AC speechcanvas-free-expression-swarm
Four-agent image-prompt swarm (Muse drafts, Guardian safety-checks, Critic perfects realism, Composer finalizes) that produces lawful, consent-aware, non-deceptive symbolic imagery prompt packs as validated JSON for journalism, protest, censorship and free-expression themes. Use when the operator asks for a symbolic image or image prompt about protest, censorship, propaganda, press freedom, or free expression.
Four-agent image-prompt swarm (Muse drafts, Guardian safety-checks, Critic perfects realism, Composer finalizes) that produces lawful, consent-aware…
As a process C 55/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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
-
medium Obfuscation
uni-mixed-script-wordscripts/safety_validator.py:221Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (2 occurrences)("fаke pаssport in the drawer", "block"), # Cyrillic homoglyph bypass
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "topics"
Process rating: all ten parameters 55/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1420 tokens
- 100Running it twice. No mutating operations
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -31 of 4 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 413: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 20 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.