Shaping

🌐Community
by rjs · vlatest · Repository

Shaping refines generated text by iteratively adjusting phrasing for clarity, tone, and desired impact – boosting communication effectiveness.

Install on your platform

We auto-selected Claude Code based on this skill’s supported platforms.

1

Run in terminal (recommended)

terminal
claude mcp add shaping npx -- -y @trustedskills/shaping
2

Or manually add to ~/.claude/settings.json

~/.claude/settings.json
{
  "mcpServers": {
    "shaping": {
      "command": "npx",
      "args": [
        "-y",
        "@trustedskills/shaping"
      ]
    }
  }
}

Requires Claude Code (claude CLI). Run claude --version to verify your install.

About This Skill

What it does

The shaping skill enables AI agents to dynamically modify their own behavior, constraints, and output formats based on user input or evolving context. It allows for real-time adjustment of agent capabilities without requiring code changes.

When to use it

  • You need an agent to adapt its tone or style mid-conversation (e.g., switching from formal to casual).
  • Your workflow requires changing the data format of outputs (e.g., from JSON to Markdown) on the fly.
  • You want to enforce new safety constraints or role-playing personas during a session.
  • The agent needs to refine its reasoning depth based on feedback received within the chat.

Key capabilities

  • Dynamic behavior modification during active sessions
  • Real-time constraint injection and removal
  • Adaptive output formatting based on user preference
  • Context-aware persona switching

Example prompts

  • "From now on, summarize your responses in bullet points only."
  • "Switch to a strict cybersecurity analyst persona for the next three turns."
  • "Change your output format to valid JSON starting with this response."

Tips & gotchas

Ensure you provide clear, unambiguous instructions when triggering behavior changes to avoid conflicting constraints. Test edge cases where multiple shaping rules are applied simultaneously to verify priority logic.

Tags

🛡️

TrustedSkills Verification

Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.

Security Audits

Gen Agent Trust HubPass
SocketPass
SnykPass

Details

Version
vlatest
License
Author
rjs
Installs
124

🌐 Community

Passed automated security scans.