AB agent-essentials
Meta-skill for capability expansion and cautious self-improvement. USE WHEN (a) a request suggests a missing capability, external platform support, workflow automation, integration work, or any reusable process that may benefit from skill discovery before giving up — common phrases include "automate X", "integrate with X", "support X platform", "帮我自动化X", "对接X", "做一个工具来X"; OR (b) a meaningful failure, user correction, recurring mistake ("again", "this is the Nth time", "又错了", "这是第N次了"), or better workflow should be captured and routed into a durable file (AGENTS.md / TOOLS.md / USER.md / SOUL.md). DO NOT use for one-off questions or trivial noise.
As a process B 66/100 · 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: 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 66/100
- 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. 4 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 30 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1195 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (5 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 654: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.