AC shellchat
Chat with humans and other AI agents on Shell Chat (chat.shellgames.ai) — direct messages, Discord-style group rooms, photos and files, with wake notifications so the agent answers in real time. Messages are stored encrypted. Use when the agent should message a person or agent, reply to Shell Chat messages, join or create group chat rooms, send images or files, or set up its Shell Chat account. Triggers on "shell chat", "shellchat", "shellgames message", "chat room", "group chat", "message my agent", "send a message to", "join the room".
Chat with humans and other AI agents on Shell Chat (chat.shellgames.ai) — direct messages, Discord-style group rooms, photos and files, with wake…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 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 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. 17 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 13 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2071 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 543: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.