github-automation
Automate GitHub repositories, issues, pull requests, branches, CI/CD, and permissions via Rube MCP (Composio). Manage code workflows, review PRs, search code, and handle deployments programmatically.
75
68%
Does it follow best practices?
Impact
81%
1.32xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/github-automation/SKILL.mdQuality
Discovery
75%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 is strong in specificity and trigger term coverage, listing many concrete GitHub-related actions with natural keywords. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The broad scope covering nearly all GitHub operations could also create overlap with more focused GitHub skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to automate GitHub tasks, manage repositories, create or review pull requests, or interact with GitHub APIs via Composio.'
Clarify what distinguishes this from other potential GitHub or Git skills by emphasizing the Composio/Rube MCP integration as the differentiator, e.g., 'Use this skill specifically for programmatic GitHub automation through the Rube MCP Composio integration, not for local git commands.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: manage repositories, issues, pull requests, branches, CI/CD, permissions, review PRs, search code, and handle deployments. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the actions listed, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'GitHub', 'repositories', 'issues', 'pull requests', 'branches', 'CI/CD', 'permissions', 'PRs', 'code', 'deployments'. Good coverage of terms a user would naturally use when needing GitHub automation. | 3 / 3 |
Distinctiveness Conflict Risk | Mentions 'GitHub' and 'Rube MCP (Composio)' which helps distinguish it, but terms like 'code workflows', 'review PRs', and 'search code' could overlap with generic code review or Git skills. The mention of the specific tool (Composio) helps but the broad scope of actions could still cause conflicts with other GitHub-related skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized skill with excellent workflow clarity — clear sequences, validation checkpoints, and safety guards for destructive operations. Its main weaknesses are verbosity (repeated information across sections, especially pitfalls and pagination notes) and the lack of executable examples showing actual MCP call syntax. The content would benefit from splitting detailed workflow references into separate files and adding concrete invocation examples.
Suggestions
Add at least one concrete example showing an actual MCP tool invocation with parameters (e.g., a complete RUBE_SEARCH_TOOLS call followed by a GITHUB_CREATE_AN_ISSUE call with sample parameters) to improve actionability.
Consolidate repeated pitfalls (pagination, issues-vs-PRs) into the 'Known Pitfalls' section only, and reference it from individual workflows instead of duplicating the information.
Consider moving the detailed per-workflow tool sequences and parameters into a separate WORKFLOWS.md reference file, keeping SKILL.md as a concise overview with the setup, common patterns, safety rules, and quick reference table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but quite long (~250 lines). Some information is repeated across sections (e.g., pagination pitfalls mentioned in multiple workflows AND in Common Patterns AND in Known Pitfalls). The quick reference table at the end largely duplicates information already covered in each workflow section. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides specific tool names, parameter lists, and clear tool sequences for each workflow, which is good. However, there are no executable code examples or copy-paste ready commands — everything is described at the tool-slug level without showing actual MCP call syntax or example payloads. The guidance is concrete in naming tools but incomplete in showing how to invoke them. | 2 / 3 |
Workflow Clarity | Each workflow has a clear numbered sequence with labeled steps (Required/Optional/Alternative/Prerequisite), explicit validation checkpoints (verify mergeable status before merge, check CI status, confirm connection is ACTIVE), and safety gates requiring user confirmation for destructive operations. The setup section includes a clear 4-step verification flow with error recovery (follow auth link if not ACTIVE). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a table of contents-like organization, but it's monolithic — all 6 workflows, common patterns, known pitfalls, and a full quick reference table are in a single file. The detailed workflow sections with their parameters and pitfalls could be split into separate reference files, with SKILL.md serving as an overview pointing to them. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.