SKILLEMALL.ai
GitHub ↗ RU Sign in

AB screencast-studio

Auto-record narrated demo videos of any web UI from a Playwright-driven walkthrough — primary use case is the vibe-coding test loop (you just shipped a feature with AI help and need to verify it / vibe-show it / iterate on it without manual screen recording). Output is a final.mp4 (synthetic cursor lerp + Material click ripples + burned-in subtitles + optional persistent mask regions for sensitive UI) plus a 4-pass review screenshot set for visual + privacy QA. Activate when the user wants to test or share something they just vibe-coded, or asks for a polished walkthrough / OSS feature demo / bug repro screencast / tutorial recording.

ClawHub Agent Skills author: TatsuKo Tsukimi v0.2.2 MIT-0 19 files body ≈ 3 323 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, running it twice

AnalyzerPlaywrightSoftware developmentMedia and videoInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
100
Quality 40%
86
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 0

    ✓ No critical or high findings

    Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 66/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Failures and branches. 6 branches
    • 100Steps. 50 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3323 tokens
    • 100Progress reporting. Reports progress

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • +1No license
    • +2Single-language instructions
    • +3Description length 642: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 50 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (5 of 5)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

    External checks

    ClawHub: suspicious
    This is a coherent local screencast tool, but its default workflow can delete unrelated files in the chosen folder and it stores login/session artifacts and private UI captures without strong handling guidance.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026