AC cloakclaw
Automatic privacy proxy for AI conversations. Redacts sensitive data (names, companies, financials, SSNs, emails, phones, addresses, API keys, IPs, passwords, and 14 more types) from documents before sending to cloud LLMs, then restores originals in the response. 24 entity types across 6 profiles (General, Legal, Financial, Email, Code, Medical). Use when: (1) user attaches a document (PDF, TXT, etc.), (2) user pastes sensitive text, (3) user mentions contracts, financials, HR docs, medical, or legal documents, (4) user explicitly asks for privacy/cloaking. Always-on by default. Requires: Node.js 22+, CloakClaw installed (`npm install -g cloakclaw`). Optional: Ollama for name/company detection (works without in regex-only mode). Optional: poppler for better PDF extraction (`brew install poppler`).
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
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 · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "install"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 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
- 30Running it twice. 5 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1090 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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)
- +3Description length 808: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (8 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.