BB Markdown
Writes, fixes, and converts Markdown that renders the same in every parser — GitHub, MDX, Pandoc, docs sites, Slack, Notion. Use when a list stops nesting, a table renders as literal pipes, a code fence swallows the rest of the file, half a document turns italic, or an anchor link 404s; when frontmatter shows up as text; when footnotes, task lists, callouts, math, or Mermaid render on GitHub but not on the docs site; when MDX rejects `{`, `<`, or an HTML comment; when a README's images break on npm or PyPI; when converting Markdown to PDF, DOCX, or HTML, or HTML back to Markdown; when markdownlint or Prettier fights the file in CI; when pasting into Slack, Discord, Notion, Confluence, or Jira; and when Markdown from an untrusted source has to be rendered safely. Not for LaTeX documents (`latex`), Word files (`word-docx`), templated PDF deliverables such as reports, invoices, and contracts (`pdf-generator`), or documentation strategy and information architecture (`documentation`).
Writes, fixes, and converts Markdown that renders the same in every parser — GitHub, MDX, Pandoc, docs sites, Slack, Notion.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitysecurity.md:23Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Dangerous beyond `<script>`: `<style>` (exfiltration via CSS selectors, page defacement), `<iframe>`, `<object>`/`<embed>`, `<form>` (credential harvesting inside a trusted page), `<meta http-equiv=
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 6415 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 14 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6415 tokens
- 100Steps. 46 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 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 12 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
- +3Description length 994: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.