daytona-secrets-volume

Daytona secrets, provider key, OpenAI key, Anthropic key, real model e2e, voice e2e, eval secrets, /daytona-secrets, openwork-eval-secrets. Use for real provider tests in Daytona.

Quality

87%

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

96%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 body is lean, fully actionable, and well-sequenced with strong safety validation for risky secret operations, all without over-explaining concepts Claude already knows. Its only minor gap is that all content lives inline with no progressive-disclosure split, which is appropriate for a focused skill but keeps it just short of the top structure anchor.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding: it assumes Claude knows what env vars and Daytona are, and every section (volume, add, shape, reload, verify, gotchas) earns its place without over-explanation.	5 / 5
Actionability	Fully executable, copy-paste-ready bash commands with concrete examples covering the common cases (setup script invocations, sandbox reload, safe verification), matching the executable anchor.	5 / 5
Workflow Clarity	Multi-step processes are sequenced with an explicit safety-validation section and a gotcha explaining why the pkill and restart must not be chained; validation checkpoints are present for the risky secret-handling operations, so the destructive-cap does not apply.	5 / 5
Progressive Disclosure	A single-purpose skill with no bundle files, organized into clear section headers and well-placed inline content; it is well-structured but slightly denser than the ideal overview-pointing-to-details 5 anchor.	4 / 5
	Total	19 / 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 specific, distinctive, and explicitly pairs a 'what' with a 'when' clause in third-person voice. It is slightly keyword-stuffed and could read more naturally, but it covers concrete capabilities and clear triggers well.

Suggestions

Reword the keyword list into a more natural sentence so the description reads as prose rather than a comma-separated token dump, improving trigger_term_quality and completeness toward 5.

Add a couple of natural trigger variations or synonyms (e.g., 'provider credentials', 'CI eval keys') to broaden the terms a user might naturally say.

Dimension	Reasoning	Score
Specificity	Lists several concrete items (provider key, OpenAI/Anthropic keys, real model e2e, voice e2e, /daytona-secrets volume) rather than vague actions, though it reads as a token list rather than enumerated actions, so it falls short of the comprehensive 5.	4 / 5
Completeness	Has both a clear 'what' (Daytona secrets, keys, the volume) and an explicit 'when' ('Use for real provider tests in Daytona'), but the trigger guidance is terser than the fully-expansive 5 anchor.	4 / 5
Trigger Term Quality	Good keyword coverage with natural phrases users would say ('real provider tests', 'eval secrets', 'OpenAI key', 'Anthropic key') plus the volume name, though the keyword-dump style omits some natural variations.	4 / 5
Distinctiveness Conflict Risk	Highly specific to Daytona eval secrets with unique tokens (/daytona-secrets, openwork-eval-secrets, voice e2e), giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	17 / 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: different-ai/openwork
Path: .opencode/skills/daytona-secrets-volume/SKILL.md
Commit: 7b76a2b

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.