yao-secret

Secret management expert. ALWAYS invoke this skill when you need to read API keys, tokens, or other secrets configured by the user. Never hardcode credentials — use this skill to retrieve them securely.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

86%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 executable commands and a clear sequenced workflow including a pre-check and fallback. It is concise and well-structured for a simple skill, with only minor redundancy in the Guidelines section.

Suggestions

Make the workflow's validation explicit by labeling the 'secret_list first' check and the 'not found → prompt user' fallback as numbered validation/checkpoint steps.

Trim Guidelines items that restate the description (e.g. 'Never hardcode API keys or tokens') to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding about what secrets are, but the Guidelines section restates the 'never hardcode' point from the description and includes a couple of slightly obvious items that could be trimmed.	4 / 5
Actionability	It gives fully executable, copy-paste-ready commands (`tai tool secret_list '{}'`, `tai tool secret_read '{"name": "GITHUB_TOKEN"}'`) with a parameter table and concrete examples covering common cases.	5 / 5
Workflow Clarity	The Typical Workflow is clearly sequenced (list → read → use) with a pre-check ('Always call secret_list first') and an error fallback ('If a secret is not found, prompt the user'), but the checkpoints are lightly stated rather than explicit validation steps.	4 / 5
Progressive Disclosure	This is a simple under-50-line skill with no need for external references, and it is well-organized into clear sections (tools, workflow, guidelines), so well-organized structure alone earns the top score.	5 / 5
	Total	18 / 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 on completeness and trigger clarity, with an explicit 'invoke when' clause and natural trigger terms. Specificity is slightly limited because the named actions collapse to a single read/retrieve operation.

Suggestions

Add a second distinct concrete action (e.g. 'list available secrets, read a secret by name') to lift specificity beyond one restated operation.

Include a couple more natural synonyms such as 'passwords' or 'connection strings' alongside 'API keys, tokens, secrets' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (secrets) and the concrete actions of reading and retrieving them, but these are essentially one action restated ('read API keys, tokens, or other secrets' / 'retrieve them securely') rather than several distinct actions.	3 / 5
Completeness	It explicitly answers both what (retrieve user-configured secrets securely) and when ('ALWAYS invoke this skill when you need to read API keys, tokens, or other secrets') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	It covers good natural keywords users would say — 'API keys', 'tokens', 'secrets', 'credentials' — though a few synonyms (e.g. passwords, connection strings) are absent.	4 / 5
Distinctiveness Conflict Risk	Secret management scoped to 'secrets configured by the user' is a mostly distinct niche, with only minor overlap risk against general credential-handling skills.	4 / 5
	Total	16 / 20 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: YaoApp/yao
Path: tools/skills/yao-secret/SKILL.md
Commit: 8999225

Reviewed: 3 days 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.