Is the Accord skill free?

Yes. The skill itself is free from simota/agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Accord SkillProof Score?

7.2/10 — installs cleanly 4/5, triggers reliably 4/5, output vs. baseline 8/10, docs & honesty 2/5.

How do I install Accord?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Accord with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Accord

Cross-team L0-L3 spec packages with BDD acceptance criteria and requirement traceability.

by simota · simota/agent-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · d2fb26b

Drafting a password-reset spec produced genuinely more disciplined output than baseline -- declarative Given/When/Then instead of UI-step scenarios, REQ-to-AC traceability IDs, audience-split L2 sections -- but a plain `cp -r accord/` install silently breaks eight of its own '_common/*.md' reference links since that folder actually lives at the repo root, and the body cites suspiciously precise, unlinked stats ('CMU SEI' 50-80% defect reduction, 'Wiley SLR 2026' 58.2%/81.2%) that read as fabricated authority.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 4/5
Output vs. baseline 8/10
Docs & honesty 2/5

What Accord does

Drives staged authoring of a unified cross-team specification (L0 Vision through L3 BDD acceptance criteria) so Business, Development, and Design can work from one traceable source of truth, with explicit scope modes (Full/Standard/Lite) and requirement-to-acceptance-criteria traceability rules. Triggers when a request needs a shared spec artifact, staged elaboration, or a spec-driven-development handoff package -- not for implementation code, mockups, or a standalone PRD.

How to install Accord

git clone https://github.com/simota/agent-skills
cd agent-skills
mkdir -p ~/.claude/skills
cp -r accord ~/.claude/skills/accord

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Accord

/accord Cross-team L0-L3 spec packages with BDD acceptance criteria and requirement traceability.

It also activates on plain-language prompts like these:

We need a shared spec doc that Business, Design, and Dev can all trace
Draft a staged spec package with BDD acceptance criteria for this feature
I need a traceable requirements doc from vision down to acceptance criteria

Frequently asked questions

Is the Accord skill free?: Yes. The skill itself is free from simota/agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Accord work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. Drafting a password-reset spec produced genuinely more disciplined output than baseline -- declarative Given/When/Then instead of UI-step scenarios, REQ-to-AC traceability IDs, audience-split L2 sections -- but a plain `cp -r accord/` install silently breaks eight of its own '_common/*.md' reference links since that folder actually lives at the repo root, and the body cites suspiciously precise, unlinked stats ('CMU SEI' 50-80% defect reduction, 'Wiley SLR 2026' 58.2%/81.2%) that read as fabricated authority.
What is the Accord SkillProof Score?: 7.2/10 — installs cleanly 4/5, triggers reliably 4/5, output vs. baseline 8/10, docs & honesty 2/5.
How do I install Accord?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Accord with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.