CD parallel-work
Shapes for running many sub-agents at once — fan-out with a barrier, maker/checker, generate-and-filter, tournaments for ranking, hypothesis fan-out for root cause, and loops that stop on a condition with a cap. Use when a phase has several independent targets, when a task is too large or too repetitive for one window, when the same edit applies across many files, when ranking or judging a large set, when several hypotheses compete, or when work must repeat until a signal says stop. Does not apply when units depend on each other's results or the cause is still unknown — investigate first, then parallelize.
Shapes for running many sub-agents at once — fan-out with a barrier, maker/checker, generate-and-filter, tournaments for ranking, hypothesis fan-out for root…
As a process D 49/100 · Unfinished process — References files that are not bundled: ../delegate/references/harness-notes/claude-code.md, ../delegate/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../delegate/references/harness-notes/claude-code.md - warning
missing-refreference to a missing file: ../delegate/SKILL.md
Process rating: all ten parameters 49/100
- 0Tools and files. 2 referenced file(s) missing: ../delegate/references/harness-notes/claude-code.md, ../delegate/SKILL.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 929 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 613: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 5 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.