AB daily-workflow
Say 开工啦 or 收工啦 and get a resumable project note written for you, so tomorrow you or another AI can pick up without re-reading everything. Use when a user asks to resume a project, save progress, record a checkpoint, end a work session, prepare a handoff, switch to a new AI session, or reconcile stale working notes. Typical triggers include 开工啦, 中段检查, 吃饭啦, 收工啦, 交接, 记一下进度, 存个档, 明天接着做, 换个 AI 继续, 上下文快满了, start work, checkpoint, wrap up, handoff, save progress, resume tomorrow, and switch to a new agent session. Reads existing project authority first, preserves dirty worktrees and governance evidence, avoids competing state files, archives rather than deletes history, and records commands, final outcomes, blockers, risks, and exact next actions without claiming unverified completion or QA acceptance.
As a process B 73/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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: 5. 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 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 15 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Failures and branches. 5 branches
- 100Tools and files. No external tools needed
- 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 2526 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
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)
- +3Description length 806: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 68 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.