BF skills-best-practices
Opinionated best practices for building Agent Skills - SKILL.md structure, frontmatter, description writing, progressive disclosure, testing, distribution. Use when creating or reviewing a skill, or debugging why one will not trigger.
As a process F 42/100 · Will not run — References files that are not bundled: FORMS.md, reference.md
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 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.
- 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-pipe-to-shellreferences/clawhub-publishing.md:29Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)**Hard-block codes** (`malicious.install_terminal_payload`, `malicious.crypto_mining`, `malicious.known_blocked_signature`) auto-hide the skill and place the uploader in manual moderation. The most co
quoted
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6063 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: FORMS.md - warning
missing-refreference to a missing file: reference.md
Process rating: all ten parameters 42/100
- 0Tools and files. 2 referenced file(s) missing: FORMS.md, reference.md
- 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. 22 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 6063 tokens
- 85Steps. 58 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 234: enough signal without eating the budget
- +4Structure: 47 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.