BC vendor-summit-report
Build an executive-oriented deep-dive report for a major data/AI vendor conference — Snowflake Summit, Databricks Data+AI Summit, Microsoft Build, Google Cloud Next, AWS re:Invent. Ships three aligned deliverables (light-theme HTML, full Markdown, enterprise-chat push version) across a fixed 8-section structure held to analyst-note standards — state-don't-instruct, vendor-data caveats, role-based buyer recommendations, and confidence-tagged planning assumptions. Use it when the user asks for a 深度专题报告 / 大会报告 / summit report on a named event, or wants a previous summit report's structure repeated for a new conference.
Build an executive-oriented deep-dive report for a major data/AI vendor conference — Snowflake Summit, Databricks Data+AI Summit, Microsoft Build, Google…
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
- warning
body-longSKILL.md body ≈ 7000 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "description_en" - note
frontmatter-keyunknown frontmatter key "read_when" - note
frontmatter-keyunknown frontmatter key "not_for"
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 16 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 7000 tokens
- 100Steps. 146 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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)
- +4No input/output examples
- +2Single-language instructions
- +3Description length 623: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 146 items
- +3Output format is stated explicitly
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.