SKILLEMALL.ai
GitHub ↗ RU Sign in

CC skill-creator

Create, edit, evaluate, and optimize skills, including benchmarking and description tuning for better triggering.

CherryHQ/cherry-studio Agent Skills author: CherryHQ AGPL-3.0 18 files · 10 scripts body ≈ 8 595 tokens Open the sourcegithub.com↗ analyzed 13 d ago

Create, edit, evaluate, and optimize skills, including benchmarking and description tuning for better triggering.

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, execution cost

AnalyzerAI and agentsData and analyticsWriting 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
C
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
64
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Execution cost w 6
40
When it triggers w 12
50
the three weakest of ten parameters · all ten

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 · 0

✓ No critical or high findings

Files scanned: 18. 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 ≈ 8595 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 213): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 63/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 8595 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 60Steps. 83 steps, 9 vague phrases
  • 70Failures and branches. 4 branches
  • 100Result and completion. Output format and completion criterion are stated
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (12 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 113: 120–800 characters recommended
  • -36 of 9 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 35 headings
  • +3Step-by-step instructions: 83 items
  • +3Output format is stated explicitly
  • +4Has examples (15 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.

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 9 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

Из них 8 не дошли до работы, и об их поведении мы ничего не узнали.

eval-viewer/generate_review.pyне запустился: generate_review.py: error: the following arguments are required: workspace
scripts/aggregate_benchmark.pyне запустился: aggregate_benchmark.py: error: the following arguments are required: benchmark_dir
scripts/generate_report.pyне запустился: generate_report.py: error: the following arguments are required: input
scripts/improve_description.pyне запустился: improve_description.py: error: the following arguments are required: --eval-results, --skill-path, --model
scripts/package_skill.pyне запустился: Usage: python utils/package_skill.py <path/to/skill-folder> [output-directory]
scripts/quick_validate.pyне запустился: Usage: python quick_validate.py <skill_directory>
scripts/run_eval.pyне запустился: run_eval.py: error: the following arguments are required: --eval-set, --skill-path
scripts/run_loop.pyне запустился: run_loop.py: error: the following arguments are required: --eval-set, --skill-path, --model
scripts/utils.pyничего за пределами своей папки

29 Sept 2026