BF read-only-workspace-audit
Audit whether one imported workspace snapshot is rich enough for export, cited AI, or MCP consumption.
As a process F 35/100 · Will not run — References files that are not bundled: examples/integrations/codex-mcp.example.json, examples/integrations/claude-code-mcp.example.json, examples/workspace-snapshot.sample.json
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 2. 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
missing-refreference to a missing file: examples/integrations/codex-mcp.example.json - warning
missing-refreference to a missing file: examples/integrations/claude-code-mcp.example.json - warning
missing-refreference to a missing file: examples/workspace-snapshot.sample.json
Process rating: all ten parameters 35/100
Will not run. References files that are not bundled: examples/integrations/codex-mcp.example.json, examples/integrations/claude-code-mcp.example.json, examples/workspace-snapshot.sample.json
- 0Tools and files. 3 referenced file(s) missing: examples/integrations/codex-mcp.example.json, examples/integrations/claude-code-mcp.example.json, examples/workspace-snapshot.sample.json
- 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
- 20When it triggers. No condition that starts the skill
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 316 tokens
- 100Running it twice. No mutating operations
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 102: 120–800 characters recommended
- +4Structure: 1 headings, hard to scan
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Step-by-step instructions: 16 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.
External checks
ClawHub: clean
The skill appears to be a read-only academic workspace auditing helper with no validated signs of data theft, destructive behavior, or hidden privilege use.
LLM: benign (medium) · VirusTotal: benign · 28 May 2026