SKILLEMALL.ai
GitHub ↗ RU Sign in

CC pulse

Defining KPIs, tracking events, and dashboards: North Star Metric, funnel and cohort analysis, test-intelligence views. GA4/Amplitude/Mixpanel/PostHog. Use when metrics design is needed.

Not recommendedcritical or high security findings
simota/agent-skills Agent Skills author: simota 15 files body ≈ 6 028 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Defining KPIs, tracking events, and dashboards: North Star Metric, funnel and cohort analysis, test-intelligence views.

As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice

ProcedureGoogle AnalyticsData and analyticstype 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
69/100
safety, quality, tests
Safety 60%
64
Quality 40%
77
Run on models
none yet
Process rating
C
62/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  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 · 2

  • high Exfiltration intent-browser-credential-store reference/funnel-cohort-analysis.md:5
    Accesses a browser credential / cookie store
    With third-party cookies still present in Chrome (Google's **2025-04-22** cancellation of TPC deprecation) but Privacy Sandbox APIs **retired 2025-10-17** (Topics, Protected Audience, Attribution Repo
  • high Exfiltration intent-browser-credential-store reference/privacy-consent.md:16
    Accesses a browser credential / cookie store
    Tactical posture for 2026: assume third-party cookies persist in Chrome, but treat them as legally hazardous (GDPR/ePrivacy still applies). Default to server-side first-party tracking + Consent Mode v

Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6028 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 62/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 19 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 65Failures and branches. 3 branches
  • 70Execution cost. Instruction body is 6028 tokens
  • 100Steps. 116 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 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)
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 186: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 116 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (14 of 14)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.