AC proactive-do
Proactive todo execution, heartbeat-driven review, and structured follow-up for a markdown todo system. Use when the agent needs to review `todo/todo.md`, pick the top 3 `[new]` items, do tasks that look doable within about 1 hour, draft simple plans for tasks likely to take over 1 hour, update `[new|wip|done]` labels, maintain per-task journals under `agent_work/`, reconcile work after about 2.5 hours, and send concise start/finish reports by email instead of chat. Strong triggers include: heartbeat prompts, system events mentioning `todo/todo.md`, `[new]` / `[wip]` / `[done]`, "proactive-do", "review todos", "pick top 3", "do it now if under 1 hour", "draft a plan", "reconcile statuses", and "agent_work" journals.
As a process C 63/100 · Has gaps — 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: 3. 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 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 22 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 92 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2061 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 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 725: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 92 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.