github-auth

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/github/github-auth/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable commands and well-sequenced workflows that include verification steps and a troubleshooting table. Its main weaknesses are minor redundant commentary and a progressive-disclosure gap where the bundled gh-env.sh script is duplicated inline rather than referenced.

Suggestions

Replace the inline "Helper: Detect Auth Method" block with a reference to the bundled script, e.g. "source scripts/gh-env.sh to detect the auth method".

Trim explanatory asides Claude already knows (e.g. "modern, secure, fast" for ed25519, "most portable method") to tighten conciseness.

Add a one-line pointer to scripts/gh-env.sh near the Detection Flow so the bundle file is clearly signaled and discoverable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and concrete, but includes unnecessary asides Claude already knows ("modern, secure, fast" for ed25519, "most portable method") and duplicates the auth-detection helper inline rather than deferring to the bundled script, so it could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready bash commands throughout (ssh-keygen, git config, gh auth login, curl API calls) with concrete examples, matching the score-3 anchor.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints (Option A "Step 4: Verify", SSH "Step 3: Test the connection", gh "Verify") plus a troubleshooting table for error recovery, satisfying the score-3 anchor.	3 / 3
Progressive Disclosure	Sections are well organized, but the bundled scripts/gh-env.sh is never referenced from the body and its detection logic is duplicated inline in the "Helper: Detect Auth Method" section — content that should be separate is inline, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and well-scoped to GitHub authentication with concrete method names, but it lacks an explicit "Use when..." trigger clause and uses the slightly unnatural term "HTTPS tokens" instead of "personal access token". Adding a trigger clause and the common PAT/PATs phrasing would raise completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when the agent needs to authenticate to GitHub for repos, PRs, issues, or CI."

Replace or supplement "HTTPS tokens" with the natural user term "personal access tokens (PATs)".

Include common trigger variations users actually say ("log in to GitHub", "set up gh", "GitHub credentials").

Dimension	Reasoning	Score
Specificity	The description names the domain ("GitHub auth setup") and lists multiple specific concrete methods — "HTTPS tokens, SSH keys, gh CLI login" — matching the score-3 anchor that rewards listing several specific actions.	3 / 3
Completeness	It clearly states what the skill does (GitHub auth setup via three methods) but has no "Use when..." clause or equivalent explicit trigger guidance for when to use it, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes natural terms users would say ("GitHub", "SSH keys", "gh CLI login"), but uses "HTTPS tokens" instead of the more common "personal access token"/"PAT" and omits common variations, fitting the score-2 anchor of some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	Authentication setup is a clear, distinct niche from the related github-* skills, with triggers (tokens, SSH keys, gh login) specific to auth, so it is unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 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 — 13 / 16 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/github/github-auth/SKILL.md
Commit: 6a8d318

Reviewed: about 14 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.