jira
Use this skill for any Jira operation in the DOCSP project — creating, viewing, searching, updating, transitioning, commenting on, or linking tickets. Also handles follow-up ticket creation to manage scope creep. TRIGGER when: user mentions a DOCSP-XXXXX ticket number or any Jira ticket URL; user asks to view, open, check, update, transition, close, comment on, link, or search tickets; user references "the ticket", "the Jira", or "open a ticket". SKIP: GitHub issues; non-Jira platforms; questions unrelated to ticket operations.
89
88%
Does it follow best practices?
Impact
88%
2.25xAverage score across 3 eval scenarios
Passed
No known issues
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 an excellent skill description that covers all key dimensions thoroughly. It lists specific concrete actions, provides rich natural trigger terms, explicitly addresses both what and when, and includes negative triggers (SKIP) to minimize conflict risk. The only minor note is the use of second-person 'Use this skill' at the start, but the rest of the description uses appropriate imperative/third-person framing.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating, viewing, searching, updating, transitioning, commenting on, linking tickets, and follow-up ticket creation for scope creep. These are all concrete, actionable operations. | 3 / 3 |
Completeness | Clearly answers both 'what' (Jira operations in DOCSP project — creating, viewing, searching, updating, etc.) and 'when' (explicit TRIGGER clause with specific patterns like ticket numbers, URLs, and natural phrases). Also includes a SKIP clause for negative triggers, which adds further clarity. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'DOCSP-XXXXX ticket number', 'Jira ticket URL', 'view, open, check, update, transition, close, comment on, link, search tickets', 'the ticket', 'the Jira', 'open a ticket'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped to a specific project (DOCSP) and platform (Jira), with explicit SKIP guidance for GitHub issues and non-Jira platforms. This makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, highly actionable Jira skill with excellent concrete examples for both CLI and MCP tools, strong workflow clarity with validation checkpoints, and useful gotcha documentation. Its main weaknesses are length (could benefit from splitting reference tables into separate files) and minor verbosity in explanatory sections. The dual-tool approach with fallback logic is well-designed.
Suggestions
Extract reference tables (labels, link types, story points, priority values) into a separate REFERENCE.md file and link to it from the main skill to reduce token footprint.
Trim explanatory text that Claude can infer — e.g., the Component Field section's advice about asking users and not guessing could be condensed to a single line rule.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and code examples, but it's quite long (~400 lines) and includes some information Claude already knows (e.g., explaining what link types mean directionally, general advice like 'keep tickets focused'). The Component Field section is somewhat vague and could be tightened. However, most content is project-specific configuration that Claude genuinely needs. | 2 / 3 |
Actionability | Excellent actionability throughout — nearly every operation has both CLI and MCP examples that are copy-paste ready with real flags, field keys, and custom field IDs. The gotchas section provides concrete wrong/correct pairs, and the closing workflow specifies exact custom field names and values needed. | 3 / 3 |
Workflow Clarity | The ticket lifecycle is clearly sequenced with a status progression table. The closing workflow has explicit validation (confirm PR merged, required fields enumerated). The tool selection fallback strategy has clear decision logic with session memory and quick-fail rules. The scope creep workflow has numbered steps with confirmation checkpoints. Error recovery is addressed (read CLI errors for valid transitions, fallback tool strategy). | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and logical grouping, but it's a monolithic ~400-line file with no references to supporting files. The labels table, link types table, story point scale, and common operations could be split into reference files to keep the main skill leaner. For a skill this long, inline everything is suboptimal even without a bundle. | 2 / 3 |
Total | 10 / 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
- mongodb/docs
- Commit
5985af5
- 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.