agent-issue-tracker

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

2.61x

Quality

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 it should be selected. 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 issue tracker. Assigns tickets, adds comments, and manages labels.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about bugs, tickets, issues, task tracking, or wants to create/update/search issues.'

Remove the invocation instruction ('invoke with $agent-issue-tracker') from the description field, as it does not help Claude decide when to select the skill and wastes space that should describe capabilities.

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 tool name than a natural keyword a user would say. Missing terms like 'bug', 'ticket', 'issue', 'task', 'Jira', 'tracking', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so generic that it could overlap with any project management, task tracking, or bug reporting skill. There are no distinct triggers or specific capabilities to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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, inlining full issue templates, aspirational feature descriptions, and marketing-style sections that provide no actionable value. The tool invocation syntax is non-standard pseudo-code rather than executable commands, and critical validation/error-handling steps are entirely absent from multi-step workflows. The content would benefit from aggressive trimming to ~25% of its current size, focusing on concrete executable patterns with validation checkpoints.

Suggestions

Remove the 'Metrics and Analytics', 'Integration with Other Modes', and 'Capabilities' sections entirely — they describe aspirational features rather than providing actionable instructions.

Add explicit validation steps after issue creation (e.g., verify the issue was created successfully with `gh issue view`) and error handling for common failures like auth issues or rate limits.

Replace the pseudo-JavaScript tool invocation syntax with either actual CLI commands or clearly documented tool call formats that match the MCP tool interface.

Move the full issue templates to separate referenced files (e.g., TEMPLATES.md) and keep only a brief summary with links in the main skill body.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive redundancy. The 'Capabilities' section duplicates the frontmatter. Templates are bloated with placeholder text Claude doesn't need. The 'Metrics and Analytics' and 'Integration with Other Modes' sections describe aspirational features rather than actionable instructions. Massive amounts of boilerplate (emoji, branding lines like '🤖 Generated with Claude Code') waste tokens.	1 / 3
Actionability	Code examples are provided but use a pseudo-JavaScript syntax that isn't directly executable (e.g., `mcp__claude-flow__swarm_init { topology: "star" }` is not valid JS or a real tool invocation format). The gh CLI commands in Bash are more concrete, but templates are just markdown scaffolding with placeholders like '[Brief description]' rather than executable guidance.	2 / 3
Workflow Clarity	Despite showing multi-step processes (issue creation, progress updates, batch operations), there are no validation checkpoints, no error handling, and no feedback loops. The batch operations section creates multiple issues without any verification that they succeeded. The workflow is a sequence of tool calls with no conditional logic or recovery steps for failures.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. Everything is inlined including two full issue templates, batch operation examples, best practices, integration notes, and metrics descriptions. No bundle files exist to offload content to, yet the content could easily be split. The document is over 200 lines with no clear navigation structure beyond flat headings.	1 / 3
	Total	5 / 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/claude-flow
Commit: 9d4a9ea

Reviewed: 6 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.