BC email-formatter
Transform rough email drafts into polished, professional messages. Use this skill when the user wants to improve email quality, fix grammar and tone, format business emails, or convert casual messages into professional communication. Triggers include: 'format my email', 'make this professional', 'improve this message', 'fix my email', 'polish this draft', or any request to enhance email writing quality. Also use when converting bullet points or notes into complete emails, adjusting tone (formal/casual/friendly), or preparing important messages for clients, managers, or stakeholders.
As a process C 57/100 · Has gaps — weak spots: consistency, execution cost, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securitySKILL.md:129Offensive-security / dual-use content (legitimate for authorised testing; review intended use)❌ **Extortion**: Blackmail, ransomware, threats for money, coercion
-
low Risky intent
intent-offensive-securitySKILL.md:155Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Credential Harvesting Red Flags:**
-
low Risky intent
intent-offensive-securitySKILL.md:559Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Layer 4: Credential Harvesting
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 13325 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 40Consistency. Frontmatter name (email-formatter) differs from the folder (email-formatter-skill)
- 40Execution cost. Instruction body is 13325 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Steps. 184 steps, 4 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 25 top-level sections: this looks like several domains in one skill
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)
- -245 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 589: enough signal without eating the budget
- +4Structure: 54 headings
- +3Step-by-step instructions: 184 items
- +3Output format is stated explicitly
- +4Has examples (34 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.