rhdh-jira-create
Skill20 starsChanged 21 days agoApache-2.0View on GitHub
Opens new work in RHDH Jira and decides what kind of work it is — Feature or Feature Request in RHDHPLAN, Epic, Story, Task, Spike or Vulnerability in RHIDP, Bug in RHDHBUGS, support conversation in RHDHSUPP — then interviews, drafts, and creates it with the right fields and parent link. Use for "file a ticket", "create a feature", "open an epic for this", "raise a bug", "log a spike", "we should track this in Jira", or turning an RHDHSUPP support case into an RHDHBUGS defect or an RHDHPLAN feature request. Picking the issue type is this skill's job, not the caller's. Editing or transitioning an issue that already exists, such as RHIDP-1234, is not creation.
In this repository73 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- rhdh-base-imagesSkill
- rhdh-konflux-rpaSkill
- rhdh-konflux-tasksSkill
- rhdh-plugin-catalog-index-status-and-update-flowSkill
- rhdh-pr-mrSkill
- rhdh-prow-jobsSkill
- rhdh-prow-release-branchSkill
- rhdh-prow-triggerSkill
- rhdh-yarn-bumpSkill
- rhdh-feature-docsSkill
- rhdh-jira-linkSkill
- rhdh-jira-refineSkill
- rhdh-jira-sprint-planSkill
- rhdh-jira-sprint-reportSkill
- rhdh-jira-updateSkill
- rhdh-prepare-refinementSkill
- agent-readinessSkill
- ask-rhdhSkill
- clean-proseSkill
- setup-rhdh-skillsSkill
- skill-authoringSkill
- rhdh-backportSkill
- rhdh-backstage-upgradeSkill
- rhdh-localSkill
- rhdh-operator-pr-testSkill
- rhdh-overlaySkill
- rhdh-playwrightSkill
- rhdh-plugin-authoringSkill
- rhdh-plugin-bug-fixSkill
- rhdh-plugin-exportSkill
- rhdh-plugin-midstream-propagateSkill
- rhdh-plugin-nfs-migrationSkill
- rhdh-plugin-wiringSkill
- rhdh-pr-createSkill
- rhdh-pr-reviewSkill
- rhdh-test-placementSkill
- backstage-api-changesSkill
- mutation-gateSkill
- openspec-journalSkill
- prose-editingSkill
- rhdh-contextSkill
- rhdh-forgeSkill
- rhdh-jira-apiSkill
- rhdh-jira-authoringSkill
- rhdh-spec-driven-schemaSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-audit-changeSkill
- openspec-bulk-archive-changeSkill
- openspec-continue-changeSkill
- openspec-exploreSkill
- openspec-ff-changeSkill
- openspec-new-changeSkill
- openspec-onboardSkill
- openspec-sync-specsSkill
- openspec-verify-changeSkill
- rhdh-overlay-cve-exportSkill
- rhdh-platform-lifecycleSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Add references/support-intake.md when the work originates from a support case: an RHDHSUPP conversation, a customer escalation, an SLA …
- Very specific: line 56
Never create-then-restrict.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create RHDH Jira work
One skill for "this should be a ticket". It decides the issue type and project, runs the interview, drafts from the RHDH template, and creates the issue.
A caller who says "file this in Jira" almost never knows whether they want a Feature, an Epic, or a Story. Deciding that is this skill's job. Getting it wrong writes the wrong issue type into a public project, so the decision happens up front and out loud, and the user confirms it before anything is created.
Route
Load workflows/create-issue.md. One workflow covers every level of the
hierarchy — the type decision is its first real step, and the steps after it
converge.
Add references/support-intake.md when the work originates from a support case:
an RHDHSUPP conversation, a customer escalation, an SLA question, or a request to
turn a case into a defect or a feature request.
Grilling is a hard gate
Creation runs its interview through /grilling, which the user installs from
mattpocock/skills alongside this pack; do not create anything without it.
/rhdh-jira-authoring carries the RHDH half of the interview — the challenge
matrix, field inference, sizing, and templates. Invoke it by name.
Every create is an external write
Invoke /mutation-gate and follow it before any acli command that
creates, links, comments, or edits. One create is rarely one operation — the
create, the field update create could not carry, the parent link, and the
comment go into the same stated set so a single approval covers them.
Afterwards, read the issue back. A create that succeeded followed by a field update that silently failed is a half-created issue, not a success.
Private issues are not "set after create." On public projects (RHIDP,
RHDHPLAN, RHDHBUGS), put security on the create payload
(/rhdh-jira-api — Private issues). RHDHSUPP is project-private; level optional.
Never create-then-restrict. If security cannot be set when required, stop.
Boundary with the neighbouring skills
- Judging whether an existing issue is ready is
/rhdh-jira-refine. - Changing status, assignee, comments, or links on a known key is
/rhdh-jira-update. aclisyntax, field IDs, the component catalog, and workflow exit criteria are/rhdh-jira-api.- Templates, the challenge matrix, sizing, duplicate detection, and decomposition
rules are
/rhdh-jira-authoring. - Creating a PR and linking it back to an issue is
/rhdh-jira-link.
Completion
Complete when the user confirmed the issue type before creation, the duplicate check ran and its result was reported, the grilling interview happened, and every created key has been read back and reported with its resulting status, parent link, and the fields that were actually set. Report any field the API refused as unset, never as set. A decomposition is complete only when the user approved the batch table before any child was created, and every child in that table has either a key or a stated reason it was skipped.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

