jira-assistant
Manage Jira issues via Atlassian MCP — search, create, update, transition status, and handle sprint tasks. Auto-detects workspace configuration. Use when user says "create a Jira ticket", "update my sprint", "check Jira status", "transition this issue", "search Jira", or "move ticket to done". Do NOT use for Confluence pages (use confluence-assistant).
71
63%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(development)/jira-assistant/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 an excellent skill description that covers all key dimensions well. It lists specific capabilities, provides natural trigger phrases users would actually say, explicitly defines both 'what' and 'when', and even includes a negative boundary (Do NOT use for Confluence) to reduce conflict risk. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: search, create, update, transition status, handle sprint tasks, and auto-detect workspace configuration. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage Jira issues — search, create, update, transition, sprint tasks) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also includes a 'Do NOT use' boundary condition for Confluence, which adds clarity. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user phrases: 'create a Jira ticket', 'update my sprint', 'check Jira status', 'transition this issue', 'search Jira', 'move ticket to done'. These are highly natural phrases users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Jira issues via Atlassian MCP) and explicit boundary against Confluence. The specific trigger terms like 'Jira ticket', 'sprint', and 'transition this issue' are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill covers Jira operations comprehensively but is severely bloated with repetitive notes, redundant sections (Best Practices, Important Notes, and inline reminders all say the same things), and content that should be split into reference files. Actionability is moderate — tool calls are shown but in pseudocode with placeholders. The lack of validation/error handling in workflows and the monolithic structure are significant weaknesses.
Suggestions
Eliminate repetitive 'Note: Replace placeholders with detected configuration values' after every example — state this once at the top and trust Claude to apply it.
Consolidate 'Best Practices', 'Important Notes', and inline warnings into a single concise section, removing all duplicated guidance.
Move the task description template, JQL patterns reference, and detailed examples into separate referenced files (e.g., TEMPLATE.md, JQL_PATTERNS.md, EXAMPLES.md) to reduce the main skill's token footprint.
Add error handling/validation steps to workflows — e.g., 'If createJiraIssue fails with field errors, call getJiraIssueTypeMetaWithFields to verify required fields and retry.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The phrase 'Replace placeholders with detected configuration values' appears after nearly every example. The 'Important Notes' section at the end repeats points already made in 'Best Practices' and throughout the document. The 'Note for skill users' and repeated configuration instructions add significant bloat. Claude already knows how to use MCP tools and doesn't need concepts like issue keys vs IDs explained. | 1 / 3 |
Actionability | Provides concrete MCP tool calls with parameter names and JQL examples, which is useful. However, all code uses placeholders like {CLOUD_ID} and {PROJECT_KEY} rather than being truly executable, and the tool calls are presented in pseudocode-like format rather than actual executable syntax. The configuration detection workflow is somewhat vague ('Use MCP search tools to discover'). | 2 / 3 |
Workflow Clarity | Multi-step processes like creating issues (steps a, b, c) and transitioning issues (steps 1, 2) are clearly sequenced. However, there are no validation checkpoints or error recovery steps — e.g., what happens if issue creation fails, if a transition is not available, or if JQL returns no results. The configuration detection workflow has a reasonable fallback chain but lacks explicit validation. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text at ~250 lines with no references to external files for detailed content. The task template, JQL patterns, and four full examples could easily be split into separate reference files. Everything is inline, making the skill heavy to load into context. The only external reference is to a config file, not to supplementary skill documentation. | 1 / 3 |
Total | 6 / 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
- tech-leads-club/agent-skills
- Commit
81e7e0d
- 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.