AD build-execution-protocol
Systematic protocol for working through a project build queue (NEXT_TASKS.md). Use when a project has an ordered task list and you need to pick up, execute, verify, and hand off work across sessions. Triggers automatically when NEXT_TASKS.md exists in a project directory and Ray says "work on [project]", "continue the build", or "keep going". Ensures consistent quality, verification, and session handoff regardless of which session picks up the work. Mirrors the heartbeat enforcement pattern.
Systematic protocol for working through a project build queue (NEXTTASKS.md). Use when a project has an ordered task list and you need to pick up, execute…
As a process D 44/100 · 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: 2. 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 44/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (build-execution-protocol) differs from the folder (lucky-build-protocol)
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 85Steps. 93 steps, 3 vague phrases
- 100Execution cost. Instruction body is 3177 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 496: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 93 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.