BD gateguard
PreToolUse fact-forcing gate that denies the first Edit/Write/Bash (including MultiEdit) attempt until the agent presents concrete facts (importers, data schemas, verbatim user instruction), then allows retry; A/B-tested at +2.25 quality points. Use when enabling or configuring the GateGuard hook, exempting paths via env vars, or handling first-touch denials.
This skill places a gate before the first edit or write attempt: the agent must present concrete facts (data schemas, exact user instructions) before being allowed to proceed. A/B testing showed a 2.25-point quality improvement. The package contains one file with 2218 tokens, no critical errors, but broken references to missing files.
In practice: works as a filter before risky operations. Configurable via environment variables with path exemptions. Grade B and quality score 78 indicate the logic is sound but implementation needs work. Supports nearly all platforms. Install if you need a safety layer against hasty code edits; otherwise, it's overhead.
PreToolUse fact-forcing gate that denies the first Edit/Write/Bash (including MultiEdit) attempt until the agent presents concrete facts (importers, data…
As a process D 39/100 · Unfinished process — References files that are not bundled: scripts/hooks/gateguard-fact-force.js
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/hooks/gateguard-fact-force.js
Process rating: all ten parameters 39/100
- 0Tools and files. 1 referenced file(s) missing: scripts/hooks/gateguard-fact-force.js
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 85Steps. 14 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2218 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 361: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.