skills/jira-to-gh/SKILL.md
Bridge a Jira (DAFO) ticket to the agent-native GitHub repo flow. Two modes — --mirror creates a one-to-one GH issue in RonanCodes/dataforce with linkbacks both ways; --prd seeds /ro:write-a-prd from the ticket body and publishes the PRD as a GH parent issue. Use when a Taskforce-filed DAFO ticket needs to enter the Skip+Ronan implementation pipeline.
npx skillsauth add RonanCodes/ronan-skills jira-to-ghInstall 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.
The Taskforce partners file work in Jira (DAFO board). Skip and Ronan implement in RonanCodes/dataforce using the agent-native repo pattern (ready-for-agent label, PRDs as GH issues, ralph/planner-worker consume from the queue). This skill is the bridge.
One-way by default: Jira → GitHub. Status drift is acceptable — Jira reflects the partner-facing state ("In Review" until they sign off), GH reflects the implementation state ("merged" the moment a PR lands). Skill ensures URLs are linked both ways so anyone can navigate.
/ro:jira-to-gh DAFO-42 # default: --mirror, into RonanCodes/dataforce
/ro:jira-to-gh DAFO-42 --mirror # one-to-one GH issue
/ro:jira-to-gh DAFO-42 --prd # seed /ro:write-a-prd from ticket body, publish as GH parent
/ro:jira-to-gh DAFO-42 --mirror --repo RonanCodes/some-other-repo
/ro:jira working (atlassian MCP authenticated)gh CLI authenticated against RonanCodes (or whichever target org)--prd: the /ro:write-a-prd skill installed; /ro:repo-mode resolved to personal for the target repo so the PRD publishes to GH and not .ralph/--mirror (default)For: small / well-specified DAFO tickets that map to a single agent slice.
Steps:
getJiraIssue). Capture: summary, description, type (Bug/Story/Task/Feature), labels, reporter, current status.## Source
Mirrored from Jira **DAFO-42** — https://simplicitylabs.atlassian.net/browse/DAFO-42
Reporter: <Jira reporter name>
Type: <Bug|Story|Task|Feature>
## Description
<Jira description, converted to GitHub-flavoured markdown>
gh issue create:
ready-for-agent, plus a type-derived label (bug, feature, task)Mirrored to GitHub for implementation: <gh issue URL>
Status updates will appear here when the GH issue closes.
--prdFor: larger DAFO tickets that need decomposition into vertical slices, or anything the user wants grilled with Matt Pocock's 7-section template.
Steps:
--mirror./ro:write-a-prd with the ticket body as the seed brief. The PRD interview will grill on Problem / Users / Scope / Out-of-Scope / Acceptance / Risks / Sequencing.PRD authored from this ticket: <gh parent issue URL>
Next: slicing into vertical-slice issues via /ro:slice-into-issues.
/ro:slice-into-issues <PRD#> — but do not run it automatically. User decides when to slice./ro:slice-into-issues when ready.This skill does NOT auto-sync status. Reason: Jira lifecycle (Taskforce-facing) and GH lifecycle (implementation-facing) diverge intentionally. A DAFO ticket can sit in "In Review" while three GH PRs ship and re-ship around it.
Convention:
Closes #N), the user (or a close-with-summary subagent) should run /ro:jira move DAFO-42 "In Review" and post a comment with the deploy URL./ro:jira move DAFO-42 done.The "Done means shipped" rule from the partnership chat is preserved by keeping the moves manual.
| Symptom | Cause | Fix |
|---|---|---|
| gh: command not found or auth error | gh not installed / not auth'd | Install gh, run gh auth login |
| Jira ticket fetched but description is empty | DAFO ticket was filed without body | Fetch comments too and use the first comment as description |
| Markdown formatting from Jira renders ugly on GH | Atlassian wiki markup vs GitHub MD difference | The MCP usually returns ADF/markdown; if it returns wiki markup, run through a converter or strip noise manually |
| /ro:write-a-prd opens but doesn't know about the Jira context | Seed not passed cleanly | Pre-format the brief as a single paragraph before the handoff; mention the DAFO key in the first line |
/ro:jira — basic ticket CRUD/ro:write-a-prd — Matt Pocock 7-section PRD interview, publishes to GH/ro:slice-into-issues — vertical-slice a PRD into ready-for-agent children/ro:ralph, /ro:planner-worker — consume the ready-for-agent queue[[agent-native-repo-pocock]] in llm-wiki-skill-labtesting
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
development
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
tools
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
research
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".