CF html-reel
Turn a tweet, a video, a YouTube video or a landing page into a 9:16 reel (Instagram Reels, TikTok, Shorts) that says what the source says and looks like it, with every cut on a word. Read the source (its words, its media, its measured fonts and colours), pick a structure (a promo, a showcase, "found this", an explainer, before and after), write the script in the creator's voice from the source's own facts, make the voice with timestamps (their cloned ElevenLabs voice), then build the picture from HTML scenes drawn from one clock (window.__frame(t)) in the source's look, opening on its cover (the hook's best moment as the first frame), its demo video framed and cut to words, and assemble it in Fil's video editor over MCP. The creator is in it from the first draft as a placeholder in the camera layouts (a backlit studio silhouette) (full frame, a bubble, half the frame), swapped for their phone takes when they record, and everything retimed to their own words by word anchors, t = W(τ); a reel can also be faceless. Use when someone wants a reel, a short or a vertical video from a post, a thread, a launch, a landing page, a demo video or a YouTube video, "a reel like this one", or a talking-head promo cut to their own delivery.
Promises to turn a tweet, video, or landing page into a vertical reel: cut by word, clone the source's voice, match its design. Sounds like automating a video editor's job.
Checks show it's rougher. Code quality 49/100, process score 31/100—numbers that speak for themselves. Files exist (28), but links are broken, scripts didn't run on models. The description is long and vague: unclear if it actually cuts by word or just slices video, how voice cloning works (does it need user data?), whether landing pages work at all. No critical errors found, but no proof of function either.
Don't install. This is a sketch, not a tool.
Turn a tweet, a video, a YouTube video or a landing page into a 9:16 reel (Instagram Reels, TikTok, Shorts) that says what the source says and looks like it…
As a process F 31/100 · No process to follow — References files that are not bundled: scripts/reel-clock.css, scripts/cursors/
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1244 chars, limit 1024 - warning
body-longSKILL.md body ≈ 6560 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/reel-clock.css - warning
missing-refreference to a missing file: scripts/cursors/
Process rating: all ten parameters 31/100
- 0Tools and files. 2 referenced file(s) missing: scripts/reel-clock.css, scripts/cursors/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 70Execution cost. Instruction body is 6560 tokens
- 100Steps. 82 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1244: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 8 headings
- +3Step-by-step instructions: 82 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +3All 18 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.