BF prompt-fidelity
Self-checks how much of a request is verifiable vs guesswork before answering it. Use when handling search, filtering, recommendation, or data-retrieval requests over any dataset (API, database, files, spreadsheet) that mix objective criteria (checkable via a query, count, or calculation) with subjective judgment (mood, style, quality, "feels like", "best"), or when the user asks how confident, reliable, or verifiable an answer is. Decomposes the request into constraints, computes a fidelity score, and reports which parts of the answer are verified vs inferred.
Self-checks how much of a request is verifiable vs guesswork before answering it.
As a process F 46/100 · Will not run — References files that are not bundled: scripts/compute_fidelity.py
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-autorun-instructionSKILL.md:221Instructs the agent to auto-run a script on every sessionAlways run the script — the score must be computed correctly either way —
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/compute_fidelity.py
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: scripts/compute_fidelity.py
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3717 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 567: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.