CtrlK
BlogDocsLog inGet started
Tessl Logo

record-video

Record and upload a short browser interaction video artifact

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./packages/sandbox-runtime/src/sandbox_runtime/skills/record-video/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable and well-structured, with a complete executable script, explicit validation, and error-recovery guidance. The only minor gap is progressive disclosure: the long inline bash pattern sits at the edge of what could live in a bundled script file.

DimensionReasoningScore

Conciseness

The body is efficient with minimal over-explanation: short Key Facts, a concrete workflow, and focused Guardrails; the inline bash script is long but earns its place as a copy-paste pattern, leaving only minor trim potential.

4 / 5

Actionability

The Command Pattern is a fully executable, copy-paste-ready bash script with real commands (agent-browser, ffprobe, upload-media) and complete flags, covering the common recording case end-to-end.

5 / 5

Workflow Clarity

The 8-step Required Workflow is clearly sequenced with an explicit validation checkpoint (ffprobe for real dimensions/duration), a cleanup trap, and a feedback loop for failed recordings (stop, then upload any available MP4).

5 / 5

Progressive Disclosure

Content is well organized into clear sections (Key Facts, Required Workflow, Command Pattern, Guardrails) with no external references needed for this single-purpose skill, though the substantial inline script slightly exceeds the under-50-line simple-skill threshold.

4 / 5

Total

18

/

20

Passed

Description

53%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 concise and names a clear, specific niche with two concrete actions, but it omits any explicit "when to use" trigger guidance and lacks natural synonym/extension keywords. Completeness is the main limiter due to the missing Use-when clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when a UI verification depends on interaction over time: menus, flows, dragging, typing, navigation, loading states, transitions, or animation."

Include natural synonyms and an extension users would say, such as "screen recording", "screen capture", "demo video", or ".mp4".

Consider adding one more concrete action (e.g. "probe encoded dimensions/duration") to broaden specificity coverage toward a 4.

DimensionReasoningScore

Specificity

"Record and upload a short browser interaction video artifact" names the domain (browser interaction video) and two concrete actions (record, upload), matching the anchor for 1-2 concrete actions without being comprehensive.

3 / 5

Completeness

The description gives a clear "what" (record and upload a browser interaction video) but includes no "Use when..." clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

"browser interaction video" provides relevant keywords but misses common natural variations users would say such as "screen recording", "screen capture", "demo video", or a file extension like .mp4.

3 / 5

Distinctiveness Conflict Risk

"browser interaction video artifact" carves a fairly distinct niche with minimal conflict risk, though "record and upload" retains minor overlap with general media-upload skills rather than being a fully isolated trigger set.

4 / 5

Total

13

/

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
ColeMurray/background-agents
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.