SKILLEMALL.ai
GitHub ↗ RU Sign in

BD knowledge-base-pro

> Corporate knowledge brain for Russian-speaking teams. Replaces HR onboarding department + internal communications team on 40-60% of routine. FAQ bot, role-based onboarding, SOP templates, smart search with filters, built-in gap analysis, knowledge audit. 14 modes in one skill. Works from day one — no external SaaS required. Battle-tested inside RAAI. Saves 10-25K RUB per new hire in onboarding costs. Russian language native. 5 proof cases with ruble ROI numbers. Корпоративный мозг компании — заменяет HR-онбординг + отдел внутренней коммуникации на 40-60% рутины. FAQ-бот, онбординг по ролям, регламенты/SOPs, умный поиск, gap-анализ пробелов знаний, аудит базы — 14 режимов в одном скилле. Работает сразу без внешнего SaaS (Guru, Botpress не нужны). Экономит 25К ₽+ на каждом новом сотруднике. 5 кейсов с рублёвыми цифрами. Русский язык нативно. Единственный KB-скилл для OpenClaw с полной RU-локализацией.

ClawHub Agent Skills author: RAAIPRO v3.5.3 MIT-0 36 files · 3 scripts body ≈ 13 981 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedurePeople and hiringCustomer supportInfrastructuretype 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
B
78/100
safety, quality, tests
Safety 60%
100
Quality 40%
44
Run on models
none yet
Process rating
D
45/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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: 35. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Not a YAML token: Corporate knowledge brain for Russian-speaking teams. Replaces HR onboarding department + internal communications team on 40-60% of routine. FAQ bot, role-based onboarding, SOP templates, smart search with filters, built-in gap analysis, knowledge audit. 14 modes in one skill. Works from day one — no external SaaS required. Battle-tested inside RAAI. Saves 10-25K RUB per new hire in onboarding costs. Russian language native. 5 proof cases with ruble ROI numbers. Корпоративный мозг компании — заменяет HR-онбординг + отдел внутренней коммуникации на 40-60% рутины. FAQ-бот, онбординг по ролям, регламенты/SOPs, умный поиск, gap-анализ пробелов знаний, аудит базы — 14 режимов в одном скилле. Работает сразу без внешнего SaaS (Guru, Botpress не нужны). Экономит 25К ₽+ на каждом новом сотруднике. 5 кейсов с рублёвыми цифрами. Русский язык нативно. Единственный KB-скилл для OpenClaw с полной RU-локализацией. at line 5, column 16: description: > Corporate knowledge brain for Russian-speaking teams. Replaces H… ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 13981 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "triggers"
  • note frontmatter-key unknown frontmatter key "target_audience"
  • note frontmatter-key unknown frontmatter key "price"
  • note frontmatter-key unknown frontmatter key "price_currency"
  • note frontmatter-key unknown frontmatter key "dogfooded_in"
  • note frontmatter-key unknown frontmatter key "differentiators"

Process rating: all ten parameters 45/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (knowledge-base-pro) differs from the folder (raai-knowledge-base-pro)
  • 40Execution cost. Instruction body is 13981 tokens: crowds the task out of the window
  • 100Tools and files. No external tools needed
  • 100Steps. 48 steps
  • 100Running it twice. No mutating operations

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 914: 120–800 characters recommended
  • +4Structure: 0 headings, hard to scan
  • +3Output format is not stated: the model decides each time
  • -5Long text without headings
  • +3Step-by-step instructions: 48 items
  • +4Has examples (23 code blocks)
  • +4Reference files are cited in the instructions (1 of 3)
  • +1License stated
  • +2Bilingual instructions (RU + EN)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 44.

External checks

ClawHub: suspicious
This appears to be a legitimate knowledge-base skill, but it under-discloses networked indexing, query logging, exports, and record-changing actions that can affect internal company data.
LLM: suspicious (high) · VirusTotal: · 29 May 2026