Gerg/ai_agent_skills

Gerg's Signature® Instructions for AI Coding Agents

2Stars on the repository
12Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

agent-collaboration

01

Gerg/ai_agent_skills

Skill Claude CodeCodex

Universal guide for agent-user collaboration - covers how to collaborate with users, plan work, make decisions, handle errors, and communicate effectively.

not rated 2 2mo ago A 32 tokens original MIT

Gerg/ai_agent_skills

Skill Claude CodeCodex

Track issues, findings, and tasks during code reviews or development work using agent-friendly issue tracking tools. Use when conducting code reviews, managing multiple parallel tasks, tracking findings that need action, coordinating work with other agents, or generating work summaries.

not rated 2 2mo ago A 54 tokens original MIT

agent-session-retro

03

Gerg/ai_agent_skills

Skill Claude CodeCodex

Conduct end-of-session retrospectives to identify improvements to skills, AGENTS.md, processes, and collaboration patterns. Use at session end to reflect on what worked well, what could be improved, and propose concrete changes to tooling or documentation.

not rated 2 2mo ago A 52 tokens original MIT

code-development

04

Gerg/ai_agent_skills

Skill Claude CodeCodex

Guide for writing production code with automated tests. Use when implementing features, fixing bugs, refactoring code, or writing any production software. Covers development practices, testing principles, code style, and architectural alignment.

not rated 2 2mo ago A 44 tokens original MIT

command-writing

05

Gerg/ai_agent_skills

Skill Claude CodeCodex

Guide for creating effective Cursor commands. Use when creating new commands, updating existing commands, reviewing command quality, or when users request help with command design, organization, or best practices. Commands are simple slash-invoked workflows distinct from skills.

not rated 2 2mo ago A 51 tokens original MIT

doc-writing

06

Gerg/ai_agent_skills

Skill Claude CodeCodex

Guide for writing user-facing technical documentation for software features. Use when writing new docs, updating existing docs, or auditing docs for accuracy and style. Covers the full workflow from researching a feature through writing and reviewing the output.

not rated 2 2mo ago A 47 tokens original MIT

pr-review

07

Gerg/ai_agent_skills

Skill Claude CodeCodex

Systematic code review process for pull requests. Use when conducting thorough PR reviews to validate implementation correctness, scope alignment, and code quality with empirical testing and structured issue tracking.

not rated 2 2mo ago A 37 tokens original MIT

skill-writing

08

Gerg/ai_agent_skills

Skill Claude CodeCodex

Meta-skill for creating effective skill documents using progressive disclosure. Use when creating new skills, updating existing skills, reviewing skill quality and structure, organizing skills with references, or when users request help with skill design, organization, or best practices.

not rated 2 2mo ago A 51 tokens original MIT

story-writing

09

Gerg/ai_agent_skills

Skill Claude CodeCodex

Guide for writing well-structured user stories across all issue trackers and domains. Use when writing user stories to ensure proper structure, Given/When/Then format, clear acceptance criteria, and appropriate tracker-specific formatting. Covers generic principles, Jira markup, Cloud Foundry API patterns, and Cloud…

not rated 2 2mo ago A 65 tokens original MIT

Gerg/ai_agent_skills

Skill Claude CodeCodex

Write, review, and edit technical design proposals — both High-Level Designs (HLDs, for alignment/approval) and Low-Level Designs (LLDs, for implementation). Use when drafting, restructuring, reviewing, or editing a design doc, architecture proposal, RFC, or "tech spec"; when deciding what belongs in a high-level vs…

not rated 2 2mo ago A 128 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: