creating-github-issues-from-web-research
This skill enhances Claude's ability to conduct web research and translate findings into actionable GitHub issues. It automates the process of extracting key information from web search results and formatting it into a well-structured issue, ready for team action. Use this skill when you need to research a topic and create a corresponding GitHub issue for tracking, collaboration, and task management. Trigger this skill by requesting Claude to "research [topic] and create a ticket" or "find [information] and generate a GitHub issue".
75
44%
Does it follow best practices?
Impact
95%
1.05xAverage score across 6 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-migration-20251108-070147/plugins/skill-enhancers/web-to-github-issue/skills/web-to-github-issue/SKILL.mdQuality
Discovery
82%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 is a reasonably well-constructed description that clearly communicates both what the skill does and when to use it, with explicit trigger phrases. Its main weaknesses are moderate specificity (it describes the workflow at a high level without detailing concrete sub-actions) and some overlap risk with standalone web research or GitHub issue creation skills. The description also uses phrases like 'enhances Claude's ability' which is slightly fluffy.
Suggestions
Add more specific concrete actions, e.g., 'searches the web for relevant articles, summarizes findings, creates a GitHub issue with title, description, labels, and acceptance criteria'
Reduce filler phrases like 'enhances Claude's ability' and 'ready for team action' in favor of more precise capability statements
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (web research + GitHub issues) and some actions ('extracting key information from web search results', 'formatting it into a well-structured issue'), but it doesn't list multiple concrete specific actions like filling specific fields, adding labels, assigning milestones, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (conducts web research and translates findings into GitHub issues) and 'when' (explicit 'Use this skill when...' clause and 'Trigger this skill by...' with example phrases). | 3 / 3 |
Trigger Term Quality | Includes good natural trigger terms: 'research [topic] and create a ticket', 'find [information] and generate a GitHub issue', plus keywords like 'web research', 'GitHub issues', 'tracking', 'collaboration', 'task management'. These cover natural phrasings users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of web research + GitHub issue creation is somewhat distinctive, but the web research component could overlap with general search skills, and the GitHub issue component could overlap with general GitHub skills. The combined workflow helps but each half is fairly broad. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a marketing description or README rather than an actionable skill file. It lacks any concrete implementation details—no CLI commands, no issue templates, no tool invocation patterns, no structured output formats. The content explains concepts Claude already understands while failing to provide the specific guidance needed to actually execute the workflow.
Suggestions
Replace the abstract 'How It Works' section with concrete tool invocations: specify the exact web_search tool usage, show the GitHub CLI command (`gh issue create --repo REPO --title TITLE --body BODY --label LABEL`), and provide a template for the issue body format.
Add a concrete issue body template with placeholders showing the expected structure (title format, sections like Summary/Key Findings/Sources/Action Items) so Claude knows exactly what output to produce.
Add validation steps: verify the repository exists before creating the issue, confirm the issue was created successfully, and handle cases where web search returns insufficient results.
Remove the 'When to Use This Skill', 'Best Practices', and 'Integration' sections entirely—they explain things Claude already knows and consume tokens without adding actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and explains concepts Claude already knows (what web search is, what information extraction means, what GitHub issues are). Sections like 'How It Works', 'When to Use This Skill', and 'Integration' are padded with unnecessary context that doesn't add actionable value. The 'Best Practices' section states obvious things like 'provide context in your request.' | 1 / 3 |
Actionability | There are no concrete commands, code snippets, API calls, or executable steps. The entire skill describes what will happen at a high level ('the skill will search the web...') without providing any actual implementation details—no GitHub CLI commands, no issue template format, no specific tool invocations, no structured output format for the issue body. | 1 / 3 |
Workflow Clarity | The numbered steps are vague descriptions of intent ('Extract key recommendations') rather than actionable workflow steps with specific tools or validation checkpoints. There is no error handling, no validation of the created issue, no feedback loop if the search returns poor results, and no concrete sequencing of tool calls. | 1 / 3 |
Progressive Disclosure | The content is organized into logical sections with headers, which provides some structure. However, there are no references to external files, no bundle files to support deeper content, and the content that is present is mostly filler that could be dramatically condensed rather than split across files. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
100%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.
- Commit
13d35b8
- Reviewed
Table of Contents
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.