CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

56

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/github-automation/SKILL.md

The canonical home for this skill is github-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%Scale 1-5

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-structured and comprehensive GitHub automation skill that provides clear tool sequences, specific parameters, and useful pitfall warnings for each workflow. Its main weaknesses are the length and repetition (pitfalls listed both per-workflow and in a consolidated section), the lack of concrete invocation examples showing actual parameter values, and the monolithic structure that could benefit from splitting into separate reference files. The safety guidance around destructive operations is good but could include more explicit feedback loops.

Suggestions

Remove the consolidated 'Known Pitfalls' section since all pitfalls are already covered in their respective workflow sections, or vice versa — keep only one location to reduce redundancy.

Add at least one concrete example per major workflow showing an actual tool call with sample parameter values (e.g., creating an issue with specific owner, repo, title, body values).

Split the Quick Reference table and detailed workflow sections into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with links to detailed workflows.

Add explicit error-handling feedback loops for workflows beyond merge (e.g., what to do when GITHUB_CREATE_A_REFERENCE returns 422, or when GITHUB_CREATE_A_WORKFLOW_DISPATCH_EVENT fails).

DimensionReasoningScore

Conciseness

The skill is comprehensive but quite long (~200+ lines). There's some repetition between the per-workflow 'Pitfalls' sections and the consolidated 'Known Pitfalls' section. The 'When to use' descriptions are somewhat obvious. However, the tool-specific parameter details and pitfalls do add genuine value that Claude wouldn't inherently know. The Quick Reference table duplicates information already covered in the workflows.

3 / 5

Actionability

The skill provides concrete tool names, exact parameter names, and specific tool sequences for each workflow. It lacks executable code examples (no actual MCP call syntax shown), but the tool slugs and parameter specifications are specific enough to be directly actionable. The setup steps are clear and concrete. Minor gap: no example of an actual tool invocation with sample parameter values.

4 / 5

Workflow Clarity

Each workflow has a clearly numbered tool sequence with annotations like [Required], [Optional], [Prerequisite], and [Alternative]. The merge workflow includes validation checkpoints (check mergeable status, verify CI, require user confirmation). However, explicit feedback loops (validate -> fix -> retry) are mostly absent — the skill says 'verify' but doesn't specify what to do on failure for most workflows beyond the merge case. The setup section has a clear sequence with a connection verification step.

4 / 5

Progressive Disclosure

The content is entirely self-contained in one large file with no references to supporting documents. For a skill this comprehensive (6 major workflows, quick reference table, common patterns), some content could benefit from being split into separate files. The internal organization with sections and a quick reference table is decent, but the monolithic structure makes it harder to navigate. No bundle files are provided to offload detail.

3 / 5

Total

14

/

20

Passed

Description

66%Scale 1-5

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 provides good specificity with multiple concrete GitHub-related actions and strong trigger terms. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The mention of the specific MCP tool (Composio) adds distinctiveness.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about GitHub automation, managing repos, creating or reviewing pull requests, or handling CI/CD pipelines.'

Include additional natural trigger terms and synonyms such as 'repo', 'merge', 'commits', 'GitHub Actions', and 'git' to improve keyword coverage.

DimensionReasoningScore

Specificity

Lists several specific actions: managing repositories, issues, pull requests, branches, CI/CD, permissions, reviewing PRs, searching code, and handling deployments. Good coverage but some actions like 'manage code workflows' are somewhat vague.

4 / 5

Completeness

The 'what' is clearly described with multiple concrete actions, but there is no explicit 'when' clause (e.g., 'Use when...'). The absence of a 'when' trigger guidance caps this at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes strong natural keywords like 'GitHub', 'repositories', 'issues', 'pull requests', 'PRs', 'branches', 'CI/CD', 'deployments', 'code', and 'permissions'. Missing some common synonyms or variations like 'merge', 'commits', 'actions', 'workflows', or 'repo'.

4 / 5

Distinctiveness Conflict Risk

Specifying 'GitHub' and 'Rube MCP (Composio)' makes it fairly distinct from generic code or git skills. The mention of the specific tooling (Composio) and the GitHub platform reduces overlap risk, though there could be minor conflict with other GitHub-related skills.

4 / 5

Total

15

/

20

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.