agentleFS
sbaiahmed1sbaiahmed1/react-native-blur/.agents/skills/speckit-clarify/SKILL.md

speckit-clarify

Skill350 starsChanged 4 months agoMITView on GitHub

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

133 other projects use a version of this, 123 of them edited; 98 of 122 edited versions we compared changed its rules; 8 new projects in the last 4 weeks, against 11 the 4 before.

How people change it

98 of 122 edited versions changed its rules, and some changes recur.

Of the 122 edited versions we compared: 11 keep every rule, 13 are an older text, 98 made changes of their own.

Not in older versions

  1. When constructing slash commands from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.missing from 12 of 13
  2. Write the updated spec back to FEATURE_SPEC.missing from 1 of 13
  3. If any Outstanding or Deferred remain, recommend whether to proceed to /speckit-plan or run /speckit-clarify again later post-plan.missing from 1 of 13
  4. Check if .specify/extensions.yml exists in the project root.missing from 1 of 13
  5. If it exists, read it and look for entries under the hooks.before_clarify keymissing from 1 of 13
  6. If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normallymissing from 1 of 13
  7. If the hook has no condition field, or it is null/empty, treat the hook as executablemissing from 1 of 13
  8. If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementationmissing from 1 of 13

Rules people drop

  1. If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normallydropped by 35 of 98
  2. When constructing slash commands from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.dropped by 3 of 98
  3. Check if .specify/extensions.yml exists in the project root.dropped by 2 of 98
  4. If it exists, read it and look for entries under the hooks.before_clarify keydropped by 2 of 98
  5. If the hook has no condition field, or it is null/empty, treat the hook as executabledropped by 2 of 98
  6. If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementationdropped by 2 of 98
  7. If no hooks are registered or .specify/extensions.yml does not exist, skip silentlydropped by 2 of 98

Rules people add

  1. Check if FEATURE_DIR/checklists/requirements.md exists.added by 95 of 98
  2. If it does NOT exist, skip this step silently.added by 95 of 98
  3. Read the checklist file.added by 95 of 98
  4. If the item now passes and was unchecked: change [ ] to [x].added by 95 of 98
  5. If the state is unchanged: leave the marker as-is (preserve existing case to avoid cosmetic diffs).added by 95 of 98
  6. 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.added by 64 of 98
  7. After the ?, the only permitted suffix is an optional parenthesized requirement/question id. Exact format: **Question:** <interrogative>? or **Question:** <interrogative>? (FR-023). …added by 64 of 98
  8. 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.added by 64 of 98

We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.

Adopted by

Cooling: 8 new projects took it in the last 4 weeks, 0.7× the 4 weeks before.

Week of Sep 20: 3 new projectsWeek of Sep 27: 3 new projectsWeek of Oct 4: 2 new projectsWeek of Oct 11: 3 new projectsWeek of Oct 18: 2 new projectsWeek of Oct 25: 2 new projectsWeek of Nov 1: 2 new projectsWeek of Nov 8: 2 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read.

Most recently taken up by

Used with

Projects with it also use speckit-agent-context-update, speckit-baseline and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Microsoft AzureSkill

    speckit-agent-context-update

    Refresh the managed Spec Kit section in coding agent context file(s)

    Also in 13 projects that use this

  • patterson-agentsSkill

    speckit-baseline

    Generate feature specifications by analyzing existing source code.

    Also in 3 projects that use this

  • patterson-agentsSkill

    claude-command-converter

    Convert Claude Code commands (.claude/commands/*.md) to standard Agent Skills (skills/*/SKILL.md). Use when migrating slash commands to portable skill format, creating skills from existing commands, or standardizing command definitions across AI runtimes.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    agentic-workflows

    Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

    Also in 3 projects that use this

  • SentrySkill

    commit

    Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

    Also in 4 projects that use this

  • GoogleSkill

    improve-codebase-architecture

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

32 rules. 19 are common, 0 are distinctive, and 13 are very specific to this project.

  • 19

    Common

    Most of the 123 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 13

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check if .specify/extensions.yml exists in the project root.

    line 25
  2. Very specific:

    If it exists, read it and look for entries under the hooks.before_clarify key

    line 26
  3. Common:

    If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally

    line 27
  4. Very specific:

    If the hook has no condition field, or it is null/empty, treat the hook as executable

    line 30
  5. Very specific:

    If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementation

    line 31
  6. Very specific:

    When constructing slash commands from hook command names, replace dots (.) with hyphens (-).

    line 32
  7. Very specific:

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

    line 55
  8. Very specific:

    Run .specify/scripts/bash/check-prerequisites.sh --json --paths-only from repo root once (combined --json --paths-only mode / -Json …

    line 65
  9. Very specific:

    If JSON parsing fails, abort and instruct user to re-run /speckit-specify or verify feature branch environment.

    line 69
  10. Common:

    Only include questions whose answers materially impact architecture, data modeling, task decomposition, test design, UX behavior, …

    line 133
  11. Common:

    Ensure category coverage balance: attempt to cover the highest impact unresolved categories first.

    line 134
  12. Common:

    If more than 5 categories remain unresolved, select the top 5 by (Impact * Uncertainty) heuristic.

    line 137
  13. Very specific:

    After the table, add: You can reply with the option letter (e.g., "A"), accept the recommendation by saying "yes" or "recommended", or …

    line 158
  14. Common:

    After the user answers:

    line 163
  15. Common:

    If the user replies with "yes", "recommended", or "suggested", use your previously stated recommendation/suggestion as the answer.

    line 164
  16. Common:

    If ambiguous, ask for a quick disambiguation (count still belongs to same question.

    line 166
  17. Common:

    Stop asking further questions when:

    line 168
  18. Common:

    All critical ambiguities resolved early (remaining queued items become unnecessary), OR

    line 169
  19. Common:

    Never reveal future queued questions in advance.

    line 172
  20. Common:

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

    line 173
  21. Very specific:

    Ensure a ## Clarifications section exists (create it just after the highest-level contextual/overview section per the spec template if …

    line 178
  22. Common:

    If the clarification invalidates an earlier ambiguous statement, replace that statement instead of duplicating.

    line 188
  23. Common:

    Keep each inserted clarification minimal and testable (avoid narrative drift).

    line 191
  24. Common:

    No contradictory earlier statement remains (scan for now-invalid alternative choices removed).

    line 197
  25. Very specific:

    Write the updated spec back to FEATURE_SPEC.

    line 201
  26. Very specific:

    If any Outstanding or Deferred remain, recommend whether to proceed to /speckit-plan or run /speckit-clarify again later post-plan.

    line 208
  27. Common:

    If no meaningful ambiguities found (or all potential questions would be low-impact), respond: "No critical ambiguities detected worth …

    line 213
  28. Very specific:

    If spec file missing, instruct user to run /speckit-specify first (do not create a new spec here).

    line 214
  29. Common:

    Never exceed 5 total asked questions (clarification retries for a single question do not count as new questions).

    line 215
  30. Common:

    Avoid speculative tech stack questions unless the absence blocks functional clarity.

    line 216
  31. Common:

    If no questions asked due to full coverage, output a compact coverage summary (all categories Clear) then suggest advancing.

    line 218
  32. Common:

    If quota reached with unresolved high-impact categories remaining, explicitly flag them under Deferred with rationale.

    line 219

“Common” is measured: kept by at least 6 in 10 of the 123 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:
      OptionDescription
      A<Option A description>
      B<Option B description>
      C<Option C description> (add D/E as needed up to 5)
      ShortProvide 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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.