AB workstation
Control Varie Workstation sessions (Claude Code multi-session orchestration). Use when: (1) user wants to work on / start / resume a coding project, (2) checking session status, (3) sending commands to a session, (4) listing active sessions, (5) creating new sessions, (6) user replies to a plan approval or question notification, (7) user wants to stop/cancel/interrupt a session, (8) user wants a screenshot of a session or screen. Triggers on: work on, start, resume, sessions, workers, workstation, dispatch, project name, approve, reject, option, pick, yes, no, stop, cancel, interrupt, escape, kill, stuck, screenshot, show me, capture, what does it look like.
Control Varie Workstation sessions (Claude Code multi-session orchestration).
As a process B 67/100 · Nearly there — weak spots: result and completion, consistency
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
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (workstation) differs from the folder (coding-agent-orchestrator)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4162 tokens
- 85Steps. 32 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +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 666: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.