atlassian-mcp
Use when querying Jira issues, searching Confluence pages, creating tickets, updating documentation, or integrating Atlassian tools via MCP protocol.
Install with Tessl CLI
npx tessl i github:jeffallan/claude-skills --skill atlassian-mcp65
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has strong trigger terms and distinctiveness due to specific product names (Jira, Confluence, Atlassian), but it's structured backwards - it only describes when to use the skill without first explaining what the skill actually does. The capabilities are implied through the trigger conditions rather than explicitly stated.
Suggestions
Add an explicit 'what' statement before the 'Use when' clause, e.g., 'Integrates with Atlassian products to manage project tracking and documentation.'
Expand the specific actions to be more concrete, e.g., 'create and update Jira tickets with custom fields, search and edit Confluence pages, manage sprints and backlogs'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Jira, Confluence, Atlassian) and lists some actions (querying, searching, creating tickets, updating documentation), but the actions are somewhat generic and not comprehensive - doesn't specify what kinds of queries, what ticket fields, or what documentation operations. | 2 / 3 |
Completeness | Has a 'Use when' clause which addresses the 'when' question well, but the 'what does this do' is only implied through the trigger conditions rather than explicitly stated. The description leads with when to use it but doesn't clearly state what the skill actually does. | 2 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'Jira issues', 'Confluence pages', 'creating tickets', 'updating documentation', 'Atlassian tools', 'MCP protocol'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche with distinct triggers - Jira, Confluence, and Atlassian are specific product names that are unlikely to conflict with other skills. The MCP protocol mention further narrows the scope. | 3 / 3 |
Total | 10 / 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.
This skill has strong organizational structure and progressive disclosure but critically lacks actionable content. The MUST DO/MUST NOT DO constraints are valuable, but without concrete code examples, JQL/CQL query samples, or actual MCP configuration snippets, Claude cannot execute the guidance effectively. The role definition section adds unnecessary tokens without adding value.
Suggestions
Add concrete JQL/CQL query examples (e.g., 'project = PROJ AND status = Open ORDER BY created DESC') directly in the skill or ensure reference files contain them
Include a minimal executable MCP server configuration JSON snippet showing authentication setup
Add validation checkpoints to the workflow (e.g., 'Test query with maxResults=1 before full execution')
Remove the 'Role Definition' section - Claude doesn't need persona framing to execute the skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary role definition and persona framing ('Senior integration specialist with deep expertise...') that Claude doesn't need. The core content is reasonably efficient but could be tighter by removing the 'Role Definition' section entirely. | 2 / 3 |
Actionability | The skill lacks any concrete, executable code examples. No actual JQL/CQL queries shown, no MCP configuration JSON, no authentication setup code. Everything is described abstractly ('Configure OAuth 2.1', 'Write JQL for Jira') rather than demonstrated with copy-paste ready examples. | 1 / 3 |
Workflow Clarity | The 5-step core workflow provides a clear sequence, but lacks validation checkpoints. For operations involving production data updates and authentication, there should be explicit validation steps (e.g., 'test query with LIMIT 1 first', 'verify permissions before bulk operations'). | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear reference table pointing to specific topic files with 'Load When' guidance. The main skill serves as a concise overview with well-signaled one-level-deep references to detailed documentation. | 3 / 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.
- 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.