oimiragieo
oimiragieo/agent-studio
相关职业SOC
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/oimiragieo/agent-studio --skill jira-pm命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Agent frontmatter enhancements — disallowedTools, mcpServers scoping, fork_eligible field
Context management — pre-compact persistence, threshold alignment, microcompact/circuit breaker detection
Hook enhancements — updatedInput for bash safety prefixes, suppressOutput for verbose blocks, denial-based routing feedback
基于 SOC 职业分类
正在显示 SKILL.md
| name | jira-pm |
| description | Jira project management and issue tracking integration |
| version | 1.1.0 |
| category | Other |
| agents | ["planner","developer"] |
| tags | ["jira","project-management","tickets","agile","sprint"] |
| model | sonnet |
| invoked_by | both |
| user_invocable | true |
| tools | ["Bash","Read","WebFetch"] |
| best_practices | ["Use JQL (Jira Query Language) for precise issue searches","Verify project keys before creating issues","Use transitions to change issue status through valid workflows","Cache project metadata to reduce API calls"] |
| error_handling | graceful |
| streaming | not_supported |
| verified | true |
| lastVerifiedAt | "2026-02-22T00:00:00.000Z" |
| source | builtin |
| trust_score | 100 |
| provenance_sha | a029de1d8ebed1f1 |
Mode: Cognitive/Prompt-Driven - No standalone utility script; use via agent context.
Jira PM (Project Management) - Provides integration with Atlassian Jira for issue tracking, project management, and workflow automation. Enables 90%+ context savings over direct MCP integration. - Issue management: search, create, update, transition - Project discovery and metadata retrieval - Sprint management and issue tracking - Comment management on issues - JQL-based advanced queries ## Environment VariablesRequired:
Optional:
<tool_categories>
| Tool | Description | Confirmation Required |
|---|---|---|
| search | Search issues using JQL | No |
| get-issue | Get detailed issue information | No |
| create-issue | Create a new issue | Yes |
| update-issue | Update existing issue fields | Yes |
| transition | Change issue status/workflow state | Yes |
| Tool | Description |
|---|---|
| list-projects | List all accessible projects |
| project-info | Get detailed project information |
| Tool | Description |
|---|---|
| active-sprint | Get currently active sprint for a board |
| sprint-issues | List all issues in a specific sprint |
| Tool | Description |
|---|---|
| get-comments | Retrieve all comments on an issue |
| add-comment | Add a comment to an issue |
</tool_categories>
<usage_patterns>
Issue Creation: List projects -> Get project info -> Create issue -> Add comment
Sprint Management: Get active sprint -> List sprint issues -> Update issue status -> Add comments
Issue Search: Use JQL for targeted searches -> Retrieve issue details -> Update issues
</usage_patterns>
<agent_integration>
</agent_integration>
<error_handling>
</error_handling>
<best_practices>
</best_practices>
<progressive_disclosure>
Context Savings: 90%+ compared to loading full Jira MCP server </progressive_disclosure>
<api_reference>
See https://developer.atlassian.com/cloud/jira/platform/rest/v3/ for full reference. </api_reference>
PUT /issue to change status — Jira status changes must go through valid workflow transitions via POST /issue/{key}/transitions; direct field updates bypass workflow validators and automation rules.summary, issuetype, and project fields when creating an issue — these three fields are the minimum required by Jira Cloud REST API v3; missing any produces a 400 error.| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Updating status via field PUT | Bypasses workflow guards; invalid state transitions succeed silently; automation rules don't fire | Use POST /issue/{key}/transitions with the correct transition ID |
| Fetching all issues and filtering locally | Times out on large projects; wastes API quota; slow for paginated results | Always use JQL with specific project/sprint/status filters |
| Creating issues without duplication check | Splits work tracking; team sees multiple tickets for same task | Search with JQL (project = X AND summary ~ "keyword") before creating |
Hardcoding field IDs (e.g., customfield_10016) | Field IDs differ between Jira instances and cloud/server; breaks across projects | Discover field IDs dynamically via /rest/api/3/field endpoint |
| No error handling for rate limits (429) | Jira Cloud rate limits at ~300 requests/minute; unhandled 429 crashes automation | Implement exponential backoff; check Retry-After header on 429 responses |
Before starting: Read .claude/context/memory/learnings.md
After completing:
ASSUME INTERRUPTION: If it is not in memory, it did not happen.