CtrlK
BlogDocsLog inGet started
Tessl Logo

run-evals

DEPRECATED legacy automation runner. Load only when a user explicitly asks to run an EXISTING evals/flows/*.flow file. New coverage uses run-tests.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/run-evals/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is a concise, well-structured policy/redirect skill with executable commands and clear guardrails; the only mild gap is the absence of an explicit validation checkpoint in the run workflow.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no concept explanations, no padding, every line directs behavior ('Refuse to create...', 'List and run only the requested existing flow'), matching the 'lean and efficient' anchor.

5 / 5

Actionability

Provides concrete executable commands ('pnpm evals:legacy --list', 'pnpm evals:legacy --flow <existing-id> --cdp-url <electron-cdp-url>') with minor gaps from placeholder arguments and a policy-heavy rather than code-heavy stance.

4 / 5

Workflow Clarity

A clear list-then-run sequence with the optional Daytona branch is present, but there is no explicit validation checkpoint between running the flow and reporting results, leaving a minor validation gap.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external file references and well-organized into directive bullets and a command block, satisfying the simple-skill exception for a top score.

5 / 5

Total

18

/

20

Passed

Description

73%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 a strong, narrow-gauge deprecation notice with an explicit trigger condition and clear redirection, though its statement of capabilities is thin.

Suggestions

Expand the 'what' beyond 'legacy automation runner' to name the concrete actions it performs (e.g., 'lists and executes existing evals/flows/*.flow files against an Electron CDP target') to lift specificity.

Add a natural-language synonym or two for the trigger (e.g., 'eval flow', 'legacy flow') so users phrasing the request differently still match.

Consider naming the file extension explicitly (e.g., '.flow files') to strengthen trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ('legacy automation runner') and one concrete action ('run an EXISTING evals/flows/*.flow file') but offers no broader enumeration of what it does, matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

Both 'what' (legacy automation runner of existing flow files) and 'when' ('Load only when a user explicitly asks to run an EXISTING evals/flows/*.flow file') are present and the when is explicit, but the 'what' is terse rather than fully concrete.

4 / 5

Trigger Term Quality

Includes natural terms users would say ('run a flow', 'evals/flows/*.flow file', 'run-tests') giving good keyword coverage, though it lacks synonyms or file-extension variants needed for a 5.

4 / 5

Distinctiveness Conflict Risk

The trigger is exceptionally narrow ('only when a user explicitly asks to run an EXISTING evals/flows/*.flow file') and explicitly redirects new work to run-tests, giving a clear niche with minimal conflict risk.

5 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
different-ai/openwork
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.