jira-issues

Create, read, update, and delete Jira issues. Use when managing Stories, Tasks, Bugs, or Epics - includes field updates and metadata.

Quality

75%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

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.md

Quality

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. It concisely covers CRUD operations on Jira issues, names specific issue types as trigger terms, and includes an explicit 'Use when...' clause. The description is distinctive, uses third-person voice, and provides enough detail for accurate skill selection.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Create, read, update, and delete Jira issues' plus 'field updates and metadata.' Also specifies issue types: Stories, Tasks, Bugs, Epics.	3 / 3
Completeness	Clearly answers both 'what' (CRUD operations on Jira issues, field updates, metadata) and 'when' ('Use when managing Stories, Tasks, Bugs, or Epics'). The explicit 'Use when...' clause is present.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms users would say: 'Jira', 'issues', 'Stories', 'Tasks', 'Bugs', 'Epics', 'field updates', and 'metadata'. These cover the common vocabulary a user would use when requesting Jira-related work.	3 / 3
Distinctiveness Conflict Risk	Clearly scoped to Jira issue management with specific issue types and operations. The mention of 'Jira' and specific issue types like Stories, Tasks, Bugs, Epics creates a distinct niche unlikely to conflict with other skills.	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 provides highly actionable, executable code for Jira CRUD operations with both TypeScript and curl examples, which is its main strength. However, it is significantly over-verbose—full interface definitions, duplicate examples in two formats, and boilerplate implementations inflate the token cost without adding proportional value. It also lacks validation checkpoints for destructive operations (delete, bulk create) and could benefit from better content splitting.

Suggestions

Reduce the TypeScript interface definitions to just CreateIssueInput and a brief note about ADF format—Claude doesn't need the full JiraIssue response type spelled out.

Choose either TypeScript OR curl examples as the primary format and move the other to a referenced file (e.g., CURL_EXAMPLES.md).

Add validation/confirmation steps for delete operations (e.g., 'verify issue exists before deleting, confirm subtask count') and error handling for bulk create (e.g., 'check results for failures, retry failed items').

Move the full function implementations to a separate REFERENCE.md and keep only a concise quick-start example (one create + one get) in the main skill.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose with full TypeScript interface definitions and 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. Both TypeScript and curl examples are provided for the same operations, nearly doubling the content. The bulk create implementation and batching logic is standard boilerplate.	1 / 3
Actionability	The code is fully executable with complete TypeScript functions and copy-paste ready curl examples. Every CRUD operation has concrete, working code with proper ADF format, query parameters, and error-prone details like assignee account IDs clearly shown.	3 / 3
Workflow Clarity	Steps are labeled sequentially but there are no validation checkpoints. The bulk create operation lacks error handling or verification steps. The delete operation (destructive) has no confirmation or validation guidance. Missing feedback loops for batch operations should cap this at 2.	2 / 3
Progressive Disclosure	The content is largely monolithic with ~300 lines of inline code that could be split into separate reference files. The API summary table and common mistakes are well-structured, but the full TypeScript implementations and curl examples should be in referenced files, with only a quick-start example inline.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

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: caee3d2

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

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.