BC web-search-rules
Search the web and save findings into your knowledge base with a source URL, date and quote attached to every claim. Works with Obsidian, NotebookLM, IMA, Feishu Docs and Tencent Docs. Use when a user asks to search the web, verify a current claim, evaluate sources, deduplicate results, manage source allow/deny rules, stage research for review, archive approved findings, or migrate research notes between local and cloud knowledge bases. Typical triggers include 帮我查一下, 这个说法现在还成立吗, verify this claim, find authoritative sources, 查最新政策/价格/版本, fact check, 整理搜索结果, 放进知识库, archive these sources, deduplicate my research, and check whether this AI summary is accurate. Covers provenance, freshness, claim-level evidence, untrusted metadata, single-source cross-checking, prompt-injection resistance, confirmations, and audit logs; it does not make a source trustworthy merely because its domain is allowed, and it does not treat a snippet, a search engine summary, or a file's embedded metadata as an opened and verified source.
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1026 chars, limit 1024
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 100Steps. 70 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2797 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 1026: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 70 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (11 of 11)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.