Templates

Copy-paste starting points with annotated fields. No email gate on the copy button, ever.

SKILL.md Templateskill-md

A copy-paste starting point for a well-formed agent skill: trigger-bearing description, procedure, boundaries, and verification.

for: Engineers writing their first (or fiftieth) skill
AGENTS.md Templateagents-md

A repository-root instruction file any agent runtime can read: setup, conventions, map, and constraints.

for: Anyone whose repo is touched by AI agents
CLAUDE.md Templateclaude-md

A Claude Code project instruction file: context, commands, style, and the accumulated gotchas that make sessions start smart.

for: Claude Code users standardizing project behavior
Cursor Rules Templatecursor-rules

A scoped Cursor rule: glob-targeted, rationale-bearing, with examples that show the rule applied.

for: Cursor power users
Agent Loop Spec Templateloop-spec

A specification for a closed-loop workflow: steps, per-step verification, exit criteria, recovery, and budget.

for: Founders and agencies productionizing agent workflows
Skill Evaluation Checklisteval-checklist

A pre-adoption review checklist for any third-party skill: triggers, completeness, boundaries, evidence, docs.

for: Engineering managers and agencies vetting skills
AI Agent Governance Checklistgovernance-checklist

The minimum governance layer for a production agent deployment: permissions, destructive-action policy, logging, human gates, data boundaries.

for: Engineering managers and enterprise AI leads
Codex Instructions Templatecodex-instructions

An AGENTS.md-skeleton tuned for OpenAI Codex CLI: same identity-layer content, Codex-specific execution notes.

for: Codex CLI users
Memory Architecture Spec Templatememory-spec

A one-page specification of an agent memory system: types, storage, retrieval, decay, and privacy, decided before the first write.

for: Founders and engineers adding memory to agent systems
Agent Workflow Spec Templateworkflow-spec

A specification for a multi-stage agent workflow: actors, stages, skills per stage, handoffs, and verification gates.

for: Agencies and teams productionizing multi-step agent work
Agent Benchmark Report Templatebenchmark-report

The reporting skeleton for a reproducible agent benchmark: hypothesis, pinned method, results, limitations, raw data.

for: Anyone publishing agent performance claims
Agent Reliability Review Templatereliability-review

A self-audit of an agent system against the Agentic Maturity Model: failure inventory, loop and memory audit, top fixes.

for: Founders and engineering managers assessing their agent stack
Agent Operating Manual Templateoperating-manual

The one-page manual for a production agent: mission, capabilities, boundaries, escalation, and ownership.

for: Teams running agents that other people depend on
Claude Code Project Setup Checklistsetup-checklist

First-hour setup for a Claude Code project: CLAUDE.md, permissions, first skills, and hooks, in order.

for: Engineers onboarding a repo to Claude Code
Skill Trigger-Test Protocoleval-checklist

The five-minute test for whether a skill actually fires: paraphrase matrix, fire-rate scoring, and description fixes.

for: Skill authors and adopters