CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gemini-auth

Setup and manage Gemini CLI authentication methods including OAuth, API keys, and Vertex AI. Use when configuring Gemini access, switching auth methods, or troubleshooting authentication issues.

Quality

74%

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 ./skills/gemini-auth/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

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

The content is highly actionable with concrete commands for all three auth methods, but it is a monolithic ~450-line document that inlines scripts and integration examples belonging in reference files, repeats verification patterns, and includes destructive and batch operations without validation checkpoints. Tightening and splitting the advanced workflows into references would address the weakest dimensions.

Suggestions

Split the Workflow Scripts (multi-account switching, pass storage, rate-limit retry), Security Best Practices, and Integration Examples (CI/CD, Docker) sections into reference files (e.g., references/workflows.md, references/integrations.md), keeping SKILL.md as a concise overview with clearly signaled one-level-deep links.

Add validation checkpoints before and after risky operations: check for an existing token backup before `rm -rf ~/.gemini/auth/tokens`, and verify auth status between iterations in the `test_all_accounts` batch loop.

Fix the executable-code gaps: replace the undefined `generate_new_key`/`revoke_old_key` placeholders in `rotate_api_key` with real steps or remove the function, and use unquoted tildes or `$HOME` so paths like `~/gemini-sa-key.json` and `~/.gemini/usage.log` actually expand.

DimensionReasoningScore

Conciseness

The body is mostly code with little conceptual padding, but at ~450 lines it inlines full scripts (pass storage, audit logging, rate-limit retry, CI/CD, Docker) beyond the core auth task and repeats the `gemini --yolo -p "Test..."` verification pattern four times — 'mostly efficient but could be tightened', not the lean level 4-5.

3 / 5

Actionability

Concrete, mostly copy-paste-ready commands throughout (env vars, gcloud IAM bindings, config.json, retry logic), but minor gaps remain: `rotate_api_key` calls undefined placeholder functions (`generate_new_key`, `revoke_old_key`), and quoted tildes like `"~/gemini-sa-key.json"` and `log_file="~/.gemini/usage.log"` do not expand in bash.

4 / 5

Workflow Clarity

Each auth method has a setup-then-test sequence and a priority order is documented, but destructive operations lack validation ("rm -rf ~/.gemini/auth/tokens" with no pre-check) and the batch `test_all_accounts` loop has no checkpoints — the missing-validation cap on destructive/batch workflows holds this at 3 rather than 4.

3 / 5

Progressive Disclosure

Section headers provide navigable structure, but no bundle files exist and ~450 lines of workflow scripts, security practices, and integration examples that clearly belong in separate reference files are all inlined in SKILL.md — matching 'content that should be separate is inline'. Not level 2 because the headers do make it navigable; not level 4 because nothing is split out.

3 / 5

Total

13

/

20

Passed

Description

78%Weight 40%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 is strong: it clearly states what the skill does, covers three concrete auth methods, and includes an explicit 'Use when...' clause with three natural trigger scenarios. The main gaps are generic verbs ('setup and manage') and missing common synonyms like 'login' or 'credentials', plus slight overlap risk with a general Gemini CLI setup skill.

DimensionReasoningScore

Specificity

Names the domain ("Gemini CLI authentication methods") and enumerates the three specific methods ("OAuth, API keys, and Vertex AI"), but the verbs "Setup and manage" are generic — matching the 'names domain and 1-2 concrete actions' anchor rather than the multiple distinct concrete actions of level 4.

3 / 5

Completeness

Explicitly answers what ("Setup and manage Gemini CLI authentication methods including OAuth, API keys, and Vertex AI") and when ("Use when configuring Gemini access, switching auth methods, or troubleshooting authentication issues") with three concrete trigger phrases, matching the level 5 anchor. It is not 4 because the when-clause is fully explicit and specific, not merely adequate.

5 / 5

Trigger Term Quality

"configuring Gemini access, switching auth methods, or troubleshooting authentication issues" plus "OAuth, API keys, and Vertex AI" give good natural keyword coverage; common variations like "login", "credentials", or "gemini auth" are missing, keeping it below the comprehensive-synonym level 5.

4 / 5

Distinctiveness Conflict Risk

The "Gemini CLI authentication" niche is mostly distinct with auth-specific triggers, but "configuring Gemini access" could overlap with a sibling general Gemini CLI setup skill (the body itself lists related skills like `gemini-cli`), giving minor overlap risk consistent with level 4 rather than the minimal-conflict level 5.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

fernandezbaptiste/Skrillz

Path

skills/gemini-auth/SKILL.md

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.