Name: gh
Rating: 68.8 (1 reviews)
Author: gsd-build

gh

Install and configure the GitHub CLI (gh) for AI agent environments where gh may not be pre-installed and git remotes use local proxies instead of github.com. Provides auto-install script with SHA256 verification and GITHUB_TOKEN auth with anonymous fallback. Use when gh command not found, shutil.which("gh") returns None, need GitHub API access (issues, PRs, releases, workflow runs), or repository operations fail with "failed to determine base repo" error. Documents required -R flag for all gh commands in proxy environments. Includes project management: GitHub Projects V2 (gh project), milestones (REST API), issue stories (lifecycle and templates), and label taxonomy management.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable gh command catalog with good reference-file signalling, weakened by inline/reference duplication, missing validation checkpoints in its multi-step workflows, and inconsistent bundle navigation (a broken ci_monitor.cjs path plus two unreferenced script files). The hardcoded `gsd-build/gsd-2` repo throughout also reduces reusability for a general skill.

Suggestions

Tighten the body: drop the inline label/milestone/project command blocks that duplicate labels.md/milestones.md/projects-v2.md (keep a one-line pointer instead) and remove the repeated description trigger/proxy-error text so the overview stays lean.

Add validation checkpoints to multi-step workflows — e.g. run `gh --version` / `gh auth status` after install, and verify the GraphQL `updateIssue` response before declaring an issue type set — so destructive/batch-style operations have feedback loops.

Fix the broken `ci_monitor.cjs` reference (it does not resolve under the bundle's `scripts/` path) and link the orphaned `scripts/github_project_setup.py` and `experiment_cleanup.py` from the body so the whole bundle is navigable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient command reference (no concept over-explanation), but it repeats the trigger/proxy-error text from the description and keeps full inline label/milestone/project command blocks that duplicate the dedicated reference files — 'mostly efficient but ... could be tightened' rather than lean.	2 / 3
Actionability	Packed with concrete, executable commands (e.g. the multi-step GraphQL issue-type workflow with real queries, `gh pr list -R ... --json number,title`), fully copy-paste ready per the top anchor.	3 / 3
Workflow Clarity	The issue-type section is a clear multi-step sequence, but it and the install/auth flows lack validation checkpoints (no `gh --version`/auth confirm after install, no verification that the `updateIssue` mutation succeeded); per the rubric, missing validation in such operations caps this at 2.	2 / 3
Progressive Disclosure	The four .md references are well-signaled and one level deep, but the body references a non-existent deeply-nested `ci_monitor.cjs` path and never surfaces the two real `scripts/` files (`github_project_setup.py`, `experiment_cleanup.py`) — incomplete bundle navigation and a broken referenced path.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A dense, specific, third-person description with explicit what/when triggers and a distinctive niche. The main weakness is an over-claim: it advertises an 'auto-install script with SHA256 verification and ... anonymous fallback' that the body does not provide (the body says gh is assumed installed via the package manager and gives no SHA256/anonymous-fallback mechanism), but this accuracy mismatch is not captured by the description rubric's dimensions.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'Install and configure the GitHub CLI', 'SHA256 verification', 'GITHUB_TOKEN auth', 'Documents required -R flag', 'GitHub Projects V2 (gh project), milestones (REST API), issue stories ... label taxonomy management' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Install and configure ... Provides ... Documents ... Includes project management') and when (a clear 'Use when ...' clause), matching the top anchor.	3 / 3
Trigger Term Quality	The 'Use when gh command not found ... need GitHub API access (issues, PRs, releases, workflow runs), or repository operations fail with "failed to determine base repo" error' clause gives good coverage of natural error/need terms a caller would encounter.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche — gh CLI setup in AI-agent/proxy environments with the specific '-R flag' and 'failed to determine base repo' triggers — making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gsd-build/gsd-2
Path: src/resources/skills/github-workflows/references/gh/SKILL.md
Commit: 33c00aa

Reviewed: about 13 hours 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.