BF web-auto-form
JSON 驱动的浏览器表单自动化工具，为 AI Agent 提供原生 function-calling 集成，支持表单填写、条件分支、数据提取与 PII 脱敏
JSON 驱动的浏览器表单自动化工具，为 AI Agent 提供原生 function-calling 集成，支持表单填写、条件分支、数据提取与 PII 脱敏
As a process F 41/100 · Will not run — References files that are not bundled: SYSTEM_PROMPT.md, docs/STEPS.md, docs/SELECTORS.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5385 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: SYSTEM_PROMPT.md - warning
missing-refreference to a missing file: docs/STEPS.md - warning
missing-refreference to a missing file: docs/SELECTORS.md - warning
missing-refreference to a missing file: docs/PII_REDACTION.md - warning
missing-refreference to a missing file: docs/AI_AGENT_INTEGRATION.md - warning
missing-refreference to a missing file: examples/ - warning
missing-refreference to a missing file: playground/ - warning
missing-refreference to a missing file: examples/job_application.json
Process rating: all ten parameters 41/100
Will not run. References files that are not bundled: SYSTEM_PROMPT.md, docs/STEPS.md, docs/SELECTORS.md
- 0Tools and files. 8 referenced file(s) missing: SYSTEM_PROMPT.md, docs/STEPS.md, docs/SELECTORS.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5385 tokens
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- +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 79: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 48 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.
External checks
ClawHub: clean
This is a disclosed browser form automation skill, with real risks around form submission, uploads, and extraction that are expected for its purpose.
LLM: benign (high) · VirusTotal: · 28 May 2026