#601

Global Rank · of 601 Skills

agent-standards AI Agent Skill

View Source: oakoss/agent-skills

Safe

Installation

npx skills add oakoss/agent-skills --skill agent-standards

32

Installs

Expert Instruction

Overview

Foundational meta-skill that defines behavioral and cognitive standards for senior AI engineering agents. Establishes the reasoning pipeline, memory architecture, and context engineering practices that enable autonomous, long-horizon task execution with verifiable outcomes.

When to use: Configuring agent reasoning, managing context windows, establishing verification protocols, orchestrating multi-agent workflows, optimizing token usage.

When NOT to use: Domain-specific coding tasks (use specialized skills), UI/UX design, database schema work.

Quick Reference

Pattern Approach Key Points
Perception Analyze terminal output, codebase, traces High-fidelity input ingestion
Hypothesis Generate multiple solution paths Evaluate before committing
Simulation Reason through change consequences Predict side effects
Action Precise tool execution Atomic, testable commits
Criticism Self-audit output Check for bugs and style violations
Context discovery Map framework versions and patterns Always discover before implementing
Dependency audit Check existing tools before adding new ones Avoid unnecessary dependencies
Verifiable planning Define Definition of Done Test pass, build success, or user approval
Interactive alignment Ask the user for ambiguous requirements Confirm critical architectural decisions
Atomic implementation Apply changes in logical, testable units Each commit should be independently verifiable
Audit and cleanup Run linter, remove debug artifacts No temporary code in final output
Selective reading Use offset and limit parameters Avoid reading entire large files
Symbol search Use grep/rg to find definitions Do not read entire directories
Few-shot anchoring Provide canonical examples More effective than long rule lists
Memory tiering Short-term, mid-term, long-term Match persistence to information lifetime
Context packing Bundle related files Structured markdown artifacts
Noise reduction Exclude node_modules, dist, binary artifacts Maximize signal-to-noise ratio in context
Semantic summarization Condense long logs into actionable facts Single-sentence failure descriptions
Cognitive load pruning Remove irrelevant history from active context Free tokens for current task reasoning

Common Mistakes

Mistake Correct Pattern
Failing silently when a tool call or build step errors Always report status and errors explicitly to the user
Inventing APIs or methods that do not exist Search documentation or use web search to verify API signatures before using them
Writing verbose explanations instead of showing code Prioritize code-first communication; explain only when asked
Ignoring surrounding code style and conventions Mimic the existing codebase patterns, naming, and formatting
Hardcoding secrets or API keys in source files Use environment variables and .env file mapping
Reading entire directories to find a single symbol Use grep or rg to locate definitions, then read only relevant sections
Skipping verification after implementation Every task must have a verification signal before marking complete
Storing sensitive data in memory or context files Run a secret scrub before persisting any memory vector
Loading full file contents into context unnecessarily Use partial reads with offset and limit for large files
Including duplicate information from multiple sources Deduplicate context to preserve token budget

Delegation

  • Explore a codebase to map framework versions and active patterns: Use Explore agent
  • Execute a complex multi-step implementation with atomic commits: Use Task agent
  • Plan architecture for a long-horizon feature with dependency analysis: Use Plan agent

References

Installs

Installs 32
Global Rank #601 of 601

Security Audit

ath Safe
socket Safe
Alerts: 0 Score: 90
snyk Low
EU EU-Hosted Inference API

Power your AI Agents with the best open-source models.

Drop-in OpenAI-compatible API. No data leaves Europe.

Explore Inference API

GLM

GLM 5

$1.00 / $3.20

per M tokens

Kimi

Kimi K2.5

$0.60 / $2.80

per M tokens

MiniMax

MiniMax M2.5

$0.30 / $1.20

per M tokens

Qwen

Qwen3.5 122B

$0.40 / $3.00

per M tokens

How to use this skill

1

Install agent-standards by running npx skills add oakoss/agent-skills --skill agent-standards in your project directory. Run the install command above in your project directory. The skill file will be downloaded from GitHub and placed in your project.

2

No configuration needed. Your AI agent (Claude Code, Cursor, Windsurf, etc.) automatically detects installed skills and uses them as context when generating code.

3

The skill enhances your agent's understanding of agent-standards, helping it follow established patterns, avoid common mistakes, and produce production-ready output.

What you get

Skills are plain-text instruction files — not executable code. They encode expert knowledge about frameworks, languages, or tools that your AI agent reads to improve its output. This means zero runtime overhead, no dependency conflicts, and full transparency: you can read and review every instruction before installing.

Compatibility

This skill works with any AI coding agent that supports the skills.sh format, including Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider, and other tools that read project-level context files. Skills are framework-agnostic at the transport level — the content inside determines which language or framework it applies to.

Data sourced from the skills.sh registry and GitHub. Install counts and security audits are updated regularly.

EU Made in Europe

Chat with 100+ AI Models in one App.

Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, GLM-5, Kimi K2.5 and many more.

Start for free View pricing
Customer Support