skills/team/jira-review/SKILL.md
Reviews Jira issues for implementation readiness. Detects complexity signals, parses acceptance criteria, and recommends clarification or planning mode when needed. Use when reviewing a Jira issue for readiness, checking whether a ticket has enough detail to implement, assessing acceptance-criteria completeness, or evaluating a story before sprint planning. Not for completed implementations (reviews readiness, not accuracy), or non-Jira trackers.
npx skillsauth add michaelalber/ai-toolkit jira-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
"Unclear requirements are the root cause of most project failures. Questions asked now prevent misunderstandings later."
Before writing a single line of code, we must understand what we're building and why. This skill systematically reviews Jira issues before implementation to prevent wasted effort (catch ambiguity early), surface hidden complexity (identify technical risk before it blocks), ensure testability (clear AC enable TDD), and align expectations. Readiness is assessed from measurable signals, not intuition — complexity is scored, gaps are named, and the recommendation follows deterministically.
Non-Negotiable Constraints:
Full principle table, extraction algorithm, scoring, signal detection, discipline rules, and worked
examples live in references/conventions.md.
TRIGGER Auto-activate on jira_get_issue / jira_get_issue_with_docs. Review before any impl work.
EXTRACT Parse the description for AC, DoD, user story, technical requirements (algorithm + patterns
in conventions.md / description-patterns.md). Flag unstructured descriptions.
SCORE Apply the 5-dimension weighted complexity score (conventions.md / complexity-scoring.md).
Detect RED/YELLOW/GREEN signals. Record the signals behind the score.
RECOMMEND Decide deterministically:
complexity < 40% AND ac_complete AND dod_present → READY TO IMPLEMENT (→ /tdd-cycle)
complexity > 70% OR critical_info_missing → NEEDS PLANNING MODE (→ plan mode)
otherwise → NEEDS CLARIFICATION
(≤ 5 questions, clarifying-questions.md)
REPORT Emit the structured review (output-templates.md) with the recommendation, named gaps,
and the handoff snippet for the chosen path.
Exit criteria: AC/DoD extracted (or their absence flagged), complexity scored with named signals, a single deterministic recommendation issued, and — when NEEDS CLARIFICATION — specific, prioritized questions provided.
<jira-review-state>
phase: TRIGGER | EXTRACT | SCORE | RECOMMEND | REPORT | COMPLETE
issue_key: [KEY-123]
issue_type: story | bug | task | epic
ac_found: yes | no | partial
dod_found: yes | no | partial
complexity_pct: [number or "unable to assess"]
critical_info_missing: true | false
recommendation: ready | needs-clarification | needs-planning | pending
open_questions: [count]
last_action: [description]
next_action: [description]
</jira-review-state>
references/output-templates.md.references/complexity-scoring.md.references/description-patterns.md.references/clarifying-questions.md.references/conventions.md.| Skill | Relationship |
|-------|-------------|
| tdd-cycle | The handoff for READY TO IMPLEMENT — write tests from the AC, implement, refactor. |
| task-decomposition | For NEEDS PLANNING MODE on high-complexity issues — break the issue into implementable sub-tasks. |
development
Interviews the user relentlessly about a plan, decision, or idea — one question at a time, each with a recommended answer. Shared engine behind "grill-me" and "grill-with-docs". Use on any "grill" trigger phrase or to stress-test thinking. Do NOT use to build the plan; it ends at shared understanding, not implementation.
testing
Runs a relentless interview to sharpen a plan or design, capturing the decisions as ADRs and a glossary along the way. Use when the user wants to be grilled AND wants the session to leave durable domain documentation behind. Do NOT use for a throwaway stress-test with no artifacts; use grill-me instead.
tools
OWASP-based security review of Vue/TypeScript front-ends. Detects framework (Vite/Vue CLI/Nuxt), entry points, and data flows; scans the OWASP Top 10 (2025) mapped to Vue client-side risks (raw-HTML XSS via v-html, URL/protocol injection, bundled secrets, insecure token storage, dependency CVEs, missing CSP, open redirects, router guard bypass); emits an exec summary plus graded findings. Use to audit Vue for vulnerabilities. Not for architecture grading (vue-architecture-checklist).
tools
Analyzes legacy Vue codebases and produces actionable modernization plans. Primary migration paths include Options API to Composition API, Vue 2 to Vue 3, Vue CLI to Vite, JavaScript to TypeScript, Vue Test Utils/Karma/Mocha to Vitest + Vue Testing Library, legacy Vuex to Pinia, and removed-in-Vue-3 pattern cleanup (filters, event bus, `$listeners`). Does NOT perform the migration — assesses, quantifies risk, and plans.