run-jira
Fetch a Jira issue and propose an implementation plan based on codebase analysis
51
56%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/run-jira/SKILL.mdQuality
Discovery
40%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 identifies a clear and distinct capability—fetching Jira issues and proposing implementation plans—but lacks explicit trigger guidance ('Use when...') and misses common user-facing keywords like 'ticket', 'story', or 'task'. It would benefit from more specific action details and an explicit 'when to use' clause.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to implement a Jira ticket, plan work for a Jira issue, or analyze the codebase for a specific ticket.'
Include common trigger term variations such as 'ticket', 'story', 'task', 'JIRA', 'bug', and 'sprint item' to improve matching.
Expand the specificity of actions, e.g., 'Fetches Jira issue details (summary, description, acceptance criteria), analyzes the relevant codebase, and proposes a step-by-step implementation plan with affected files and code changes.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Jira) and two actions (fetch a Jira issue, propose an implementation plan based on codebase analysis), but doesn't elaborate on what the implementation plan includes or what kind of codebase analysis is performed. | 2 / 3 |
Completeness | Describes what the skill does but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent (not even implied beyond the what), this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'Jira issue' and 'implementation plan' which are relevant keywords, but misses common variations like 'ticket', 'JIRA', 'story', 'task', 'bug', 'sprint', or 'plan implementation'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Jira issue fetching and codebase-based implementation planning is a fairly distinct niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-structured skill that provides actionable guidance with specific tool names, parameters, and a clear multi-step workflow. Its main weaknesses are minor verbosity (explaining why steps matter rather than just stating them) and missing validation checkpoints between the analysis and proposal steps. The hardcoded Datadog-specific cloudId and URL patterns appropriately encode organization-specific knowledge.
Suggestions
Remove explanatory rationale like 'This step is critical — linked resources often contain...' to improve conciseness; Claude doesn't need motivation, just instructions.
Add a brief validation checkpoint after Step 3 (e.g., 'If no linked resources could be fetched, note this limitation in the summary and proceed with available context') and after Step 4 (e.g., 'If no relevant code is found, ask the user for guidance before proposing').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary explanation. Phrases like 'This step is critical — linked resources often contain the root cause analysis...' explain rationale Claude doesn't need. The step-by-step structure is clear but could be tighter. | 2 / 3 |
Actionability | Provides specific MCP tool names, exact parameter names and values (cloudId, fields array), concrete tool references (Glob, Grep, Read, Task with subagent_type=Explore), and specific URL patterns for resource detection. The guidance is directly executable. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced and logically ordered, with a good error handling note in Step 1 ('If the issue cannot be found, stop'). However, there are no validation checkpoints between steps 3-5 — no verification that linked resources were successfully fetched, no check that codebase analysis found relevant files before proposing implementation. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~50 lines) with no need for external references, the content is well-organized into clear sequential sections. No bundle files are needed, and the structure is easy to navigate with well-labeled steps. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- DataDog/datadog-agent
- Commit
a41685a
- 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.