daytona-recording-artifacts

frame proof, HTML frames, screenshots, recording, PR proof, e2e evidence, validate visually. Daytona artifacts workflow for validated screenshots and optional videos.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/daytona-recording-artifacts/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable commands, clear numbered workflows, and strong validation/feedback checkpoints, which makes it effective in practice. Its main weakness is verbosity from repetition and a lack of progressive disclosure, since all detail lives inline in one file.

Suggestions

De-duplicate the repeated http.server and preview-url command blocks by extracting them into a single reusable snippet or a referenced helper script.

Move the long Before/After Flow command sequence and the Recording Standard guidance into a reference file referenced one level deep to improve progressive disclosure.

Trim prose in the Recording Standard and Validation Standard sections to the essential rules so the body stays lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense executable commands with no basic-concept padding, but at ~234 lines it repeats itself (the python http.server command is restated in the fallback section, and preview-url usage is restated under Get Artifact URLs) and could be tightened. It is not 1 because it does not explain concepts Claude already knows.	2 / 3
Actionability	It provides abundant copy-paste-ready executable bash such as 'daytona exec ... python3 -m http.server 8090', 'daytona preview-url "$SANDBOX" -p 8090', and 'ffprobe ... -show_entries format=duration', with specific concrete examples throughout.	3 / 3
Workflow Clarity	Frame-proof production is given as numbered steps (1-5) with explicit validation checkpoints ('verify every file is non-zero before sharing', ffprobe duration check, 'Only share the refreshed URL after the local curl -I returns 200 OK') and feedback loops (recapture on mismatch, supersede invalid evidence with new frames).	3 / 3
Progressive Disclosure	The skill has clear section headings but is a monolithic >50-line single file with all content inline and no split-out reference files (references/scripts/assets are absent). External scripts are signaled inline, but there is no one-level-deep reference structure that the 3 anchor requires.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 communicates a clear, distinctive Daytona proof-gathering niche but leans on keyword fragments and omits an explicit 'Use when...' trigger clause. Tightening the nouns into verb actions and adding trigger guidance would lift completeness and specificity.

Suggestions

Rewrite the opening keyword list as concrete verb phrases, e.g. 'Capture HTML frame proof, screenshots, and optional video clips of Daytona UI flows and validate them for PR evidence.'

Add an explicit trigger clause such as 'Use when the user asks for e2e UI proof, visual validation, or PR evidence for a Daytona flow.'

Replace internal jargon ('frame proof', 'PR proof') with natural user terms ('UI flow proof', 'PR review evidence') to improve trigger quality.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Daytona artifacts workflow for validated screenshots and optional videos') and lists concrete artifacts, but they are phrased as noun-fragment keywords ('frame proof, HTML frames, screenshots, recording, PR proof, e2e evidence') rather than concrete verb actions. This matches 'Names domain and some actions, but not comprehensive' rather than the verb-phrase list required for 3.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guideline. It is not a 1 because the 'what' is clearly stated.	2 / 3
Trigger Term Quality	It includes some natural terms a user might say ('screenshots', 'recording', 'e2e evidence', 'validate visually'), but they are mixed with internal jargon ('frame proof', 'PR proof', 'HTML frames') that users would not naturally say, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The Daytona artifacts / PR-proof / e2e-evidence niche is clearly distinct and unlikely to trigger for the wrong skill. It is not below 3 because the niche and triggers are specific enough to avoid overlap.	3 / 3
	Total	9 / 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: Devin-AXIS/iPolloWork
Path: .opencode/skills/daytona-recording-artifacts/SKILL.md
Commit: bd5caef

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.