BD workflow-ship-change
Ship every change the way the user requires, with the guardrails. Take screenshots of the start, the key moment and the result; give the change its own changelog version with pictures; verify with tests; commit only your own files; merge with the latest main and push as a fast-forward; publish that exact main live; confirm each step; and report measured sizes, asking before any upload over 50 MB. Use at the end of every change (feature, fix, tweak, art, balance, polish) and whenever the user says "ship it", "commit", "push", "merge", "publish", "deploy", "go live" or "update the changelog". Project specifics (hosting, the changelog pipeline, merge conflicts) go in an optional local references/<project>.md next to this skill.
Ship every change the way the user requires, with the guardrails.
As a process D 49/100 · Unfinished process — References files that are not bundled: references/<project>.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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/<project>.md
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: references/<project>.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 48 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 68 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1875 tokens
- 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
- +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
- +5Description quotes 6 example trigger phrases
- +3Description length 734: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 68 items
- +4Has examples (0 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.