BC research-decision
对复杂问题进行联网调研，并基于高质量信源输出判断、建议、排查方向或下一步动作。适用于技术选型、方案对比、版本升级、兼容性判断、架构取舍、社区口碑调研、已知问题排查、疑难 bug 冲突分析，以及其他需要上网查证、多方比较、最后给出建议或方向的问题。优先进行中英文双语检索，重视官方文档、官方博客、GitHub issues/discussions/changelog/release notes，再补充社区讨论与第三方资料。重点是信源管理、交叉验证、识别已知问题和处理冲突信息。
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
ReferenceGitHubInfrastructureWriting and documentstype and topics are labelled automatically from the skill text
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 110 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 874 tokens
- 100Running it twice. No mutating operations
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 238: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 110 items
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.
External checks
ClawHub: clean
This appears to be a research/troubleshooting skill with read-only local checks and web research behavior that is mostly purpose-aligned, but users should be aware it may reveal software inventory and search topics.
LLM: benign (medium) · VirusTotal: · 29 May 2026