SKILLEMALL.ai

BF open-persona

Meta-skill for building and managing agent persona skill packs (instruction-only; no bundled installer or auto-downloaded binaries). Credentials are never written into generated packs by the framework; publish/ACN/register require explicit user CLI. Use when the user wants to create a new agent persona, install/manage existing personas, or publish persona skill packs to OpenPersona.

ClawHub Agent Skills author: neil v0.22.0 MIT-0 10 files body ≈ 9 744 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 57/100 · Will not run — References files that are not bundled: scripts/state-sync.js, scripts/economy-hook.js

GeneratorAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
95
Quality 40%
70
Run on models
none yet
Process rating
F
57/100
Will not run
References files that are not bundled: scripts/state-sync.js, scripts/economy-hook.js
Tools and files w 18
0
Result and completion w 14
0
Execution cost w 6
40
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.

Broad scope 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 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.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-agent-memory-dump references/HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    references/HEARTBEAT.md

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

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9744 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/state-sync.js
  • warning missing-ref reference to a missing file: scripts/economy-hook.js

Process rating: all ten parameters 57/100

Will not run. References files that are not bundled: scripts/state-sync.js, scripts/economy-hook.js
  • 0Tools and files. 2 referenced file(s) missing: scripts/state-sync.js, scripts/economy-hook.js
  • 0Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 9744 tokens: crowds the task out of the window
  • 70When it triggers. States when to use, but not when not to
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 90 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 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (39 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
  • +2Single-language instructions
  • +3Description length 385: enough signal without eating the budget
  • +4Structure: 48 headings
  • +3Step-by-step instructions: 90 items
  • +4Has examples (13 code blocks)
  • +4Reference files are cited in the instructions (8 of 8)
  • +1License stated

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

External checks

ClawHub: clean
This instruction-only persona manager is broadly disclosed and purpose-aligned, but users should review optional proactive memory, workspace, calendar, publishing, and external CLI features before enabling them.
LLM: benign (high) · VirusTotal: · 19 Jul 2026