BC ai-persona-os
The complete operating system for OpenClaw 5.x agents. Built-in memory tool integration (memory_search, memory_get, DREAMS.md), Discord channel-routing fixes (configure Discord + route check), zero-terminal agent-driven setup, 24-soul gallery (11 originals + 13 iconic characters), SOUL.md Maker, in-chat commands, ambient context monitoring, enforced heartbeat protocol with 🟢🟡🔴 indicators, MEMORY.md auto-pruning, structured escalation, security inoculation, never-forget context protection, 8 operating rules, and 4 growth loops.
As a process C 61/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Broad scope
meta-agent-memory-dumpexamples/coding-assistant/HEARTBEAT.mdAgent memory / workspace files bundled with the skill (6) — likely a workspace dump with personal data or tokensexamples/coding-assistant/HEARTBEAT.md, examples/coding-assistant/SOUL.md, examples/executive-assistant/HEARTBEAT.md, examples/executive-assistant/SOUL.md, examples/marketing-assistant/HEARTBEAT.md
-
low Risky intent
intent-offensive-securityexamples/prebuilt-souls/01-contrarian-strategist.md:60Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)**Red Team Mode:** If [HUMAN] says "red team this" — go full adversarial. Find every way this plan fails. No mercy, no softening. This is a feature, not a bug.
fixture -
low Risky intent
intent-offensive-securitySECURITY_NOTE.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Reality:** The command **only greps for routing-related keys** (`default`, `defaultAccount`, `target`, `requireMention`). The `gateway.auth.token` is in the same file but is **never read, displaye
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 69. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 16959 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 10Execution cost. Instruction body is 16959 tokens: crowds the task out of the window
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 91 steps
- 100Failures and branches. 29 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 38 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (33 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)
- -4Absolute local paths (C:\Users, /home/…): not portable
- -280 emoji in the instructions: noise for the model
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 535: enough signal without eating the budget
- +4Structure: 79 headings
- +3Step-by-step instructions: 91 items
- +3Output format is stated explicitly
- +4Has examples (46 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.