Is the Design Harness skill free?

Yes. The skill itself is free from tigerless-labs/design-harness. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Design Harness SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Design Harness?

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 Design Harness 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.

Design Harness

Evidence board for contested calls, projected to a self-contained HTML canvas

by tigerless-labs · tigerless-labs/design-harness

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 30, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · fe71bfc

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 30, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran the whole pipeline on a real decision (which Python task queue for a small Flask app): bootstrapped the workspace, filed four source cards and two idea cards, and built the canvas — 7 nodes, 9 edges, 163 KB of HTML with zero external resource references, including a red conflict edge derived from one card's `conflicts:` frontmatter. The no-skill baseline for the same question produced a single markdown memo with a recommendation and no traceable link between claim and source. Then I injected four schema defects (two tags on one card, a missing id, a dangling link, markdown in an unknown directory); the validators named all four and the build refused, writing no HTML at all. The cost is real: it never picks a side for you, so a question that wants an answer gets a board instead, and script failures surface as raw Python tracebacks. The README's own copy-the-folder snippet also fails on a machine that has no ~/.claude yet — the install command above adds the missing mkdir.

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 4/5

What Design Harness does

Turns scattered sources and half-formed judgments into a three-layer markdown workspace (sources, ideas, output) plus a free-form board, then projects the whole thing onto one self-contained HTML canvas whose edges are derived from the links inside the cards. Bundled Python validators gate every build, so a broken card blocks the projection instead of producing a misleading board. Triggers on vendor or tool selection, literature reviews, due diligence and similar decisions that must stand on traceable evidence.

How to install Design Harness

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Design Harness

/design-harness Evidence board for contested calls, projected to a self-contained HTML canvas

It also activates on plain-language prompts like these:

File these three papers into the evidence board and link them to our ideas
We're choosing between Postgres and DynamoDB, build the evidence board
Put this on the board: I think we should drop the mobile client, with sources

Frequently asked questions

Is the Design Harness skill free?: Yes. The skill itself is free from tigerless-labs/design-harness. SkillProof publishes the install command and an independent test verdict at no cost.
Does Design Harness work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 30, 2026. Verdict: Tested · Works. Ran the whole pipeline on a real decision (which Python task queue for a small Flask app): bootstrapped the workspace, filed four source cards and two idea cards, and built the canvas — 7 nodes, 9 edges, 163 KB of HTML with zero external resource references, including a red conflict edge derived from one card's `conflicts:` frontmatter. The no-skill baseline for the same question produced a single markdown memo with a recommendation and no traceable link between claim and source. Then I injected four schema defects (two tags on one card, a missing id, a dangling link, markdown in an unknown directory); the validators named all four and the build refused, writing no HTML at all. The cost is real: it never picks a side for you, so a question that wants an answer gets a board instead, and script failures surface as raw Python tracebacks. The README's own copy-the-folder snippet also fails on a machine that has no ~/.claude yet — the install command above adds the missing mkdir.
What is the Design Harness SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Design Harness?: 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 Design Harness 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.