AD link-library
Personal knowledge base that captures web content (articles, tweets/threads, videos, podcasts, images, PDFs) and makes it retrievable for future conversations and writing. Use when: (1) User shares a URL with ANY interest signal — asking to summarize, commenting positively, saying "有意思/不错/interesting/值得看/学到了", or requesting it be saved, (2) User asks to find previously saved content ("我之前存的那篇...", "find that article about..."), (3) User needs reference material for writing or discussion, (4) User shares Twitter/X, WeChat, YouTube, Bilibili, or any web link and engages with it. Interest signals that trigger save: "帮我总结一下", "这篇不错", "有意思", "记一下", "留着以后用", "这个观点很好", "学到了", "值得保存", "放进知识库", sharing link + any commentary or opinion, asking follow-up questions about link content. Do NOT require literal "save"/"bookmark" keywords.
As a process D 49/100 · Unfinished process — 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: 8. 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 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1489 tokens
- low 11 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 834: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.