skills.rest
klh
klhCOMMUNITY
Explore all skills by this author →
Website𝕏@klhougesenGitHub

klh-all-skills

Guides agent output verbosity, efficiency, and formatting rules for any user request.

1|Updated Apr 16, 2026
Search Tags:#agent behavior#token efficiency#hallucination prevention#output formatting#coding agents#context drift#verbosity control
One-click install
npx skills add https://github.com/klh/skills --skill klh-all-skills-klh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: klh-all-skills
Source: https://github.com/klh/skills/tree/main/.well-known/agent-skills/klh-all-skills
Command: npx skills add https://github.com/klh/skills --skill klh-all-skills-klh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents often produce verbose, inconsistent, or hallucinated output that wastes tokens and breaks downstream consumers. This Skill enforces global behavior rules covering verbosity, efficiency, encoding, and hallucination prevention across every response. ## Core Features & Use Cases - Output Discipline: Enforces structured output (JSON, bullets, tables), ASCII-only encoding, and no filler text or status narration. - Efficiency Budgets: Caps tool calls at 50, prevents redundant file reads, and promotes single-pass coding workflows. - Hallucination Prevention: Forbids invented file paths, API endpoints, or field names; unknown values return null or "UNKNOWN". - Context Drift Management: Provides recovery strategies (summarize, save anchors, branch isolation) for long sessions. - Use Case: A team running multi-agent pipelines installs this skill globally so every agent returns parseable, token-efficient output without sycophantic openers or fabricated references. ## Quick Start Install the skill with npx skills add klh/skills --skill klh-all-skills and ask your agent to perform any coding task with concise structured output.

Frequently Asked Questions about klh-all-skills

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make AI agent output less verbose?▼

Install a global behavior skill that enforces structured output rules such as JSON, bullets, and tables while banning status narration and filler text. This skill applies those rules automatically to every response.

How to prevent AI agents from hallucinating file paths?▼

Use explicit hallucination-prevention rules: never invent file paths, endpoints, or field names, and return null or UNKNOWN for missing values. This skill encodes those rules as standing agent instructions.

Does this skill work with Claude Code and other coding agents?▼

Yes, it follows the agentskills.io specification and works with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, and other agents that support SKILL.md-based skills.

What is context drift in long AI agent sessions?▼

Context drift is when an agent repeats file reads, contradicts earlier decisions, or forgets the original task in long sessions. This skill defines recovery strategies: proactive summarization, saving decision anchors to files, and branch isolation.

When should I not use a global behavior modifier skill?▼

Avoid it when a task requires rich prose output, such as writing documentation or marketing copy for human readers, since the skill restricts output to structured, minimal formats.

Related Skills

Explore More Software Engineering Skills→
pantheon-orgpantheon-org
9

opencode-configure

Configure OpenCode runtime settings in opencode.json and AGENTS.md.

Official
Intermediate
LisztVanLisztVan
2

dispatching-parallel-agents

Delegate independent debugging tasks to isolated agents for parallel execution.

Community
Advanced
arelbenarelben

project-memory

Create a project memory system with docs/project_notes templates for AI tools.

Community
Intermediate
nevirnevir
19

skill

Create portable agent skills with SKILL.md scaffolds per the Agent Skills spec.

Community
Advanced