jira
Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.
89
87%
Does it follow best practices?
Impact
95%
1.48xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent trigger terms and completeness. Its main weakness is that the 'what' portion could be more specific about concrete capabilities (e.g., adding comments, transitioning statuses, assigning issues, querying with JQL). The trigger guidance and distinctiveness are both excellent.
Suggestions
Expand the capability list with more specific concrete actions, e.g., 'add comments, transition issue statuses, assign issues, query with JQL, link issues' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions some actions like 'create/view/update issues, check sprint status, manage Jira workflow' but these are somewhat generic and bundled together rather than listing multiple distinct concrete capabilities. It leans more toward naming the domain with some actions rather than comprehensively listing specific operations. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (create/view/update issues, check sprint status, manage Jira workflow) and 'when' (with a clear 'Use when...' clause and explicit trigger keywords). Both dimensions are well-covered. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'jira', 'issue', 'ticket', 'sprint', 'backlog', issue key patterns like 'PROJ-123'. These are terms users would naturally use when requesting Jira-related help. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with Jira-specific terminology, issue key patterns (e.g., 'PROJ-123'), and domain-specific keywords like 'sprint', 'backlog'. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that effectively handles a complex scenario (dual backends) with clear decision logic, actionable command references, and strong safety guardrails. The progressive disclosure is particularly well done with the 'Deep Dive' load-reference decision table. Minor verbosity in sections like Triggers and Issue Key Detection slightly reduces token efficiency, but overall the content is high quality.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables, but includes some unnecessary sections like 'Triggers' (which just lists example phrases Claude doesn't need) and the 'Before Any Operation' self-reflection prompts are somewhat verbose. The 'Issue Key Detection' section explains a regex pattern Claude already knows. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready commands for both CLI and MCP backends. The quick reference tables map intents directly to specific commands/tool calls, and the NEVER section gives precise, actionable constraints with clear rationale. | 3 / 3 |
Workflow Clarity | Multi-step workflows for creating and updating tickets include explicit validation checkpoints (fetch first, show changes, get approval, verify after). The NEVER section serves as strong guardrails with clear error-prevention steps. The backend detection flow is clearly sequenced with explicit decision points. | 3 / 3 |
Progressive Disclosure | Excellent structure with quick reference tables for common operations inline and clear pointers to `references/commands.md` and `references/mcp.md` for complex tasks. The 'Deep Dive' section explicitly defines when to load references vs when the inline content suffices, which is a strong progressive disclosure pattern. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- jdrhyne/agent-skills
- Commit
6768672
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.