SKILLEMALL.ai
GitHub ↗ RU Sign in

BC engram-brain

Native local memory for OpenClaw agents: Capture, Cue, Project, Recall, and Consolidate conversations into a private Helix-backed brain.

ClawHub Agent Skills author: Moshik21 v0.3.5 MIT-0 2 files body ≈ 3 201 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

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
Technical rating
B
77/100
safety, quality, tests
Safety 60%
89
Quality 40%
59
Run on models
none yet
Process rating
C
61/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
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.

Dangerous commands 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:31
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -sSL https://raw.githubusercontent.com/Moshik21/engram/main/scripts/install.sh | bash -s -- openclaw
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:74
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -sSL https://raw.githubusercontent.com/Moshik21/engram/main/scripts/install.sh | bash -s -- full
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:7
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    metadata: {"openclaw":{"requires":{"anyBins":["curl"]},"envVars":[{"name":"ANTHROPIC_API_KEY","required":false,"description":"Optional richer entity extraction; deterministic extraction works without
    quoted

Files scanned: 2. 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: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Native local memory for OpenClaw agents: Capture, Cue, Project, Re… ^ ); 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")
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 61/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 3 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 24 steps
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3201 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 136: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 24 items
  • +4Has examples (22 code blocks)

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

External checks

ClawHub: suspicious
This is a real local memory integration, but it asks for broad persistent memory, background services, and an unpinned remote installer that changes local OpenClaw configuration.
LLM: suspicious (high) · 22 Jul 2026