AgentSpec commands for workflow. Use /workflow-commands + intent. Reads .github/config/grounding.md before executing. Commands: /brainstorm, /build, /validate, /create-pr, /define, /design, /iterate, /ship

2026-05-081

knowledge-context-commands

Tiao553/sdd-harness-copilot

AgentSpec commands for managing project knowledge context. Use /knowledge-context-commands + intent. Reads .github/config/grounding.md before executing. Commands: /create-context, /update-context, /check-context

2026-05-031

create-skills

Tiao553/sdd-harness-copilot

Meta-skill for scaffolding new AgentSpec skills. Creates skill directory structure with SKILL.md, commands/, references/, templates/, and scripts/.

2026-05-021

knowledge-commands

Tiao553/sdd-harness-copilot

AgentSpec commands for knowledge. Use /knowledge-commands + intent. Reads .github/config/grounding.md before executing. Commands: /create-kb, /update-kb, /refresh-stale-kbs

2026-05-021

visual-explainer

Tiao553/sdd-harness-copilot

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

2026-05-011

core-commands

Tiao553/sdd-harness-copilot

AgentSpec commands for core. Use /core-commands + intent. Reads .github/config/grounding.md before executing. Commands: /meeting, /memory, /readme-maker, /status, /sync-context

2026-04-301

name	review-commands
description	AgentSpec review commands. Use /review-commands + command. Commands: /review, /judge
license	MIT
compatibility	GitHub Copilot VS Code, GitHub Copilot cloud agent
metadata	{"version":"1.0.0","category":"commands"}

Review Commands

Invoke as:

/review-commands /review <file-or-directory>
/review-commands /judge <file> [--context "..."] [--model <openrouter-model>]
/review-commands /judge --ledger

Grounding

Read .github/config/grounding.md.
Treat this skill as the primary routing source.
For /review, use .github/agents/python.code-reviewer.agent.md.
For /judge, use .github/agents/dev.judge-agent.agent.md.
Load only the KB files required by the selected agent or by the reviewed domain.

/review

Use for code review, config review, migration review, and documentation review.

Execution:

Read the target file or directory.
Use the code-review stance: findings first, ordered by severity.
Cite concrete file paths and line numbers.
Include missing tests or residual risks.

/judge

Use for a second opinion on high-risk or ambiguous output.

Execution:

Read .github/agents/dev.judge-agent.agent.md.
If the request targets a file, read the file before judging.
If an external judge runtime is configured and OPENROUTER_API_KEY is available, run that runtime.
If the runtime or key is missing, stop and report the missing prerequisite instead of inventing an external verdict.
Write ledger entries only to .github/storage/judge-ledger.jsonl.

Comandos Disponíveis

Comando	Descrição	Arquivo	Agente
`/review`	Code review com findings por severidade	`commands/review.md`	`code-reviewer`
`/judge`	Segunda opinião via judge runtime externo	`commands/judge.md`	`judge-agent`

Constraints

Do not use #skill: or skill: syntax.
Do not use .claude/** paths.
Do not initiate SDD workflow phases from this skill.