CD vendor-summit-report
Build an executive-oriented deep-dive industry report for a major data/AI vendor conference (e.g. Snowflake Summit, Databricks Data+AI Summit / DAIS, Microsoft Build, Google Cloud Next, AWS re:Invent). Use this when the user wants a "深度专题报告" / "专题报告" / "summit report" / "大会报告" for a vendor event, especially as a follow-up to a previous one (e.g. "等 databricks 大会过后用这个做报告"). Produces three aligned deliverables — light-theme HTML, full Markdown, and a WeCom (企微) push version — using a fixed 8-section structure optimized for an industry-insider / executive reader, held to Gartner/Forrester analyst-note standards (state-don't-instruct, vendor-data caveats, a role-based buyer-recommendations section, and confidence-tagged Strategic Planning Assumptions). The HTML follows a judgment-headline + lead + bullet-point reading contract and is optionally put through a reader-fit review. The STRUCTURE and VISUAL STYLE are the reusable asset; the CONTENT (insights, analysis frameworks, industry extension) must be freshly derived from the actual conference — never copy the previous report's specific analytical frameworks (e.g. a "七层治理生态") into a new vendor's report. Covers the proven workflow: research → core judgment → insights-first → product panorama as support → customer evidence → competitive landscape → buyer recommendations → conference-specific industry extension → summary.
Build an executive-oriented deep-dive industry report for a major data/AI vendor conference (e.g. Snowflake Summit, Databricks Data+AI Summit / DAIS…
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1387 chars, limit 1024 - warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Build an executive-oriented deep-dive industry report for a major … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "description_en" - note
frontmatter-keyunknown frontmatter key "agent_created"
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
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 110 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3385 tokens
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 1387: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 110 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 44.