AC alter
Build and run a digital persona of the user, their alter ego. Interviews them through chat and voice memos, learns from their documents, writing samples, and AI chat exports from OpenAI or Claude, then chats, answers questions, and drafts messages and emails in their voice, values, and style. Improves continuously from corrections and new uploads, and asks for clarification when it finds contradictions. Use when the user wants to create a persona of themselves, talk to their persona, add material to it, correct it, check its progress, or have something drafted the way they would write it.
Build and run a digital persona of the user, their alter ego.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 595 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 19 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1424 tokens
- 100Progress reporting. Reports progress
- 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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 595: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 19 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.