SKILLEMALL.ai
GitHub ↗ RU Sign in

CB slides-generator

Презентация-дек из MD-файла — однофайловый HTML в тёмном минимал-стиле с упором на визуал: на каждом слайде свой анимированный SVG-арт под смысл (библиотека из 134 мотивов + 25 иконок), 4-цветная палитра (зелёный+янтарь UI / синий+фиолетовый арт), баланс 50/50 текст+визуал, 6 пресетов структуры (webinar, pitch, report, workshop, strategy, course), каркас сессии с цветными разделителями блоков. Триггеры: "сделай презентацию", "собери слайды", "создай дек", "сгенерируй HTML-слайды", "презентация из этого файла", /slides-generator <путь к MD>; страница настроек — /slides-generator config | setup.

alexivanovvv/turboskills Agent Skills author: alexivanovvv MIT 13 files · 6 scripts body ≈ 18 003 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Презентация-дек из MD-файла — однофайловый HTML в тёмном минимал-стиле с упором на визуал: на каждом слайде свой анимированный SVG-арт под смысл (библиотека…

As a process B 72/100 · Nearly there — weak spots: result and completion, execution cost, running it twice

GeneratorWriting and documentsData and analyticsDesigntype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
79/100
safety, quality, tests
Safety 60%
89
Quality 40%
65
Run on models
none yet
Process rating
B
72/100
Nearly there
Result and completion w 14
0
Execution cost w 6
10
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Obfuscation uni-mixed-script-word publish.py:9
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    `netlify deploy --dir published` заменяет весь сайт, поэтому published/ хранит ВСЕ деcки.
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Bash Write Edit
  • low Dangerous commands cmd-persistence SKILL.md:347
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (security demo / example; quoted — discussed, not commanded)
    - Сервер можно держать запущенным постоянно (опционально, macOS): LaunchAgent с `settings.py --no-open` (например `~/Library/LaunchAgents/<you>.slides-generator-settings.plist`, лог `/tmp/slides-gener
    demoquoted

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 18003 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 72/100

  • 0Result and completion. Does not say what the result is
  • 10Execution cost. Instruction body is 18003 tokens: crowds the task out of the window
  • 30Running it twice. 10 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 130 steps
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 23 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (33 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

  • +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
  • -212 emoji in the instructions: noise for the model
  • +1No license
  • +5Description quotes 5 example trigger phrases
  • +3Description length 600: enough signal without eating the budget
  • +4Structure: 40 headings
  • +3Step-by-step instructions: 130 items
  • +4Has examples (11 code blocks)
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.