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

95%

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

100%

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

The body is a well-structured, executable guide: lean prose, copy-paste commands, explicit sequencing with safety checkpoints, and a useful gotchas section, all appropriately self-contained for a simple single-purpose skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it never explains what Daytona or env files are, and every section (volume, add, reload, verify, gotchas) earns its tokens with directly useful guidance.	3 / 3
Actionability	It provides copy-paste-ready, executable commands throughout (setup-daytona-secrets-volume.sh invocations, daytona exec restart sequence, ls and test -n verification) with concrete examples for each.	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced with checkpoints: the reload section separates kill/sleep/restart and explicitly warns against chaining pkill with restart, and a dedicated verify section provides a safe validation step (test -n) for a secrets operation.	3 / 3
Progressive Disclosure	With no bundle files present, the content is well-organized into clearly headed sections with no nested references; for this single-purpose skill the inline, sectioned structure is appropriate and easy to navigate.	3 / 3
	Total	12 / 12 Passed

Description

90%

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 a trigger-keyword-optimized line with an explicit "Use for" clause and a clearly distinct Daytona-eval-secrets niche, though it enumerates entities rather than concrete actions.

Suggestions

Lead with one or two concrete action verbs (e.g., "Provision and mount eval-only provider keys") before the keyword list so the capability, not just the domain, is explicit.

Trim internal jargon tokens like the bare path "/daytona-secrets" and "openwork-eval-secrets" from the user-facing description; keep them in the body where they aid execution.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ("Daytona secrets, provider key, OpenAI key, Anthropic key, real model e2e, voice e2e, eval secrets") but lists entities rather than actions, so it falls short of the anchor that requires multiple specific concrete actions.	2 / 3
Completeness	It answers "when" with an explicit trigger ("Use for real provider tests in Daytona.") and conveys the "what" via an enumerated scope of secrets/keys, satisfying the rubric's explicit-trigger requirement that gates the top level.	3 / 3
Trigger Term Quality	It includes natural terms a user would say ("OpenAI key", "Anthropic key", "real model e2e", "real provider tests", "eval secrets") alongside the volume path, giving good coverage of likely trigger phrasing.	3 / 3
Distinctiveness Conflict Risk	The niche is highly specific (Daytona eval-only secrets volume with named paths like /daytona-secrets and openwork-eval-secrets), making it unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 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: different-ai/openwork
Path: .opencode/skills/daytona-secrets-volume/SKILL.md
Commit: 1345d51

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.