AC foreman
Dispatch-and-acceptance control desk for farming coding work out to background agents. Probes which worker backend is actually usable, gives each task its own git worktree, sends it to a worker agent via the handoff CLI, takes delivery only as a real commit inside a path whitelist, then gates the merge behind an acceptance protocol whose core rule is that the builder may never touch the tests, assertions, or CI config that judge it. Be aware before using it — it sends repository content to the worker backends you configure; its probes read your local agent login status and may make one minimal request to a backend; and the optional caged worker starts a Docker container, passes DEEPSEEK_API_KEY into it, and lets the worker skip permission prompts inside that container. Use it when batching implementation work out to background agents, or when accepting code that someone else — human or agent — built.
Dispatch-and-acceptance control desk for farming coding work out to background agents.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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: 10. 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
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 4 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1259 tokens
- 100Progress reporting. Reports progress
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 913: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 4 headings
- +3Step-by-step instructions: 16 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.