AB competitor-analysis-zhangzaiwang
A systematic competitive analysis skill based on Zhang Zaiwang's "Effective Competitive Analysis" methodology. Provides a complete competitive analysis framework, tools, and templates to help users conduct professional competitor research.
As a process B 65/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, consistency
How to improve
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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Unexpected scalar at node end at line 7, column 30: author: "Zhang Zaiwang" capers@qq.com ^^^^^^^^^^^^^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 65/100
- 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. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (competitor-analysis-zhangzaiwang) differs from the folder (effective-competitive-analysis)
- 65Failures and branches. 3 branches
- 70Execution cost. Instruction body is 4856 tokens
- 100Tools and files. No external tools needed
- 100Steps. 213 steps
- 100Result and completion. Output format and completion criterion are stated
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)
- -219 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 239: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 213 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.
External checks
ClawHub: clean
This is a competitive-analysis guidance skill made of Markdown templates, with no executable code or hidden system access.
LLM: benign (high) · VirusTotal: · 29 May 2026