🤖
AI EngineeringHTML

Agent Spec

by mohitagw15856

Agent Spec is an AI Engineering skill for Claude Code, published by mohitagw15856 in pm-claude-skills.

1.3K stars231 forkson mohitagw15856/pm-claude-skillsAdded 2026/08/20Repository updated 2026/08/20
View source on GitHubDownload repo ZIP
agent-skillsagentsai-agentsai-toolsanthropicchatgptclaudeclaude-codeclaude-skillscursordeveloper-toolsgeminillmmcpmcp-serverproduct-managementproductivityprompt-engineeringpromptsskills
Install in seconds
Install Agent Spec
Copy Agent Spec into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/agent-spec ~/.claude/skills/agent-spec

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/mohitagw15856/pm-claude-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/agent-spec/SKILL.md in mohitagw15856/pm-claude-skills
Installs to
~/.claude/skills/agent-spec
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering — 2451 skills

What Agent Spec does

Agent Spec defines the goal, tools, control loop, guardrails, memory, escalation, evaluation, and failure handling for an autonomous or tool-using AI agent before it is built. Use it when asked to design an AI agent, define its tools and permissions, or write an agent spec/PRD.

Agent Spec is cataloged under AI Engineering on DirSkills. Agent Spec comes from a repository tagged agent-skills, agents, ai-agents, ai-tools and anthropic.

Documentation

README

Agent Spec Skill

An agent is a model plus tools plus a loop — and the danger lives in the tools and the loop, not the model. This skill specifies an agent so its authority is explicit: what it can do, what needs a human yes, and what happens when it's wrong. Scope and guardrails first; cleverness second.

Required Inputs

Ask for these only if they aren't already provided:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Agent Spec

  • What else does mohitagw15856 publish alongside Agent Spec?

    Agent Spec is one of 25 skills that DirSkills catalogs from mohitagw15856/pm-claude-skills, the repository it ships in. Its siblings there include 360 Feedback Template, 401k Plan Decoder and A/B Test Planner. Each one is a separate skill with its own page in this directory, installs the same way Agent Spec does, and is maintained by mohitagw15856 in that same repository. The rest of the collection is listed on the mohitagw15856/pm-claude-skills page.

  • How does Agent Spec compare to other AI Engineering skills?

    Agent Spec ranks #1117 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Spec against them. Open each page to compare what they document and how they install.

More from mohitagw15856/pm-claude-skills

Agent Spec is one of 25 skills cataloged on DirSkills from mohitagw15856/pm-claude-skills.

See all 25 skills →
📋
2w ago

360 Feedback Template

360 Feedback Template designs a 360-degree feedback survey or writes a structured 360 feedback report. Use it when building a 360 feedback process, writing 360 feedback for a colleague, designing a survey, or producing a feedback report.
Writing
1.3K231
📊
2w ago

401k Plan Decoder

401k Plan Decoder decodes a 401k or workplace retirement plan—the real cost of its funds, match fine print, vesting math, and plan features worth using or avoiding. Use it to review fees, understand employer match conditions, and prepare questions for HR.
Data
1.3K231
📊
2w ago

A/B Test Planner

A/B Test Planner designs statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments. Use it to set up an experiment, calculate sample size, or interpret test results with a complete test plan including hypothesis, variants, guardrail metrics, and a results interpretation guide.
Data
1.3K231
📊
2w ago

A/B Test Readout

A/B Test Readout analyzes finished A/B test results and produces a readout with statistical and practical significance, segment cuts, and a ship/no-ship recommendation. Use it when asked to interpret experiment data, write a test readout, or decide whether to ship a variant.
Data
1.3K231
🎯
2w ago

AEO Optimizer

AEO Optimizer optimizes articles for Answer Engine Optimization so AI engines like ChatGPT, Perplexity, and Claude can extract, quote, and cite the content. Use it when asked to AEO-optimize, make content AI-readable, or improve AI citation chances.
SEO
1.3K231
♿
2w ago

Accessibility Audit

Accessibility Audit generates a WCAG 2.2 accessibility audit checklist and remediation suggestions for any UI or design. Use it when asked to audit for accessibility, check WCAG compliance, review a design for a11y issues, or create an accessibility remediation plan.
Quality
1.3K231

More AI Engineering skills

Agent Spec is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #1117 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K