SKILLEMALL.ai
GitHub ↗ RU Sign in

CB dossier

Досье на конкретного живого человека перед деловой встречей или переговорами: поиск волнами по открытым источникам, порог подтверждения по силе источника, машинная проверка каждого числа, триангуляция фактов через Perplexity Sonar и детерминированная вёрстка в Word (Arial 12, две страницы) плюс тот же текст в чате.

ClawHub Agent Skills author: Sergey Petrakov v1.0.6 MIT-0 7 files · 4 scripts body ≈ 14 880 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

Досье на конкретного живого человека перед деловой встречей или переговорами: поиск волнами по открытым источникам, порог подтверждения по силе источника…

As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, execution cost

AnalyzerResearchPeople and hiringtype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
C
83/100
safety, quality, tests
Safety 60%
95
Quality 40%
65
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
When it triggers w 12
20
Execution cost w 6
40
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.

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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Obfuscation uni-mixed-script-word scripts/verify_facts.py:484
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (2 occurrences)
    words = re.findall(r"[А-Яа-яЁёA-Za-z][А-Яа-яЁёA-Za-z-]+", str(text or "").lower())

Files scanned: 7. 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 ≈ 14880 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "type"
  • note frontmatter-key unknown frontmatter key "runtime"
  • note frontmatter-key unknown frontmatter key "timeout_sec"
  • note frontmatter-key unknown frontmatter key "permissions"
  • note frontmatter-key unknown frontmatter key "env_from_settings"
  • note frontmatter-key unknown frontmatter key "dependencies"
  • note frontmatter-key unknown frontmatter key "scripts"

Process rating: all ten parameters 67/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 40Execution cost. Instruction body is 14880 tokens: crowds the task out of the window
  • 60Result and completion. Output format stated, no completion criterion
  • 70Failures and branches. 17 branches
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 71 steps
  • 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 14 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)
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +3Description length 316: enough signal without eating the budget
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 71 items
  • +4Has examples (17 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 4 scripts are documented
  • +1License stated
  • +2Bilingual instructions (RU + EN)

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

External checks

ClawHub: suspicious
This skill is not clearly malicious, but it deserves review because it broadly creates dossiers on living people, sends personal research data to a third-party API, persists search/query artifacts, and fetches cited URLs without strong network scoping.
LLM: suspicious (high) · 28 Sept 2026