BD web-capture
Each Monday the company's own website, its competitors' pages and recent news about both land in context/ as one pull request: the first run seeds positioning, offerings, an inferred ICP with a disqualifier, competitors, clients and proof; every run after adds a dated note of what changed (pricing, a launch, funding, a customer) and never edits an existing file. Triggers: "keep our context current from our website", "watch competitor pricing pages", "add our company news to the knowledge base", "our context repo is empty, seed it from our website", "set up the workspace context from our domain". Cargo CDK, harness claudeCode, parallel, GitHub. Skip when: news about target accounts, which is monitor-buying-signals; one company researched before a call, which is research-account; or the ICP verified against won and lost deals, which is win-loss-review.
Each Monday the company's own website, its competitors' pages and recent news about both land in context/ as one pull request: the first run seeds…
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
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 49/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 15 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4074 tokens
- 100Steps. 30 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 The response is described with custom markup (9 tags): a typed call is more reliable
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 862: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.