SKILLEMALL.ai
GitHub ↗ RU Sign in

BC run-coach

Science-based running coach via Telegram. Logs training, sends visual training plans as HD photo albums, and coaches with evidence-driven discipline — never nags, never asks for data it already has. Optional Garmin sync collects health metrics (HR, stress, Body Battery, VO2max) stored locally only; credentials and session tokens live in chmod-600 dotfiles — see the Data & privacy section.

ClawHub Agent Skills author: LeoYann v1.1.6 MIT-0 11 files · 2 scripts body ≈ 1 629 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceTelegramData and analyticsInfrastructuretype 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
84/100
safety, quality, tests
Safety 60%
91
Quality 40%
73
Run on models
none yet
Process rating
C
51/100
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.
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 · 5

✓ No critical or high findings

Medium and low: 5
  • medium Broad scope meta-agent-memory-dump MEMORY.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    MEMORY.md
  • low Dangerous commands cmd-privilege training/screenshot.mjs:41
    Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
    args: ['--no-sandbox', '--disable-setuid-sandbox']
    detectorcode literal
  • low Exfiltration exfil-webhook-url training/send-album.mjs:31
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    const API = `https://api.telegram.org/bot${botToken}`;
    placeholder
  • low Exfiltration exfil-webhook-url training/text-to-image-canvas.mjs:162
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    const res = await fetch(`https://api.telegram.org/bot${BOT_TOKEN}/sendPhoto`, {
    placeholder
  • low Exfiltration net-credential-use training/text-to-image-canvas.mjs:162
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    const res = await fetch(`https://api.telegram.org/bot${BOT_TOKEN}/sendPhoto`, {
    vendor-host

Files scanned: 11. 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")

Process rating: all ten parameters 51/100

  • 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
  • 30Running it twice. 10 mutating operations with no state check
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 100Steps. 11 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1629 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +2Single-language instructions
  • +3Description length 391: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (3 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: clean
This running-coach skill uses Telegram and optional Garmin data in ways that match its stated purpose and are clearly disclosed.
LLM: benign (high) · VirusTotal: · 20 Aug 2026