oprogramadorreal/optimus-claude / skills/jira
jira
VerifiedFetches a JIRA issue via a configured MCP server and distills it into a structured task file at docs/jira/<KEY>.md that downstream skills auto-detect. Analyzes the codebase to surface missing criteria, scope, and risks; optionally writes an analysis comment or implementation tickets back to JIRA after explicit confirmation. Re-runs reconcile the local file instead of regenerating. Guides MCP setup if none is configured.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 6.9 KB |
| SKILL.md | skill md | 6.3 KB |
| agents/openai.yaml | config | 198 B |
| references/jira-codebase-analysis.md | markdown | 6.9 KB |
| references/jira-context-extraction.md | markdown | 8.0 KB |
| references/jira-implementation-tickets.md | markdown | 6.3 KB |
| references/jira-refresh.md | markdown | 7.6 KB |
| references/jira-setup.md | markdown | 3.0 KB |
| references/plan-mode-prompt.md | markdown | 1.0 KB |
references/jira-implementation-tickets.md
View on GitHub# JIRA Implementation Ticket Creation
Create implementation tickets in JIRA after a Complex-scope codebase analysis. This is the only place in the skill that creates new JIRA issues — the **MCP Safety** table in [`jira-context-extraction.md`](jira-context-extraction.md) enumerates the write tools this procedure may call and at which gate.
## Entry condition
Check in order:
1. `docs/jira/<KEY>.md` has an `### Implementation Tickets` table with a real JIRA key — a `Ticket` cell matching `^[A-Z][A-Z0-9]+-\d+$` (`(proposed-N)` placeholders from a prior Skip-mode recording do not count) → skip this procedure, tell the user existing tickets are managed by refresh, and continue to Step 6.
2. The detected server has no create-issue tool (`createJiraIssue` / `jira_create_issue` per the Tool Name Resolution table) → run [Decomposition](#decomposition) and [Recording](#recording) in Proposed mode (no JIRA writes), then continue to Step 6.
3. Otherwise continue to [Decomposition](#decomposition).
## Decomposition
Derive ticket boundaries from the Step 5 output already in `docs/jira/<KEY>.md` (`### Codebase Impact`, `### Suggested Approach`, `### Risks`) — do not re-analyze the codebase.
- One ticket per discrete unit of work in the Suggested Approach. Do NOT split per-file — multi-file changes sharing a goal stay in one ticket.
- A risk requiring its own implementation effort (e.g., a migration backfill) gets its own ticket; a risk that is just a caveat does not.
- Shared infrastructure that gates other work gets the lowest sequence number and is recorded as the prerequisite of dependent tickets.
- Maximum 12 tickets per round. If decomposition produces more, ask the user whether to scope down or split into rounds within this run: run the [Confirmation gate](#confirmation-gate) and [Creation procedure](#creation-procedure) per round of ≤ 12, then [Linking](#linking) and [Recording](#recording) once, after the last round, for every created key.
For each proposed ticket, draft: `summary` (one imperative sentence, ≤ 80 chars), `description` (three sections — `Goal`, `Tied to parent acceptance criteria` with parent criterion numbers, `Prerequisites` listing other ticket keys from this batch or `None`), `issuetype: Task`. Everything, including the section headers, inherits the parent issue's language (the English names here are reference labels — translate from the local file's English content as needed). If the project schema requires `Sub-task` instead of `Task`, that is out of scope — the user creates those manually.
## Confirmation gate
Present the full proposed list before any JIRA write, as a table (`| # | Summary | Type | Prerequisites | Tied to AC |`), then ask the user (AskUserQuestion) — "Create these implementation tickets in JIRA?":
- **Skip — I'll create them manually** (default) — run [Recording](#recording) in Proposed mode (no JIRA writes), continue to Step 6.
- **Create all** — run the [Creation procedure](#creation-procedure) for the full list.
- **Review one-by-one** — per ticket, present the full payload and ask **Create** / **Skip** / **Stop batch** (which finalizes without prompting for the rest). After the loop, proceed to [Linking](#linking) and [Recording](#recording) with the keys created so far.
## Creation procedure
Create tickets in dependency order — prerequisites first (Decomposition already sorted them).
1. Call the create-issue tool with the parent's project key (e.g., `OPTS` for `OPTS-8`) and the drafted `summary`, `description`, `issuetype: Task`. No parent field is needed for `Task`.
2. On success, record the returned key and proceed.
3. On failure (permission, schema, validation), report the tool's error message plus the un-created remainder (drafted summaries and prerequisites), stop the batch, and run [Recording](#recording) for the tickets created so far in Created mode — never mix `(proposed-N)` placeholders into the same table. Do NOT retry automatically: the Entry condition guards real-key rows against duplicate creation, and schema/permission errors won't resolve on retry. The user creates the remainder manually from the drafts in this chat.
## Linking
Run only if the create-link tool is available; best-effort — failures never block the batch. For each created child, call the create-link tool with `inwardIssue` = parent key, `outwardIssue` = child key, and `linkType` = a link type's **name**, not its inward/outward description: if the get-link-types Read tool is available, call it once first and use the name of the type whose name or inward/outward description is `relates`, `relates to`, `related to`, or `is related to` (case-insensitive); otherwise use `Relates`, Jira's default name. If the listed types match none, skip the links and report it — do NOT fall back to directional or causal types (`blocks`, `is blocked by`, `duplicates`, `clones`, `causes`), which would misrepresent the relationship. On a failed link call, record the failure and continue; the local table is the source of truth.
## Recording
Always run after the batch completes or is skipped. Read `docs/jira/<KEY>.md` and append (or replace, if present) the `### Implementation Tickets` section immediately before `### Scope Assessment` (guaranteed present — Task File Update ran before this procedure). Exact format:
```markdown
### Implementation Tickets
| Ticket | Title | Prerequisites |
|--------|-------|---------------|
| <KEY-1> | <summary> | None |
| <KEY-2> | <summary> | <KEY-1> |
```
- **Created mode (Create all / Review one-by-one):** real JIRA keys in the `Ticket` column; note above the table: `Created on YYYY-MM-DD as part of /optimus:jira analysis.` Bump `description-refresh-date` to today.
- **Proposed mode (Skip):** `(proposed-N)` placeholders in the `Ticket` column; note above the table: `Proposed on YYYY-MM-DD; not yet created in JIRA.` Do NOT bump `description-refresh-date` — no JIRA-driven change occurred.
## Refresh interaction
On re-runs, the Entry condition blocks re-creation when real keys are recorded (even on Re-analyze); files with only `(proposed-N)` placeholders remain eligible for a fresh batch. Existing real-key tickets get a read-only drift review via `jira-refresh.md` "Sub-item walk". To spawn an additional batch on top of a real-key recording, the user must remove or rename the `### Implementation Tickets` section first, then re-run and re-analyze.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |