AB clawsouls
Manage AI agent personas (Souls) for OpenClaw, Hermes Agent, ZeroClaw, and other agents that use Soul Spec workspace files (SOUL.md, IDENTITY.md, AGENTS.md). Installs/switches/restores persona files in the agent workspace, searches and publishes to the clawsouls.ai registry (network + token auth), optionally syncs encrypted agent memory via Git (explicit `sync`/`swarm` commands only), and detects the local agent platform. Use only when the user explicitly asks to manage personas — e.g. "install a soul", "switch persona to X", "list souls", "restore my previous soul", "publish my soul", or "login to clawsouls". Workspace-modifying and publishing actions should be confirmed with the user first.
As a process B 67/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitySKILL.md:149Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Security**: 53 pattern checks (prompt injection, code execution, XSS, data exfiltration, privilege escalation, social engineering, harmful content, secret detection)
detector
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 21 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 48 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2909 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 701: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (21 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.