grinrus/spec-interview
skills/spec-interview/SKILL.md
Collects missing spec inputs and synchronizes answers into `spec.yaml`. Use when review-spec leaves unresolved specification fields. Do not use when the request is readiness gating in `review-spec` or task derivation in `tasks-new`.
$ install --global
skillsauthnpx skillsauth add grinrus/ai_driven_dev spec-interviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 3:33 PM3.9s3 files scanned
SKILL.md
- name:
- spec-interview
- description:
- Collects missing spec inputs and synchronizes answers into `spec.yaml`. Use when review-spec leaves unresolved specification fields. Do not use when the request is readiness gating in `review-spec` or task derivation in `tasks-new`.
- argument-hint:
- $1 [note...]
- lang:
- ru
- prompt_version:
- 1.0.15
- source_version:
- 1.0.15
- model:
- inherit
- disable-model-invocation:
- true
- user-invocable:
- true
Follow feature-dev-aidd:aidd-core.
Steps
- Set active stage
spec-interviewand active feature. - Run
python3 ${CLAUDE_PLUGIN_ROOT}/skills/spec-interview/runtime/spec_interview.py --ticket <ticket>. - Run subagent
feature-dev-aidd:spec-interview-writer. - Use
AskUserQuestionToolto gather missing spec details; updateaidd/docs/spec/<ticket>.spec.yaml. - If answers arrive, sync them into the spec and
AIDD:OPEN_QUESTIONS/AIDD:DECISIONSas needed. - Return the output contract and next step
/feature-dev-aidd:tasks-new <ticket>.
Command contracts
python3 ${CLAUDE_PLUGIN_ROOT}/skills/spec-interview/runtime/spec_interview.py
- When to run: as canonical spec interview entrypoint after review-spec and before tasklist derivation.
- Inputs:
--ticket <ticket>with current PRD/plan context and optional notes. - Outputs: updated
spec.yaml, synchronized open questions/decisions, and stage status. - Failure mode: non-zero exit when required source artifacts are missing or spec contract is violated.
- Next action: gather missing inputs/answers, then rerun the same command.
Notes
- Use the aidd-core question format.
- Planning stage:
AIDD:ACTIONS_LOG: n/a. - Canonical stage name:
spec-interview(legacy aliasspecnormalizes tospec-interview).
Additional resources
- Spec template source: templates/spec.template.yaml (when: creating or reconciling spec structure; why: keep generated
spec.yamlaligned with canonical schema).
Related Skills
grinrus/tasks-new
tools
VerifiedTrustedCommunity
Derives or refines tasklist items from PRD and plan artifacts. Use when tasklist stage prepares implementation-ready work items. Do not use when the request is plan authoring in `plan-new` or loop execution in `implement`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/status
testing
VerifiedTrustedCommunity
Generates consolidated ticket status summary and key artifact pointers. Use when checking current stage state or handoff readiness. Do not use when the request is diagnostics/inventory from `aidd-observability` or flow-state mutation via `aidd-flow-state`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/review
testing
VerifiedTrustedCommunity
Runs review-stage validation for scope changes, findings, and follow-up task derivation. Use when review stage needs verdict and handoff tasks. Do not use when the request is direct implementation execution in `implement` or QA validation in `qa`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/review-spec
tools
VerifiedTrustedCommunity
Reviews plan and PRD, then gates readiness for task derivation. Use when plan and PRD artifacts are ready for downstream planning readiness. Do not use when the request is plan authoring in `plan-new` or task derivation in `tasks-new`.
5SKILL.mdUpdated Apr 5, 2026