Concepts

Skills

How Agent Skills work in pair — the open standard for structured AI assistant instructions, skill categories, and composition.

Skills are structured instructions that AI assistants discover and execute. They follow the Agent Skills open standard, supported by Claude Code, Cursor, VS Code Copilot, and OpenAI Codex.

Where the Knowledge Base provides context, skills provide actions. A skill tells the AI exactly how to perform a specific task — from creating a PRD to reviewing a pull request.

How Skills Work

Each skill is a SKILL.md file that defines:

  • What the skill does — purpose and scope
  • When to use it — trigger conditions
  • How to execute it — step-by-step instructions the AI follows
  • What it composes — other skills it calls during execution

When a developer invokes a skill (e.g., /implement), the AI reads the SKILL.md file and follows its instructions precisely. The skill references adoption files, guidelines, and templates from the Knowledge Base, ensuring consistent execution.

Skill Categories

pair organizes skills into two categories:

Process Skills

Process skills guide the AI through lifecycle phases. They follow a defined sequence and often compose capability skills:

SkillPurpose
/specify-prdCreate or update a Product Requirements Document
/bootstrapOrchestrate full project setup
/plan-initiativesCreate prioritized strategic initiatives
/plan-epicsBreak initiatives into epics
/plan-storiesBreak epics into user stories
/refine-storyAdd acceptance criteria and technical analysis
/plan-tasksCreate implementation tasks
/implementImplement a story task-by-task
/reviewPerform structured code review

Capability Skills

Capability skills perform specific, reusable operations. They are invoked independently or composed by process skills:

SkillPurpose
/verify-qualityRun quality gates against the codebase
/record-decisionRecord architectural or non-architectural decisions
/assess-stackEvaluate and register new dependencies
/verify-adoptionCheck code against adoption file compliance
/verify-doneCheck Definition of Done criteria
/write-issueCreate or update issues in the PM tool
/estimateEstimate story size

Composition

Skills compose other skills to build complex workflows. For example, /implement composes:

  • /verify-quality — after each task, to check quality gates
  • /record-decision — when a new architectural decision is made
  • /assess-stack — when a new dependency is introduced
  • /verify-adoption — before committing, to check compliance

And /review composes:

  • /verify-quality — to check quality gates on the PR
  • /verify-done — to check Definition of Done criteria
  • /assess-debt — to evaluate technical debt
  • /record-decision — if a decision needs recording

This composition means complex processes are built from simple, tested parts. Each capability skill works the same whether invoked directly or composed by a process skill.

The /next Entry Point

At the start of any session, running /next reads the project's adoption files and PM tool state to recommend the most relevant action. It tells you which skill to invoke based on where your project is in the lifecycle.

Distribution

Skills are stored in .skills/ within the KB and distributed to AI tool directories:

.claude/skills/pair-process-implement/SKILL.md    # Claude Code (canonical)
.github/skills/pair-process-implement/SKILL.md    # GitHub Copilot (symlink)
.cursor/skills/pair-process-implement/SKILL.md    # Cursor (symlink)

The canonical copy goes to .claude/skills/. Secondary targets receive symlinks, so all AI tools share the same skill definitions. The directory structure uses a flatten/prefix naming convention: process/implement becomes pair-process-implement.

On this page