SKILLEMALL.ai
GitHub ↗ RU Sign in

DC humanize-ai-text

Применять при переписывании текстов, сгенерированных LLM-агентами (отчеты, README, доки, письма, посты), в живой человеческий стиль. Триггеры - пользователь пишет 'убери AI-стиль', 'перепиши по-человечески', 'сделай естественно', 'убери воду', 'не как ChatGPT', 'убери LLM-штампы'; либо на входе текст с явными маркерами генерации: H2/H3 на каждый абзац, буллеты вместо прозы, штампы 'в современном мире', 'давайте погрузимся', избыток длинных тире, эмодзи-заголовки, обязательные 'надеюсь, это поможет!'. Сверх того ВСЕГДА проверяет технический регистр: в README, журнале изменений, документации и описаниях заменяет бытовую метафору на действие и предмет ('досыпает', 'кладет', 'копит', 'под капотом', 'из коробки', 'ядро библиотеки'); в письме, ответе и эссе эта проверка сама выключается по жанру, ключ отключения - --no-technical. Переписывание в живой стиль не применять к структурированным форматам, где списки и заголовки уместны по существу: API-документация, чек-листы, табличные данные, бенчмарки, юридические документы.

Desko77/claude-code-skills-1c Claude Code author: Desko77 MIT 7 files · 1 script body ≈ 6 541 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Применять при переписывании текстов, сгенерированных LLM-агентами (отчеты, README, доки, письма, посты), в живой человеческий стиль.

As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorWriting and documentstype 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
D
74/100
safety, quality, tests
Safety 60%
95
Quality 40%
43
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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.

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. Shorten the description to 1024 characters.
  3. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Edit

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1031 chars, limit 1024
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 6541 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 61/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 70Failures and branches. 7 branches
  • 70Execution cost. Instruction body is 6541 tokens
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 78 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 15 top-level sections: this looks like several domains in one skill

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 1031: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +4Structure: 21 headings
  • +3Step-by-step instructions: 78 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +3All 1 scripts are documented
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.