capture-tasks-from-meeting-notes

Analyze meeting notes to find action items and create Jira tasks for assigned work. When an agent needs to: (1) Create Jira tasks or tickets from meeting notes, (2) Extract or find action items from notes or Confluence pages, (3) Parse meeting notes for assigned tasks, or (4) Analyze notes and generate tasks for team members. Identifies assignees, looks up account IDs, and creates tasks with proper context.

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%

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

Highly actionable with a clear, well-validated 7-step workflow, but undermined by verbosity and redundancy: action-item patterns are repeated in three places and the provided reference file is never linked from the body. Tightening the duplicated pattern sections and pointing to references/action-item-patterns.md would raise both conciseness and progressive disclosure.

Suggestions

Remove the standalone "Action Item Pattern Examples" section (and trim the Step 2 pattern list) since the same content lives in references/action-item-patterns.md; link to it once with "See [action-item-patterns.md](references/action-item-patterns.md) for the full pattern catalog" to eliminate triplication.

Condense the "Tips for High-Quality Results", three "Examples", and "Quick Reference" sections — much of their content restates the workflow; keep only non-obvious guidance to recover token budget.

Move the detailed edge-case dialog templates (no-action-items, mixed formats, duplicates, long descriptions) into the reference file, leaving a one-line pointer for each, so SKILL.md stays an overview.

Dimension	Reasoning	Score
Conciseness	The body is largely useful and avoids explaining concepts Claude already knows, but it is verbose through redundancy — action-item patterns appear in Step 2, again in the standalone "Action Item Pattern Examples" section, and yet again in references/action-item-patterns.md; the Tips/Examples/Quick-Reference sections further pad the token budget. It is not a level-1 wall of background explanation, but it could be tightened considerably.	2 / 3
Actionability	Provides concrete, copy-paste-ready tool calls with parameters (getConfluencePage, getVisibleJiraProjects, lookupJiraAccountId, getJiraProjectIssueTypesMetadata, createJiraIssue) plus exact presentation and task-description formats — fully executable guidance rather than abstract direction.	3 / 3
Workflow Clarity	A clearly sequenced 7-step process with an explicit human-in-the-loop validation checkpoint (Step 5: "CRITICAL: Always show the parsed action items... BEFORE creating any tasks", "Do NOT create tasks until user confirms") and an issue-type metadata check before batch creation — appropriate feedback loops for a batch/outward-facing operation.	3 / 3
Progressive Disclosure	A references/ bundle file exists (action-item-patterns.md) but is never linked or signaled from the body, while the same pattern content is duplicated inline in two places — content that should live in the separate reference is inline and the reference is poorly signaled. Not a monolithic level-1 document (sections are organized), but structure and signaling fall short of level 3.	2 / 3
	Total	10 / 12 Passed

Description

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.

A strong, specific description that states concrete capabilities, provides explicit "when to use" triggers, and stays in third-person voice. Trigger terms are natural and well-covered with little conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "find action items", "create Jira tasks", "looks up account IDs", and "creates tasks with proper context" — rather than vague language; voice is third person ("Identifies", "looks up", "creates"), so no person-voice penalty applies.	3 / 3
Completeness	Clearly answers both what ("Analyze meeting notes... create Jira tasks... Identifies assignees, looks up account IDs") and when via the explicit "When an agent needs to: (1)...(4)..." trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "meeting notes", "action items", "create tasks", "create tickets", "Jira tasks", and "Confluence pages" — with good variation across the four numbered triggers.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (meeting notes → Jira tasks with assignee lookup) with distinct triggers unlikely to fire for adjacent skills like general note-taking or meeting summarization.	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 (680 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/atlassian-rovo/skills/capture-tasks-from-meeting-notes/SKILL.md
Commit: 11c74d6

Reviewed: about 9 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.