smith-clarify

name	smith-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.
handoffs	[{"label":"Build Technical Plan","agent":"smith-plan","prompt":"Create a plan for the spec. I am building with..."}]

Workflow requirement (Smith 20+): This skill must be invoked from inside an active top-level workflow (/smith-new, /smith-bugfix, /smith-debug, /smith-build). The workflow-gate hook will block standalone invocation. To use this skill standalone, start a top-level workflow first.

Vault Logging

Throughout this action, log significant events to the vault session log. Read the session log path from .smith/vault/.current-session. If the file is missing or the vault is not initialized, skip all logging silently.

Append entries using this format:

### [HH:MM:SS] /smith-clarify <event>

**User Request:**
> <verbatim user message that triggered this action>

**Synthesized Input:** <brief summary>
**Outcome:** <what happened>
**Artifacts:** <files modified>
**Systems affected:** <system IDs>

Log at these points:

1. On invocation — which spec is being clarified (feature name and path)
2. After questions asked — number of questions, brief topic summary for each
3. After answers received — decision summary for each answered question (topic + chosen option)
4. After spec updates — which sections of the spec were updated based on answers

User Input

$ARGUMENTS

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

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 /smith-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 /smith-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").

   Questions file location: Store the questions file inside the feature spec folder at FEATURE_DIR/questions.md (NOT in a separate specs/questions/ directory). The questions are part of the feature's decision record and should travel with the feature spec. If FEATURE_DIR points to a .specify/systems/<system>/features/<feature>/ path, use that directly. If clarify is run multiple times, append new questions to the existing file with a ### Session YYYY-MM-DD timestamp header rather than overwriting.

1.5. Check for existing unanswered questions. After resolving FEATURE_DIR, check if FEATURE_DIR/questions.md exists. If it does, scan for unanswered questions — lines matching **Answer**: ___ or **Answer:** followed by only whitespace/underscore.

If unanswered questions exist: Skip the spec ambiguity scan (steps 2-3) and enter the Interactive Answer Collection flow below. This handles the case where /smith-new generated a questions.md during the planning phase and the user wants to answer them conversationally.

If no questions.md exists, or all questions are already answered: Proceed with the normal spec ambiguity scan (steps 2-4).

---

Interactive Answer Collection (for existing questions.md)

When a questions.md file exists with unanswered questions, walk through each one interactively:

A. Parse questions.md — extract all question blocks. Each block has: question number, topic, context, question text, options table, recommended answer, and current answer status.

B. For each unanswered question, present it one at a time:

Display in this format:

## Question [N] of [Total]: [Topic]

**Context:** [Quote from plan/spec that raises this question]

**Question:** [The specific implementation decision]

**Options:**
| Option | Description | Implications |
|--------|-------------|--------------|
| A | [description] | [pros: ..., cons: ...] |
| B | [description] | [pros: ..., cons: ...] |
| C | [description] | [pros: ..., cons: ...] |

**Recommended:** [Option letter] — [Clear reasoning for why this is the best choice]

Reply with an option letter (e.g., "A"), say "yes" to accept the recommendation,
type "skip" to defer this question, or provide your own custom answer.

C. Process the user's response:

• "yes", "recommended", or "rec" → use the recommended answer
• An option letter ("A", "B", "C") → use that option's description as the answer
• "skip" → mark as **Answer:** SKIPPED — needs follow-up
• Anything else → accept as a custom answer verbatim

D. After each answer, immediately:

1. Update questions.md — replace the **Answer**: ___ line for that question with **Answer:** [chosen answer]
2. Confirm to the user: Saved: Q[N] → [brief answer summary]. ([remaining] questions remaining)
3. Present the next unanswered question

E. If the session is interrupted before all questions are answered, the questions.md file reflects the current state — answered questions have their answers filled in, unanswered questions still show **Answer**: ___. The user can resume later by running /smith-clarify again (it will pick up where they left off).

F. After all questions are answered (or the user says "done"):

1. Update questions.md header — change **Status**: AWAITING ANSWERS to **Status**: ANSWERED (or PARTIALLY ANSWERED if any were skipped)
2. Display a summary of all answers:

   ## Answers Summary
   
   | # | Topic | Answer |
   |---|-------|--------|
   | Q1 | [topic] | [answer] |
   | Q2 | [topic] | [answer] |
   | Q3 | [topic] | SKIPPED |
   ...
   

3. Ask: "Would you like to change any answers before proceeding? Reply with a question number to revise, or 'looks good' to continue."
4. If the user wants to change an answer, re-present that question and collect a new answer. Update questions.md.
5. Once confirmed, update spec.md with the decisions from the answered questions:
   • For each non-skipped answer, identify the relevant section of spec.md and incorporate the decision
   • Add or update a ## Implementation Decisions section in the spec if answers affect implementation approach
   • Save spec.md
6. Suggest next step: "Questions answered and spec updated. Next: /smith-plan to generate the implementation plan."

Log all answers to the vault session log per the Vault Logging section above.

After completing the Interactive Answer Collection, skip to step 8 (Report completion).

---

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 10 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 Non-Functional / Quality Attributes section (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 /smith-plan or run /smith-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 /smith-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