jira-search
Search Jira issues using JQL queries. Use when filtering issues by project, status, assignee, date, or building reports.
73
66%
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-search/SKILL.mdQuality
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 solid skill description that clearly communicates its purpose and when to use it. It excels at trigger term coverage and completeness with an explicit 'Use when' clause. The main weakness is that it only describes one action (search) rather than listing multiple concrete capabilities, which limits its specificity score.
Suggestions
Consider listing additional concrete actions if the skill supports them, e.g., 'Search Jira issues using JQL queries, filter by custom fields, export results' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Jira issues) and one specific action (search using JQL queries), but doesn't list multiple concrete actions like creating issues, updating fields, or managing workflows. | 2 / 3 |
Completeness | Clearly answers both 'what' (search Jira issues using JQL queries) and 'when' (Use when filtering issues by project, status, assignee, date, or building reports) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Jira', 'issues', 'JQL', 'project', 'status', 'assignee', 'date', 'reports' — these cover common variations of how users would phrase Jira search requests. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'Jira', 'JQL queries', and specific filter dimensions (project, status, assignee) creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable code and comprehensive JQL coverage, but is far too verbose for a skill file. It explains things Claude already knows (JQL operators, date formats), duplicates guidance across TypeScript and curl sections, and dumps everything into one monolithic file. Cutting this to a lean overview with references to detailed files would dramatically improve it.
Suggestions
Extract the JQL Quick Reference tables, curl examples, and response structure into separate reference files (e.g., JQL_REFERENCE.md, CURL_EXAMPLES.md) and link to them from a concise overview.
Remove the TypeScript interface definitions and helper function wrappers (searchByProject, searchByStatus, etc.) — Claude can trivially generate these. Keep only the core searchIssues and searchAllIssues functions.
Add error handling and validation to the pagination loop (rate limiting, HTTP error responses, empty result handling) to improve workflow robustness.
Remove the JQL operators table and date formats table — Claude already knows JQL syntax. Keep only the 'Common JQL Patterns' section as a quick reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250 lines. It includes full TypeScript interface definitions, multiple wrapper functions Claude could trivially write, a JQL reference table Claude already knows, and extensive curl examples that are largely redundant with the TypeScript code. The pagination formula section and common mistakes are useful but the overall content could be cut by 60%+. | 1 / 3 |
Actionability | The code is fully executable with concrete TypeScript functions, curl commands with real endpoints, specific JQL examples, and a clear JSON response structure. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The steps are numbered and sequenced (define types → basic search → paginated search → builders → advanced examples), but there are no validation checkpoints. For bulk search operations, there's no error handling, no rate limit guidance, and no verification that results are correct. The pagination loop lacks error recovery. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content. The JQL reference tables, curl examples, TypeScript implementations, and response structures are all inline when they could easily be split into separate reference files. The skill would benefit enormously from a concise overview pointing to JQL_REFERENCE.md, EXAMPLES.md, etc. | 1 / 3 |
Total | 7 / 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
e437c3c
- 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.