create-user-story

Create user stories with duplicate checking across any project tracker (Linear, GitHub Issues, Jira)

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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 and well-sequenced with explicit user-confirmation checkpoints and error-handling feedback loops, earning top marks on actionability and workflow clarity. It loses points on conciseness and progressive disclosure because a 230-line, single-file skill repeats per-tracker blocks and inlines content that could be split into reference files.

Suggestions

Extract the per-tracker duplicate-check and create command blocks (Linear/GitHub/Jira) into reference files under ./references/ and link to them from the body, reducing repetition and shrinking the main SKILL.md.

Move the full user-story markdown template into a ./references/story-template.md and reference it, keeping only a brief format summary inline.

Tighten the duplicate-checker agent prompts by consolidating shared structure rather than restating the full checklist for each tracker.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is sectionally efficient, but at ~230 lines it repeats near-identical duplicate-check and create blocks across three trackers and embeds a large story template that could be tightened or externalized.	2 / 3
Actionability	Provides executable, copy-paste-ready commands and tool calls: 'gh search issues ... --json', 'gh issue create --repo ...', real Linear MCP tool names (mcp__claude_ai_Linear_2__save_issue), and concrete Jira JQL and REST paths, with customization placeholders clearly marked.	3 / 3
Workflow Clarity	A clear six-phase sequence (Pre-Flight through Confirm and Link) with explicit validation checkpoints ('Wait for user confirmation before proceeding', 'Present the formatted story ... before creating it') and an Error Handling section defining retry/fallback feedback loops.	3 / 3
Progressive Disclosure	Sections are well-organized with headers and a fallback table, but the skill is a single monolithic file with no bundle references; tracker-specific command sets and the full story template that could live in separate reference files are inlined.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 states a clear, third-person purpose with a distinctive niche, but it stops at score 2 on most dimensions because it omits an explicit 'Use when...' trigger clause and a broader set of natural trigger terms. It is concise and non-over-claiming rather than padded.

Suggestions

Add an explicit 'Use when...' clause with natural triggers, e.g. 'Use when the user wants to create a user story, feature request, or issue and check for duplicates across Linear, GitHub Issues, or Jira.'

Include common phrasings users actually say ('new story', 'add issue', 'create ticket', 'feature request') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Create user stories with duplicate checking') plus the supported trackers (Linear, GitHub Issues, Jira), but does not enumerate the fuller set of actions the body performs (formatting, linking, vault fallback).	2 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'Use when...' clause or equivalent trigger guidance, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Contains some natural terms a user would say ('Create user stories', tracker names) but omits common variations like 'issue', 'ticket', or 'feature request' that the body itself lists as triggers.	2 / 3
Distinctiveness Conflict Risk	The combination of user-story creation plus cross-tracker duplicate checking is a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: huytieu/COG-second-brain
Commit: 5e9851c

Reviewed: 14 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.