Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
Finding documentation protocol — Markdown template, YAML frontmatter schema, CVSS v4.0 severity guide, confidence levels, naming conventions, post-creation checklist.
When you discover a vulnerability or notable security issue, create an individual
Markdown file in the findings/ directory using write_file().
findings/{severity}-{slugified-title}.md
Derive the slug from the finding title — lowercase, hyphens for spaces, strip special characters.
The id field in YAML frontmatter (FIND-001, FIND-002, ...) is the canonical cross-reference.
Determine the next ID by counting existing files: ls findings/*.md | wc -l.
Examples:
findings/critical-exposed-mysql-api-example-com.mdfindings/high-subdomain-takeover-staging-herokuapp.mdfindings/medium-missing-hsts-header-www.mdEvery finding MUST use this Markdown structure with YAML frontmatter:
---
id: FIND-001
severity: critical
cvss_score: 9.8
cvss_vector: "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N"
cvss_version: "4.0"
cwe: [CWE-89]
mitre: [T1190]
affected_target: "10.0.0.5"
affected_component: "MySQL 5.7 on port 3306"
confidence: verified
objective_id: OBJ-001
phase: recon
agent: recon
detected: null
remediation_priority: immediate
npx skills add PurpleAILAB/Decepticon --skill finding-protocolHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
Very clear and well structured, with almost no room for misunderstanding.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
Highly actionable with clear, concrete steps that an agent can follow directly.