auto-jira

Autonomously work on Jira backlog tickets, creating PRs and shepherding them to merge

Quality

58%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/auto-jira/SKILL.md

Quality

Discovery

32%

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 conveys a clear high-level workflow (Jira tickets → PRs → merge) but lacks the specificity and explicit trigger guidance needed for reliable skill selection. It would benefit from listing concrete sub-actions and adding a 'Use when...' clause with natural trigger terms users would employ.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to work on Jira tickets, process backlog items, create pull requests from Jira issues, or automate ticket-to-PR workflows.'

Include common trigger term variations such as 'pull request', 'Jira issues', 'sprint backlog', 'code review', and 'merge PR'.

List more specific concrete actions such as 'picks up Jira tickets, creates feature branches, implements changes, opens pull requests, addresses review feedback, and updates ticket status upon merge'.

Dimension	Reasoning	Score
Specificity	Names the domain (Jira backlog tickets) and some actions (creating PRs, shepherding to merge), but lacks detail on specific sub-actions like branch creation, code changes, review handling, or ticket status updates.	2 / 3
Completeness	Describes what the skill does but has no explicit 'Use when...' clause or equivalent trigger guidance, and per the rubric guidelines, a missing 'Use when' clause caps completeness at 2. However, the 'when' is so absent that it scores a 1 — there's no indication of when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'Jira', 'backlog tickets', and 'PRs', but misses common variations users might say such as 'pull request', 'issues', 'sprint', 'merge request', or 'code review'.	2 / 3
Distinctiveness Conflict Risk	The combination of Jira + PR creation + merge shepherding is fairly specific, but could overlap with general Git/GitHub workflow skills or generic Jira integration skills without clearer scoping.	2 / 3
	Total	7 / 12 Passed

Implementation

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, well-architected skill that provides clear autonomous workflow guidance with robust safety mechanisms including critic agent validation, explicit constraints, and human intervention protocols. The progressive disclosure is excellent with well-signaled supporting documents. Minor verbosity in the Critic Agent prompt templates and attribution section prevents a perfect conciseness score, but overall the content is highly actionable and well-organized.

Dimension	Reasoning	Score
Conciseness	The skill is generally well-structured and avoids explaining basic concepts, but includes some redundancy (e.g., the Critic Agent section with full prompt templates is verbose, and the attribution table could be more compact). The ticket selection criteria section is thorough but lengthy.	2 / 3
Actionability	Provides specific MCP tool names, exact CLI commands, concrete branch naming conventions, precise PR title formats, and detailed argument parsing. The workflow steps are copy-paste actionable with specific tool invocations and exact formats for attribution, comments, and commit messages.	3 / 3
Workflow Clarity	The workflow is clearly sequenced with an explicit 8-step per-ticket loop, mandatory PRE-CHECK and POST-CHECK validation via Critic agent for every write action, error recovery paths (fix and retry on rejection), and clear human intervention triggers with specific escalation steps (transition to HOLD, comment, move on).	3 / 3
Progressive Disclosure	Excellent use of a supporting documents table with clear 'When you need to...' / 'Read this' mapping to four separate files (ticket-workflow.md, pr-workflow.md, ci-validation.md, troubleshooting.md), with an explicit instruction to not load all docs at once. The main SKILL.md serves as a clear overview with one-level-deep references.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 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: 0f36ad4

Reviewed: about 16 hours 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.