spec-to-backlog

Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When an agent needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

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

The body is highly actionable with a clear, validated workflow, but it is verbose and fails to use its reference files, inlining templates and examples that should live one level deep. Tightening generic advice and routing examples to the references would lift both conciseness and progressive disclosure.

Suggestions

Move the Epic/Task description templates and the 'Examples of Good Breakdowns' section into references (e.g. epic-templates.md, breakdown-examples.md) and link to them from the body to reduce inline bulk and exercise progressive disclosure.

Remove generic decomposition coaching Claude already knows ('Use action verbs', 'Be Specific', 'Logical Grouping', 'Avoid Duplication') or condense it to a one-line pointer.

Eliminate the duplicated issue-type selection logic: define it once (Step 2) and reference it from Step 6 instead of restating the Bug/Story/Task rules.

Dimension	Reasoning	Score
Conciseness	The ~540-line body includes generic decomposition advice Claude already knows ('Use action verbs', 'Be Specific' with check/cross examples, 'Logical Grouping', 'Avoid Duplication') and repeats the issue-type selection logic in both Step 2 and Step 6.	2 / 3
Actionability	Provides copy-paste-ready tool calls with real parameter names, complete Epic/Task description templates, JSON response examples, and concrete error-recovery steps.	3 / 3
Workflow Clarity	A clear 7-step sequence with CRITICAL flags, a user-confirmation checkpoint before batch ticket creation (Step 4), Epic-key capture, and a failed-creation feedback loop via getJiraIssueTypeMetaWithFields.	3 / 3
Progressive Disclosure	Sections are well-organized, but the bundle files (breakdown-examples.md, epic-templates.md, ticket-writing-guide.md) are never referenced or linked while equivalent template/example content is inlined in the body.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 is specific, complete, and distinct: it names concrete actions, provides explicit natural-language triggers, and clearly defines when the skill applies. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.'	3 / 3
Completeness	Clearly states what it does (convert Confluence specs into structured Jira backlogs with Epics and tickets) and explicit 'when' triggers via the numbered 'When an agent needs to: (1)...(4)' clause.	3 / 3
Trigger Term Quality	Natural terms a user would say are covered: 'Create Jira tickets from a Confluence page', 'Generate a backlog from a specification', 'Break down a spec into implementation tasks'.	3 / 3
Distinctiveness Conflict Risk	The Confluence-to-Jira backlog niche with distinct, product-specific triggers and third-person voice makes it unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (544 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/atlassian-rovo/skills/spec-to-backlog/SKILL.md
Commit: 11c74d6

Reviewed: 17 days 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.