

  --append writes one line to .spec-context.events.jsonl and does not read or rewrite the shared .spec-context.json, so it never hits the "read the file first" retry and parallel workers can each append their own finish at the same time without contending — the line carries its own real timestamp (date -u is stamped by the script). The --did/--files flags ride along so the Activity panel's Tasks card is populated from the script. Do NOT hand-edit the - [ ] checkbox in tasks.md — the script owns it: materialize flips it to - [x] from your appended finish, so a fanned-out subagent only appends and never touches the shared tasks.md. Do NOT hand-author per-task JSON and do NOT write a per-task start.

  Then fold the appended lines into .spec-context.json — run this once per wave (after the wave reconciles) and again when the step ends:

  python3 .specify/extensions/companion/scripts/write-context.py --feature-dir <feature_dir> --materialize
  

  --materialize is the one read-modify-write: it folds the finishes into the panel and checks off the matching tasks.md boxes for every journaled task, idempotently (re-folding never double-counts), so running it per wave keeps the GUI current without re-serializing the work. The end-of-step hook is a backstop that materializes anything you didn't fold and fills any task you didn't journal. What's trustworthy here is the per-task summary (did/files) and the order tasks completed, plus the step-level start→complete span, which the scripts stamp exactly. The per-task timestamps are best-effort — a single agent logs a task right after building it, so they reflect when you recorded it, not a precisely measured duration; that's fine, the summaries are the point. Still, record each finish as you go, wave by wave rather than dumping every task at the very end — a per-wave cadence keeps the panel live and the ordering true.

• Never write the next step's start. Only the next command appends the next step's start entry; writing it here makes the viewer render a phantom "Generating …".