BD smart-sourcing
Selects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification
Selects optimal sources for tool calls, balancing accuracy with token cost.
As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "triggers" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_plugin" - note
edit-residuethe text marks something as outdated (lines 25): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 39/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (smart-sourcing) differs from the folder (nm-conserve-smart-sourcing)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 1177 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 153: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.
External checks
ClawHub: clean
This skill is a small Markdown-only guide for deciding when to verify claims with sources, and its behavior is disclosed and proportionate.
LLM: benign (high) · VirusTotal: · 16 Sept 2026