Is the Relay 80 100 Workflow skill free?

Yes. The skill itself is free from AgentWorkforce/relay. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Relay 80 100 Workflow SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Relay 80 100 Workflow?

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 Relay 80 100 Workflow 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.

Relay 80 100 Workflow

Patterns for agent-relay workflows that validate features E2E before committing

by AgentWorkforce · AgentWorkforce/relay

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · a1ac84b

Located SKILL.md at .claude/skills/ and .agents/skills/ (content-identical, only heading levels differ; frontmatter valid; no bundled scripts, so nothing to spot-check missing). No security smells — the only absolute path is a '/home/daytona' mock-sandbox return value, not an install path. Verified install in a temp HOME: clone+cp places SKILL.md correctly. For output, I designed one task (an agent-relay workflow adding a user_sessions table + lookup, validated before commit) and wrote two real artifacts: /tmp/baseline-workflow.ts (4 steps, all failOnError default-true, single test run, agent write+run in one step, no verify gate, no regression, no commit proof) vs /tmp/skill-workflow.ts (19 steps, 6 failOnError:false repairable gates, separate verify-schema gate, 4-step run-fix-rerun-final-fix loop, PGlite helper, regression run, record-head-baseline + verify-commit-created HEAD-advance proof). The baseline reproduces the exact anti-patterns the skill's own table names; the skill version fixes them concretely. Not 10 because I cannot execute the @relayflows/core runtime to prove the definition runs green.

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

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

What Relay 80 100 Workflow does

Teaches how to author @relayflows/core agent workflows that go from "code compiles" to "feature works, tested E2E locally" before committing. Triggers when writing agent-relay workflows that need repair-before-failure validation gates, run-fix-rerun test loops, PGlite in-memory Postgres tests, verify gates after every edit, and green-only commits. Provides concrete TypeScript step templates and an anti-pattern table rather than bundled scripts.

How to install Relay 80 100 Workflow

git clone --depth 1 https://github.com/AgentWorkforce/relay.git /tmp/relay-80-100-workflow-src
mkdir -p ~/.claude/skills
cp -R /tmp/relay-80-100-workflow-src/.claude/skills/relay-80-100-workflow ~/.claude/skills/relay-80-100-workflow
# Documentation-only skill (single SKILL.md, no bundled scripts). It teaches how to author
# @relayflows/core workflows with full E2E validation. The workflows it produces depend on
# @relayflows/core plus @electric-sql/pglite (dev) — installed per-project, not by this skill.
# A byte-identical copy also lives at /tmp/relay-80-100-workflow-src/.agents/skills/relay-80-100-workflow.

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

Commands — how to trigger Relay 80 100 Workflow

/relay-80-100-workflow Patterns for agent-relay workflows that validate features E2E before committing

It also activates on plain-language prompts like these:

Run the 80-to-100 validation gate before merging
Set up a Claude-then-Codex review loop for this PR
Add PGlite-based E2E tests to this workflow

Frequently asked questions

Is the Relay 80 100 Workflow skill free?: Yes. The skill itself is free from AgentWorkforce/relay. SkillProof publishes the install command and an independent test verdict at no cost.
Does Relay 80 100 Workflow work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Located SKILL.md at .claude/skills/ and .agents/skills/ (content-identical, only heading levels differ; frontmatter valid; no bundled scripts, so nothing to spot-check missing). No security smells — the only absolute path is a '/home/daytona' mock-sandbox return value, not an install path. Verified install in a temp HOME: clone+cp places SKILL.md correctly. For output, I designed one task (an agent-relay workflow adding a user_sessions table + lookup, validated before commit) and wrote two real artifacts: /tmp/baseline-workflow.ts (4 steps, all failOnError default-true, single test run, agent write+run in one step, no verify gate, no regression, no commit proof) vs /tmp/skill-workflow.ts (19 steps, 6 failOnError:false repairable gates, separate verify-schema gate, 4-step run-fix-rerun-final-fix loop, PGlite helper, regression run, record-head-baseline + verify-commit-created HEAD-advance proof). The baseline reproduces the exact anti-patterns the skill's own table names; the skill version fixes them concretely. Not 10 because I cannot execute the @relayflows/core runtime to prove the definition runs green.
What is the Relay 80 100 Workflow SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Relay 80 100 Workflow?: 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 Relay 80 100 Workflow 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.