Skip to content
Back to skills

Patterns

ASecurity

**Use Case:** Complex domains where the agent needs to generate its own contextual reference files or even scaffold out entirely new skills dynamically.

  • 7 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 2, 2026
ai-agents

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned September 2, 2026

npx -y skills add richfrem/agent-plugins-skills --skill patterns --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Patterns?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Patterns
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/richfrem-patterns/badge)](https://www.skillsdirectory.com/skills/richfrem-patterns)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# The Dual-Mode Meta-Skill (Bootstrap → Iteration)

**Use Case:** Complex domains where the agent needs to generate its own contextual reference files or even scaffold out entirely new skills dynamically.

## The Core Mechanic

A tool that doesn't just execute logic, but *manages the creation of other tools and skills*. It operates in two explicit lifecycle modes declared in its frontmatter: Bootstrap (create from scratch) and Iteration (update existing).

### Implementation Standard

Define the modes explicitly in the skill description:

```yaml
---
name: domain-context-extractor
description: >
  BOOTSTRAP MODE - Triggers: "Create a new domain context skill"
  → Asks key questions, structures directories, and generates the initial SKILL.md
  
  ITERATION MODE - Triggers: "Add context about [new topic]"
  → Loads the existing skill, finds gaps, and appends new reference files without destroying the old structure.
---
```

Instruct the agent inside the skill on how to handle the filesystem operations for both modes, acting as an internal file scaffolding engine.

Files in this skill

  • action-forcing-output-with-deadline-attribution.md901 B
  • adversarial-objectivity-constraint.md1001 B
  • anti-pattern-vaccination.md914 B
  • anti-symptom-triage.md1.1 KB
  • artifact-embedded-execution-audit-trail.md969 B
  • artifact-generation-xss-compliance-gate.md1.8 KB
  • artifact-lifecycle.md490 B
  • artifact-state-interrogative-routing.md2.2 KB
  • asynchronous-benchmark-metric-capture.md1.6 KB
  • audience-segmented-information-filtering.md816 B
  • category-calibrated-benchmark-anchoring.md3.7 KB
  • category-semantic-deferred-tool-binding.md2.7 KB
  • chained-command-invocation.md983 B
  • chained-commands.md376 B
  • client-side-compute-sandbox-constraint.md1.7 KB
  • complexity-tiered-output.md1.1 KB
  • conditional-step-inclusion.md1 KB
  • connector-placeholders.md1.2 KB
  • cyclical-state-propagation-contract.md3 KB
  • delegated-constraint-verification-loop.md1.9 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.