AC qrclaw
Generate QR codes for any string or URL using the QRClaw open source service (qrclaw.goplausible.xyz). Use this skill whenever the user asks to create a QR code, generate a scannable code, share a link as a QR, make something scannable, or needs a visual/terminal-friendly QR representation of text or URLs. Also use when the user says 'make a QR', 'QR code for this', 'generate QR', 'scannable link', or wants to share content via QR. Covers both terminal (UTF-8 block characters) and web (image smart link) output formats.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
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 Risky intent
intent-wallet-secretsSKILL.md:21Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target**Before generating a QR code, check that the input does not contain sensitive material.** If the input looks like it could be a secret (e.g., starts with `sk_`, `AKIA`, contains `password=`, looks li
Files scanned: 2. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 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
- 100Steps. 34 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1551 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 524: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.