jira-issues
Create, read, update, and delete Jira issues. Use when managing Stories, Tasks, Bugs, or Epics - includes field updates and metadata.
80
75%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/01000001-01001110/agent-jira-skills/jira-issues/SKILL.mdQuality
Discovery
100%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, well-crafted skill description that concisely covers CRUD operations on Jira issues with explicit trigger guidance. It uses third person voice, names specific issue types as natural trigger terms, and clearly delineates its niche. The only minor improvement could be mentioning additional trigger terms like 'ticket', 'backlog', or 'sprint' that users commonly associate with Jira.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions (create, read, update, delete) and specifies the domain (Jira issues) along with specific issue types (Stories, Tasks, Bugs, Epics) and mentions field updates and metadata. | 3 / 3 |
Completeness | Clearly answers 'what' (CRUD operations on Jira issues including field updates and metadata) and 'when' ('Use when managing Stories, Tasks, Bugs, or Epics') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Jira', 'issues', 'Stories', 'Tasks', 'Bugs', 'Epics', and CRUD-related terms. These are terms users naturally use when requesting Jira work. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Jira issue management with specific issue types named, making it highly distinct and unlikely to conflict with other skills like general project management or other tool integrations. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with complete, executable code examples covering all CRUD operations for Jira issues. However, it is significantly over-verbose, including extensive type definitions, redundant curl examples that mirror the TypeScript code, and repetitive required-fields sections. It lacks validation checkpoints for destructive operations (delete, bulk create) and could benefit from splitting detailed reference material into separate files.
Suggestions
Reduce verbosity by trimming the JiraIssue interface to only non-obvious fields, removing the repetitive 'Required Fields by Issue Type' section (the create function already documents this), and consolidating either curl or TypeScript examples rather than both.
Add validation/confirmation steps for the delete operation and error handling with retry logic for the bulk create operation.
Move the ADF format reference and curl examples into separate bundle files (e.g., ADF_FORMAT.md, CURL_EXAMPLES.md) and reference them from the main skill.
Remove the 'Common Mistakes' items that are already implicit in the code examples (e.g., ADF format is already shown in every description field).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose with extensive TypeScript interface definitions and full function implementations that Claude doesn't need spelled out in this detail. The JiraIssue interface alone is ~30 lines of type definitions Claude already understands. The curl examples largely duplicate the TypeScript code. The 'Required Fields by Issue Type' section repeats the same three fields for Story, Task, and Bug with minimal variation. | 1 / 3 |
Actionability | The skill provides fully executable TypeScript functions and curl commands that are copy-paste ready. Code examples are complete with proper types, error handling patterns, and real API paths. Both programmatic (TypeScript) and direct (curl) approaches are covered. | 3 / 3 |
Workflow Clarity | Steps are labeled sequentially but there are no validation checkpoints. The bulk create operation lacks error handling/verification, and the delete operation (destructive) has no confirmation or validation step. The 'steps' are really just individual CRUD operations rather than a coherent workflow with feedback loops. | 2 / 3 |
Progressive Disclosure | The content is a monolithic document with everything inline. The ADF format details, full interface definitions, and curl examples could be split into separate reference files. References to external docs exist at the bottom, but the skill itself doesn't leverage any bundle files for progressive disclosure of detailed content. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
aa009ea
- 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.