CD implement-feature
Use when the plan_ref returned by add-new-feature is provided. Executes the SAM implementation loop — opens an attempt per ready task, dispatches each to a specialist agent in parallel, settles and judges what comes back, manages bookend tasks (T0 baseline capture and TN verification), and tracks concerns and contract violations per task. Drives task state through the work ledger via the SAM CLI.
Executes the SAM implementation loop — opens an attempt per ready task, dispatches each to a specialist agent in parallel, settles and judges what comes back…
As a process D 46/100 · Unfinished process — References files that are not bundled: ../../docs/work-ledger/work-loop.md, ../work-milestone/SKILL.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5008 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../../docs/work-ledger/work-loop.md - warning
missing-refreference to a missing file: ../work-milestone/SKILL.md
Process rating: all ten parameters 46/100
- 0Tools and files. 2 referenced file(s) missing: ../../docs/work-ledger/work-loop.md, ../work-milestone/SKILL.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 23 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Execution cost. Instruction body is 5008 tokens
- 85Steps. 34 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- +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 399: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.