agent-issue-tracker

Agent skill for issue-tracker - invoke with $agent-issue-tracker

2.61x

Quality

13%

Does it follow best practices?

Impact

81%

2.61x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-issue-tracker/SKILL.md

Quality

Discovery

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 description is critically deficient across all dimensions. It functions more as an invocation instruction ('invoke with $agent-issue-tracker') than a skill description, providing no information about what the skill does, what actions it performs, or when Claude should select it. It would be nearly impossible for Claude to correctly choose this skill from a pool of available skills.

Suggestions

Add concrete actions the skill performs, e.g., 'Creates, updates, searches, and closes issues in the project issue tracker. Assigns issues to team members, adds labels, and manages priorities.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user mentions bugs, tickets, issues, tasks, tracking work items, or managing project issues.'

Remove the invocation instruction ('invoke with $agent-issue-tracker') from the description field, as it is operational metadata rather than a capability description useful for skill selection.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for issue-tracker' is extremely vague and does not describe what the skill actually does (e.g., create issues, assign tickets, search bugs).	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of capabilities. The description only states how to invoke it.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'issue-tracker', but it reads more like an internal label than a natural user keyword. Missing terms users would say like 'bug', 'ticket', 'issue', 'task', 'Jira', 'track', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so generic that it could overlap with any project management, bug tracking, or task management skill. There are no distinct triggers or specific domain markers to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

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

This skill is excessively verbose, mixing aspirational feature descriptions with actual instructions. While it provides some concrete code examples for issue management workflows, the examples use inconsistent pseudo-syntax and are hardcoded to specific repositories. The content would benefit enormously from being trimmed to essential patterns, moving templates to separate files, and adding validation steps for batch operations.

Suggestions

Cut the content by at least 60%: remove the Purpose/Capabilities sections (redundant with frontmatter), the Metrics/Analytics section (aspirational, not actionable), and the Best Practices section (generic advice Claude already knows).

Move the two issue templates (Integration and Bug Report) to separate referenced files (e.g., TEMPLATES.md) and link to them from a concise overview section.

Add explicit validation steps after batch issue creation (e.g., verify each `gh issue create` succeeded with exit code checks before proceeding to tracking setup).

Ensure tool names referenced in the body match those declared in the frontmatter tools list, and use consistent, valid syntax for tool invocations rather than pseudo-JavaScript.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~200+ lines. Repeats capabilities in multiple sections (frontmatter, Purpose, Capabilities). Includes extensive template boilerplate, marketing-style descriptions ('Intelligent issue management'), emoji decoration, and sections like 'Metrics and Analytics' that describe aspirational features rather than actionable instructions. Much of this content (what issues are, how labeling works) is knowledge Claude already has.	1 / 3
Actionability	Provides concrete code examples with specific tool calls and gh CLI commands, which is good. However, the JavaScript-like syntax for MCP tool calls is pseudocode (not valid JS), tool names in the body (mcp__github__*) don't match the tools declared in frontmatter, and many examples are hardcoded to specific repos/issues (ruvnet/ruv-FANN, issue #54) making them non-generalizable templates rather than truly executable guidance.	2 / 3
Workflow Clarity	The 'Complete Issue Management Workflow' section shows a sequence of steps, and the progress update pattern shows a retrieve-update-store flow. However, there are no validation checkpoints or error handling for the batch operations (creating multiple issues via gh CLI). No feedback loops for verifying issue creation succeeded before proceeding to tracking setup. Batch/destructive operations without validation caps this at 2.	2 / 3
Progressive Disclosure	Monolithic wall of text with everything inline. The two full issue templates (Integration and Bug Report) should be in separate referenced files. No content is split into external references despite the skill being well over 200 lines. The 'Integration with Other Modes' and 'Metrics and Analytics' sections add bulk without actionable content. No navigation structure or cross-references to separate files.	1 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Commit: ccb062f

Reviewed: 3 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.