Agent skill
jira-aipcc-create
Create Jira issues in the AIPCC project. Infers summary, description, type, and component from conversation context, confirms with the user before creating. Use when the user wants to file a new AIPCC Jira issue.
Install this agent skill to your Project
npx add-skill https://github.com/opendatahub-io/ai-helpers/tree/main/helpers/skills/jira-aipcc-create
SKILL.md
Create AIPCC Jira Issue
Create Jira issues in the AIPCC project using the acli CLI.
Prerequisites
aclimust be installed and authenticated (acli jira auth)
Implementation
Step 1: Infer Issue Details from Context
Analyze the conversation to determine:
-
Summary: A concise title (under 100 characters) describing the issue
-
Description: A Markdown description with relevant context, root cause, fix details, or requirements (use Markdown)
-
Type: One of the following based on the nature of work
Bug: problem that impairs or prevents product functions; tracks escaped defectsStory: action-oriented, smallest unit of work that can be completed within one sprintEpic: large user story that needs to be broken down; groups bugs, stories, and tasks to show progress of a larger effort; represents significant deliverable; does not span teamsFeature: use when tracking capability or well-defined set of functionality delivering business value; can include additions/changes to existing functionalitySpike: time-bound unit of work representing research-related task; not easy to sizeInitiative: use when capturing internal improvementsTask: unit of work to be accomplished, not end-user facing
-
Component: One of the valid AIPCC components:
PyTorchAIPCC ProductizationAccelerator EnablementWheel Package IndexAI Testing + Workflow ValidationModel ValidationDevelopment Platform
-
Parent Epic (optional): If the user specifies an epic key (e.g. AIPCC-1234), include it as the parent
If any field cannot be confidently inferred, ask the user.
Step 2: Confirm with the User
Present the proposed issue details to the user in a clear format:
I'll create the following AIPCC JIRA issue:
**Type**: Bug
**Component**: Wheel Package Index
**Parent Epic**: AIPCC-1234 (if specified)
**Summary**: Fix duplicate CI pipeline runs
**Description**:
> [description]
Shall I go ahead and create this?
Wait for user confirmation before proceeding. If the user requests changes, adjust accordingly.
Step 3: Create the Issue
Build a JSON file with the following structure.
Important: The description field MUST be in Atlassian Document Format (ADF), not plain text. acli will reject plain text descriptions with an error.
If the user specifies a parent epic, include the parent field in additionalAttributes. This is the only way to set the epic/parent relationship — acli jira workitem edit does not support additionalAttributes or custom fields, so the parent must be set at creation time.
{
"projectKey": "AIPCC",
"summary": "<summary>",
"type": "<type>",
"description": {
"version": 1,
"type": "doc",
"content": [
{
"type": "paragraph",
"content": [
{
"type": "text",
"text": "<description text>"
}
]
}
]
},
"additionalAttributes": {
"components": [{"name": "<component>"}],
"parent": {"key": "<EPIC-KEY>"}
}
}
Omit the parent field from additionalAttributes if no epic is specified.
Write it to a temporary file:
cat > "$(mktemp /tmp/acli-issue-create-XXXX.json)" << 'EOF'
{ ... }
EOF
Create the issue using:
acli jira workitem create --from-json <JSON-FILE>
Step 4: Report Result
On success, acli prints the new issue key and URL. Report this to the user:
Created AIPCC-12345: https://redhat.atlassian.net/browse/AIPCC-12345
Clean up the temporary JSON file after creation.
Error Handling
- acli not found: Tell the user to install acli and run
acli jira auth - Authentication failure: Tell the user to run
acli jira auth - Creation failure: Display the error from acli and suggest checking permissions
- Invalid component: Show the list of valid components and ask the user to pick one
Examples
Context-Aware Creation
User: [After discussing a bug fix] Create a JIRA for this
Assistant: [Infers details from conversation, presents for confirmation, creates on approval]
Explicit Request
User: /jira.aipcc-create Bug: selfservice build monitoring flakes
Assistant: [Uses provided info, infers description and component, confirms, creates]
Ambiguous Component
User: File a task for updating the CI pipeline docs
Assistant: I'll create an AIPCC task. Which component does this fall under?
1. AIPCC Productization
2. Wheel Package Index
3. Development Platform
...
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
python-packaging-env-finder
Investigate environment variables that can be set when building Python wheels for a given project. Analyzes setup.py, CMake files, and other build configuration files to discover customizable build environment variables.
torchtalk-analyzer
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.
ai-bug-fix-triage
Triage JIRA bugs against repository code to classify AI fixability. Use when reviewing a backlog of bugs to determine which ones an AI agent can fix.
python-packaging-complexity
Analyze Python package build complexity by inspecting PyPI metadata. Evaluates compilation requirements, dependencies, distribution types, and provides recommendations for wheel building strategies.
coderabbit-review
Evaluate CodeRabbit PR comments and fix or reply
git-shallow-clone
Perform a shallow clone of a Git repository to a temporary location.
Didn't find tool you were looking for?