github

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

1.23x

Quality

85%

Does it follow best practices?

Impact

100%

1.23x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

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.

The description is strong in specificity and distinctiveness, clearly naming the tool (`gh` CLI) and its key subcommands with their purposes. The main weakness is the absence of an explicit 'Use when...' clause, which caps completeness at 2. Adding trigger guidance would make this description excellent.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about GitHub issues, pull requests, CI/CD status, repository management, or wants to interact with GitHub from the command line.'

Include common natural language variations like 'pull request' (spelled out), 'workflow', 'actions', 'merge', 'review' to improve trigger coverage for edge cases.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: interacting with GitHub via `gh` CLI, and explicitly names subcommands (`gh issue`, `gh pr`, `gh run`, `gh api`) mapped to specific domains (issues, PRs, CI runs, advanced queries).	3 / 3
Completeness	Clearly answers 'what does this do' (interact with GitHub using gh CLI for issues, PRs, CI runs, advanced queries), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill. The when is only implied by the capabilities listed.	2 / 3
Trigger Term Quality	Includes strong natural keywords users would say: 'GitHub', 'gh', 'issue', 'PR', 'CI runs', 'gh api'. These cover common variations of how users refer to GitHub operations. Missing some terms like 'pull request' spelled out or 'workflow', but coverage is good.	3 / 3
Distinctiveness Conflict Risk	Very distinct niche: specifically about the `gh` CLI tool for GitHub interactions. The mention of specific subcommands (`gh issue`, `gh pr`, `gh run`, `gh api`) makes it clearly distinguishable from generic code or git skills.	3 / 3
	Total	11 / 12 Passed

Implementation

87%

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-crafted, concise skill that provides immediately actionable gh CLI commands. Its main strength is token efficiency and concrete examples. The one area for improvement is making the implicit CI debugging workflow (checks → run list → view → log-failed) more explicit as a sequenced process.

Suggestions

Consider adding a brief numbered workflow for the CI debugging flow, e.g., '1. Check PR status → 2. If failing, list runs → 3. View failed run → 4. Get failed logs' to make the implicit sequence explicit.

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient. It doesn't explain what GitHub is, what PRs are, or how the gh CLI works conceptually. Every line provides a concrete command or minimal context needed to use it.	3 / 3
Actionability	Every section provides copy-paste ready bash commands with realistic arguments. The commands are fully executable and cover common use cases (PR checks, run logs, API queries, JSON filtering).	3 / 3
Workflow Clarity	The commands are individually clear but there's no explicit workflow sequencing. For example, the CI debugging flow (check PR → find failed run → view logs) is implied by ordering but not explicitly connected as a sequence with decision points.	2 / 3
Progressive Disclosure	For a simple, focused skill under 50 lines with no need for external references, the content is well-organized into logical sections (Pull Requests, API, JSON Output) with clear headers. No bundle files are needed.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	9 / 11 Passed

Repository: HKUDS/nanobot
Commit: 851150f

Reviewed: about 1 hour 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.