Resolve ambiguities in any project artifact — auto-detects the most recent artifact (spec, plan, checklist, testify, tasks, or constitution), asks targeted questions with option tables, and writes answers back into the artifact's Clarifications section. Use when requirements are unclear, a plan has trade-off gaps, checklist thresholds feel wrong, test scenarios are imprecise, task dependencies seem off, or constitution principles are vague.
From jm-adknpx claudepluginhub javimontano/jm-adk-alfaThis skill uses the workspace's default tool permissions.
agents/guardian.mdagents/lead.mdagents/specialist.mdagents/support.mdevals/evals.jsonknowledge/body-of-knowledge.mdknowledge/knowledge-graph.mdprompts/meta.mdprompts/primary.mdprompts/variations/deep.mdprompts/variations/quick.mdreferences/ambiguity-taxonomies.mdreferences/clarification-format.mdreferences/constitution-loading.mdreferences/conversation-guide.mdreferences/model-recommendations.mdtemplates/output.docx.mdtemplates/output.htmlSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Ask targeted clarification questions to reduce ambiguity in the detected (or user-specified) artifact, then encode answers back into it. [EXPLICIT]
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty). [EXPLICIT]
If the user provides a target argument (e.g., plan, spec, checklist, testify, tasks, constitution), use that artifact instead of auto-detection. [EXPLICIT]
Load constitution per constitution-loading.md (soft mode — parse if exists, continue if not). [EXPLICIT]
Run: bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/check-prerequisites.sh --phase clarify --json
Windows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/check-prerequisites.ps1 -Phase clarify -Json
Parse JSON. If needs_selection: true: present the features array as a numbered table (name and stage columns). Follow the options presentation pattern in conversation-guide.md. After user selects, run:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/set-active-feature.sh --json <selection>
Windows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/set-active-feature.ps1 -Json <selection>
Then re-run the prerequisites check from step 1.
Determine the target artifact (see "Target Detection" below).
If the user provided a target argument, map it: [EXPLICIT]
| Argument | Artifact file |
|---|---|
spec | {FEATURE_DIR}/spec.md |
plan | {FEATURE_DIR}/plan.md |
checklist | {FEATURE_DIR}/checklists/*.md (all files) |
testify | {FEATURE_DIR}/tests/features/*.feature (read for scanning), {FEATURE_DIR}/tests/clarifications.md (write Q&A) |
tasks | {FEATURE_DIR}/tasks.md |
constitution | {REPO_ROOT}/CONSTITUTION.md |
If no argument, auto-detect by checking artifacts in reverse phase order. Pick the first that exists: [EXPLICIT]
{FEATURE_DIR}/tasks.md{FEATURE_DIR}/tests/features/*.feature{FEATURE_DIR}/checklists/*.md{FEATURE_DIR}/plan.md{FEATURE_DIR}/spec.md{REPO_ROOT}/CONSTITUTION.mdIf no clarifiable artifact exists: ERROR with No artifacts to clarify. Run /iikit-01-specify first or /iikit-00-constitution. [EXPLICIT]
Load the target artifact and perform a structured scan using the taxonomy for that artifact type from ambiguity-taxonomies.md. Mark each area: Clear / Partial / Missing. [EXPLICIT]
Constraints:
Present ONE question at a time. [EXPLICIT]
For multiple-choice: follow the options presentation pattern in conversation-guide.md. Analyze options, state recommendation with reasoning, render options table. User can reply with letter, "yes"/"recommended", or custom text.
After answer: validate against constraints, record, move to next.
Stop when: all critical ambiguities resolved or user signals done.
## Clarifications section exists in the target artifact with ### Session YYYY-MM-DD subheading- Q: <question> -> A: <answer> [<refs>]
Testify exception: .feature files are Gherkin syntax — do NOT add markdown sections to them. Instead:
.feature files for ambiguities (step 1){FEATURE_DIR}/tests/clarifications.md (create if missing).feature files themselves (update scenarios, add/remove steps)See clarification-format.md for format details. [EXPLICIT]
After each write and final pass: [EXPLICIT]
[refs]Output: questions asked/answered, target artifact and path, sections touched, traceability summary table (clarification -> referenced items), coverage summary (category -> status), suggested next command. [EXPLICIT]
Next command logic: run check-prerequisites.sh --json status and use its next_step field. This returns the actual next phase based on feature state (which artifacts exist), not what was just clarified. Clarify can run at any point — the next step depends on where the feature is, not where clarify was invoked.
Commit the modified artifact(s): [EXPLICIT]
git add -u
git commit -m "clarify: <target-artifact> Q&A"
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/generate-dashboard-safe.sh
Windows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/generate-dashboard-safe.ps1 [EXPLICIT]
Run: bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/next-step.sh --phase clarify --json [EXPLICIT]
Windows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/next-step.ps1 -Phase clarify -Json [EXPLICIT]
Parse the JSON and present: [EXPLICIT]
clear_after is true: suggest /clear before proceeding (always true for clarify — Q&A sessions consume significant context)next_step as the primary recommendationalt_steps non-empty: list as alternativesnext_step and each alt_step, include the model_tier from the JSON so the user knows which model is best for each option. Look up tiers in model-recommendations.md for agent-specific switch commands.Format:
Clarification complete! [EXPLICIT]
Next: /clear → <next_step> [EXPLICIT]
[- <alt_step> — <reason> (model: <tier>)]
- Dashboard: file://$(pwd)/.specify/dashboard.html (resolve the path)
Example invocations: [EXPLICIT]
| Scenario | Handling |
|---|---|
| Empty or minimal input | Request clarification before proceeding |
| Conflicting requirements | Flag conflicts explicitly, propose resolution |
| Out-of-scope request | Redirect to appropriate skill or escalate |