BF digest-builder
将聚合池中的原始候选内容转换为可判断的 Digest：优先从 FreshRSS 的未读列表经 Google Reader API 拉取候选，再执行 URL 去重、相似事件聚类、正文抓取检查、噪音过滤、摘要生成与初步排序。用于需要把一批原始 feed 条目或 FreshRSS 未读条目整理成结构化候选文档的场景。
As a process F 35/100 · Will not run — References files that are not bundled: 链接
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
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: 9. 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") - warning
missing-refreference to a missing file: 链接
Process rating: all ten parameters 35/100
Will not run. References files that are not bundled: 链接
- 0Tools and files. 1 referenced file(s) missing: 链接
- 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
- 100Steps. 81 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 656 tokens
- 100Running it twice. No mutating operations
- low 13 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 156: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 81 items
- +4Reference files are cited in the instructions (2 of 2)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.
External checks
ClawHub: clean
This appears to be a legitimate FreshRSS digest builder that uses an API password and saves feed content locally as part of its stated purpose.
LLM: benign (high) · VirusTotal: · 29 May 2026