SKILLEMALL.ai
RU Sign in

B shieldcortex

Memory and defence for AI agents: semantic recall, knowledge graph and decay, plus a memory firewall that scans and enforces against prompt injection, credential leaks and poisoning.

ClawHub Agent Skills author: jarvis-drakon v4.54.15 MIT-0 10 files body ≈ 6 318 tokens open source ↗ analyzed 27 h ago
ProcedureAI and agentsInfrastructuretype 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
B
84/100
Overall score
Safety 60%
100
Quality 40%
59
Tests bonus
0

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): it is the main trigger signal.
  2. The SKILL.md body exceeds 5,000 tokens: move reference detail into references/ and load it on demand.
  3. Add evals/evals.json with 4–6 real requests and expected answers: the full check will then use your cases instead of a model draft.
  4. Add a spec.yaml with triggers and assertions (skilltest init): the behaviour contract for CI.

Guard findings · 0

✓ No critical or high findings

Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

Lint

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 6318 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "install"
  • note frontmatter-key unknown frontmatter key "permissions"

Process maturity 56/100

  • 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
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 70Execution cost. Instruction body is 6318 tokens
  • 100Steps. 56 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 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 (3 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)
  • +3Output format is not stated: the model decides each time
  • -230 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +3Description length 182: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 56 items
  • +4Has examples (9 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.

External checks

ClawHub: clean
This is a disclosed local-first memory and security integration with meaningful privacy considerations, but the inspected artifacts do not show hidden exfiltration or malicious behavior.
LLM: benign (medium) · VirusTotal: · 1 Sept 2026