agentic-coding-harnesses

Use when modifying the agentic coding environment, including dotfiles, skills/rules wiring, AGENTS.md/CLAUDE.md loading, Stow symlinks, Claude/Codex/OpenCode/Pi config, plugins, MCP, hooks, or harness compatibility. Loads the runbook to avoid breaking cross-harness setup. Defer to skill-creator-global for skill authoring craft, description quality, and progressive disclosure.

Jump to install

Repository: av1155/.dotfiles
Last source activity: May 12, 2026 at 09:01
Detected SKILL.md language: English
Stars: 6
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/av1155/.dotfiles --skill agentic-coding-harnesses

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

write-email

Write, shorten, or fix a real email to a real person. Use when the user says write an email, draft an email, reply to this, send this to, email my coworker/boss/client/vendor, follow up on, ask them for, make this email shorter, is this too long, review my email, or fix the tone. Applies research-backed structure (bottom line up front, length targets, skimmable formatting) and strips the narration and hedging that make drafts unreadable. Skip for marketing campaign copy, newsletters, and cold outreach sequences.

2026-08-14

deep-audit

Exhaustive post-work audit for any codebase. Run after finishing a feature, sprint, bug fix, or refactoring pass to find overlooked edge cases, discarded response data, missing cross-field validations, misleading success signals, untested failure paths, and implicit assumptions. Invoke with /deep-audit or /deep-audit followed by context. Use this skill whenever the user says audit, review my changes, check my work, what did I miss, post-mortem, sanity check, edge cases, or asks to verify completeness of recent code changes.

2026-08-14

review

Adversarial code review of the current branch. Launches a thorough review checking correctness, security, performance, architecture, type safety, and test coverage. Verifies findings against current library documentation via ctx7 and web sources to avoid flagging correct modern patterns as errors. Use after completing a feature, before merging any agent-generated code, when running gate checks between waves, or whenever you suspect code quality issues. Also use when asked to "review," "audit," "check," or "look over" code changes, even if the user doesn't say "adversarial."

2026-08-14

View all from this repository

name	agentic-coding-harnesses
description	Use when modifying the agentic coding environment, including dotfiles, skills/rules wiring, AGENTS.md/CLAUDE.md loading, Stow symlinks, Claude/Codex/OpenCode/Pi config, plugins, MCP, hooks, or harness compatibility. Loads the runbook to avoid breaking cross-harness setup. Defer to skill-creator-global for skill authoring craft, description quality, and progressive disclosure.