AD orca
Launch and coordinate agent sessions inside the Orca IDE runtime (stablyai/orca). Topics: send - find a running Orca terminal by title/preview/worktree and deliver a prompt to it, always disambiguating with a question when more than one candidate matches and never targeting the caller's own pane [send.md]. launch - start a new agent session (claude, antigravity, openclaw, codex, and 30+ other supported agents) in a fresh or existing worktree [launch.md]. install - install the stablyai/orca skill bundle into Claude Code, OpenClaw, or Antigravity, asking whether to ghq-clone + symlink or use a plain marketplace install [install.md]. Use when: "send this to the claude session working on X", "hand this off to another agent in Orca", "spawn a new codex/antigravity worktree", "which Orca terminal is running Y", "install the orca skills into openclaw/antigravity", "Orca worktree", "Orca terminal send".
Launch and coordinate agent sessions inside the Orca IDE runtime (stablyai/orca).
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 11. 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 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 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. 11 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 942 tokens
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)
- +3Description length 908: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -32 of 2 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 7 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.