CC scrollcraft
Premium scroll-driven landing pages; scroll = timeline.
Premium scroll-driven landing pages; scroll = timeline.
As a process C 61/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
The same skill appears in 1 more place: hermes-agent
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
read-dotenvscripts/doctor.mjs:139Reads a .env file (quoted — discussed, not commanded)"Only needed to GENERATE imagery. Building from your own photos and footage needs no key and no spend. Copy .env.example to .env to set one.");
quoted
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 23 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 2878 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 tags): a typed call is more reliable
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)
- +3Description length 55: 120–800 characters recommended
- -2localhost URLs: will not work for another user
- -31 of 7 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 8 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 1 не дошёл до работы, и об их поведении мы ничего не узнали.
engine/scrollcraft.js | ничего за пределами своей папки |
scripts/doctor.mjs | ничего за пределами своей папки |
scripts/encode.sh | не запустился: ERROR: no full ffmpeg build found. Set SCROLLCRAFT_FFMPEG to one. |
scripts/kie.mjs | ничего за пределами своей папки |
scripts/serve.mjs | ничего за пределами своей папки |
scripts/shoot.mjs | ничего за пределами своей папки |
scripts/workspace.mjs | ничего за пределами своей папки |
scripts/worldflight-assert.mjs | ничего за пределами своей папки |
24 Sept 2026