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 that concisely covers CRUD operations on Jira issues with explicit trigger guidance. It uses third person voice, includes natural keywords users would say, and clearly distinguishes itself through Jira-specific terminology. Minor improvement could include mentioning file extensions or API-related terms, but overall it's effective.

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 both 'what' (CRUD operations on Jira issues) 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 working with Jira.	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 is highly actionable with complete, executable code examples and curl commands covering all CRUD operations. However, it is significantly over-verbose — the full TypeScript interface definitions, complete function implementations, curl equivalents, AND ADF format documentation all inline create a monolithic document that wastes token budget. It also lacks validation checkpoints for destructive operations (delete, bulk create).

Suggestions

Drastically reduce inline content: move full TypeScript implementations and curl examples to separate reference files, keeping only a concise quick-start pattern and API endpoint table in SKILL.md

Remove the JiraIssue interface definition entirely — Claude can infer response shapes from the API; only the CreateIssueInput and ADF format (the non-obvious parts) add value

Add validation/confirmation steps for deleteIssue (verify issue exists first, confirm subtask handling) and error handling for bulkCreateIssues (partial failure recovery)

Consolidate the 'Required Fields by Issue Type' section — Story, Task, and Bug all have identical required fields, so listing them separately adds no value

Dimension	Reasoning	Score
Conciseness	The skill is excessively verbose. The full TypeScript interface definitions (JiraIssue with all nested fields), the complete CRUD function implementations, AND the curl examples are redundant — Claude already knows how to write REST API wrappers. The ADF format explanation and the required fields table repeat information already shown in the code examples.	1 / 3
Actionability	The skill provides fully executable TypeScript code and copy-paste ready curl examples for every CRUD operation. The code is complete with proper types, error handling patterns, and real API paths.	3 / 3
Workflow Clarity	Steps are listed 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. Missing feedback loops for batch operations caps this at 2.	2 / 3
Progressive Disclosure	The content is largely monolithic — over 250 lines of inline code that could be split into separate reference files. The references section at the bottom is good, but the ADF format details, curl examples, and full TypeScript implementations should be in separate files with the SKILL.md serving as a concise overview.	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: e437c3c

Reviewed: 6 days 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.