skills/executing-jira-task/SKILL.md
Executes exactly one planned Jira workflow task after critique approval. Use when a numbered task should move through kickoff, implementation, documentation, requirements verification, review gates, targeted fix cycles, and final reporting without continuing to the next task.
npx skillsauth add b-mendoza/agent-skills executing-jira-taskInstall 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.
You are the per-task execution orchestrator for the Jira workflow. Do three things: validate readiness, dispatch the next specialist, and decide whether to advance, run a targeted fix cycle, or escalate. Specialists do the heavy lifting in isolation; the orchestrator carries only concise summaries, paths, and verdicts between phases.
The execution kickoff is the first mutation boundary after critique approval. Everything before kickoff remains critique and planning on disk.
| Input | Required | Example | Notes |
| ----- | -------- | ------- | ----- |
| TICKET_KEY | Yes | JNS-6065 | Used to derive artifact and Jira paths. |
| TASK_NUMBER | Yes | 3 | Exactly one task per invocation. |
Required artifacts, readiness checks, handoff shapes, kickoff semantics, and
artifact lifecycle rules live in ./references/contracts.md. Read that file
before crossing the execution boundary.
| Stage | Goal | Primary result |
| ----- | ---- | -------------- |
| 0. Readiness | Confirm the selected task can start | Ready task or explicit blocker |
| 1. Kickoff | Enter the planned branch and start tracker state | KICKOFF_REPORT |
| 2. Execution | Implement the approved change | EXECUTION_REPORT |
| 3. Documentation | Add in-code docs and update local tracking before gates | DOCUMENTATION_REPORT |
| 4. Requirements Verification | Confirm Definition of Done coverage | VERIFICATION_RESULT |
| 5. Quality Gates | Run clean-code, architecture, security review | Review verdicts |
| 6. Targeted Fix Cycle | Re-run only failed verification or review paths with explicit retry budgets | Re-validated task or escalation |
| 7. Finalize and Report | Finalize eligible Jira completion after gates and report this task's outcome | FINAL_TRACKING_REPORT and FINAL_TASK_REPORT |
| Subagent | Path | Purpose |
| -------- | ---- | ------- |
| execution-starter | ./subagents/execution-starter.md | Performs kickoff, workspace checks, branch entry, and eligible Jira startup updates. |
| task-executor | ./subagents/task-executor.md | Implements the scoped change and tests from approved planning artifacts. |
| documentation-writer | ./subagents/documentation-writer.md | Adds minimal in-code docs, updates task tracking, and finalizes optional Jira completion updates only after gates pass. |
| requirements-verifier | ./subagents/requirements-verifier.md | Checks that the task's DoD is fully implemented before quality review. |
| clean-code-reviewer | ./subagents/clean-code-reviewer.md | Reviews readability, maintainability, SOLID alignment, and test quality. |
| architecture-reviewer | ./subagents/architecture-reviewer.md | Reviews domain boundaries, composition, and architectural fit. |
| security-auditor | ./subagents/security-auditor.md | Audits the task-scoped change set for exploitable security weaknesses. |
Read exactly one subagent definition per dispatch and pass only the inputs that subagent needs.
This package is standalone: runtime-critical rules are bundled in this skill folder. External URLs are optional just-in-time background, not dependencies for normal execution.
Use progressive disclosure:
| Need | Read |
| ---- | ---- |
| Artifact contracts and readiness checks | ./references/contracts.md |
| Normal execution flow and fix-loop order | ./references/pipeline.md |
| Status handling, retries, escalations | ./references/retry-and-escalation.md |
| Shared reviewer expectations | ./references/review-gate-policy.md |
| Optional website links for current/source-backed context | ./references/external-sources.md |
| Dispatch and targeted-fix examples | ./references/examples.md |
| Final user report template | ./references/template-final-report.md |
Subagent report templates are loaded by the corresponding subagent only at return time:
| Subagent | Return template |
| -------- | --------------- |
| execution-starter | ./references/template-execution-kickoff-report.md |
| task-executor | ./references/template-execution-report.md |
| documentation-writer | ./references/template-documentation-report.md |
| requirements-verifier | ./references/template-requirements-verification.md |
| clean-code-reviewer | ./references/template-code-quality-review.md |
| architecture-reviewer | ./references/template-architecture-review.md |
| security-auditor | ./references/template-security-audit.md |
When documentation-writer runs in FINALIZE_TRACKER mode, it uses
./references/template-documentation-report.md and returns that report as
FINAL_TRACKING_REPORT.
./references/contracts.md and confirm the selected task is ready to
cross the execution boundary../references/pipeline.md and follow its phase order.Every run ends with exactly one FINAL_TASK_REPORT using
./references/template-final-report.md. Allowed final statuses are COMPLETE,
BLOCKED, STOPPED_FOR_USER_INPUT, and ESCALATED.
On COMPLETE, the workflow produces Category B implementation changes, updates
Category A tracking artifacts on disk, records eligible Jira startup updates or
skips, finalizes eligible Jira completion updates only after requirements and
quality gates pass, and includes the quality-gate summary and implementation
artifact summary expected by the parent orchestrator.
Stopped or escalated runs still return a FINAL_TASK_REPORT with the blocker,
retry counts, preserved phase results, unresolved items, and next required
action.
Input: TICKET_KEY=JNS-6065, TASK_NUMBER=3
./references/contracts.md.execution-starter; continue only on KICKOFF_REPORT -> READY../references/pipeline.md order.FINAL_TASK_REPORT using
./references/template-final-report.md.testing
Diagnoses runtime bugs, crashes, regressions, failing CI/CD pipelines, and underspecified user reports through read-only, evidence-first root-cause analysis with traceable reports and bounded subagent workflows.
tools
Coordinate an end-to-end Jira or GitHub work-item workflow from initial fetch through per-task implementation. Use this skill when the user provides a Jira ticket URL, a GitHub issue URL, owner/repo/issue coordinates, says "work on ticket PROJECT-123", "work on issue owner/repo#42", "resume <work-item-key>", "continue this workflow", or asks for status without naming a specific phase. This top-level coordinator detects the platform from the input, loads the matching playbook just-in-time, keeps SKILL.md as a routing layer, and dispatches execution-heavy work to downstream skills or co-located utility subagents.
testing
Retrieves a Jira ticket or a GitHub issue into docs/<KEY>.md as a read-only, validated Markdown snapshot for downstream workflow phases. Use when a Jira URL, a GitHub issue URL, or owner/repo/number coordinates need the Phase 1 fetch-work-item step. Detects the platform from the input and loads the matching playbook just-in-time.
development
Runs a structured nine-seat council deliberation on an idea, project, business, startup, goal, or objective, then writes a full decision handoff file with a compact recommendation summary and reusable mental-model teaching cards. Use when a user asks to stress-test a decision, get adversarial review, classify a decision as reversible or irreversible, or wants multiple independent perspectives on a course of action.