prototype-lab
Skill6 starsChanged 51 days agoMITView on GitHub
Produce 3 thin comparable variants of a proposed design with a comparison artifact and mandatory Human Validation Plan
3 other projects use a version of this.
Adopted by
Most recently taken up by
- gvastethecreator/prototype-lab-skilltheir own version, first seen Nov 1, 2026
- lglucas/ai-dev-operating-systemtheir own version, first seen Sep 28, 2026
- markoblogo/abvx-agent-skillstheir own version, first seen Jun 14, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- markoblogo/abvx-agent-skills★ 16same name
- lglucas/ai-dev-operating-system★ 12same name
- gvastethecreator/prototype-lab-skill★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-safety-reviewSkill
- agent-team-executionSkill
- agent-team-reviewSkill
- alert-hygieneSkill
- authorial-judgmentSkill
- batch-scriptingSkill
- capture-knowledgeSkill
- deploy-gateSkill
- design-debateSkill
- implementation-drift-checkSkill
- improvement-minerSkill
- incident-analysisSkill
- incident-trend-analyzerSkill
- openspec-shipSkill
- outcome-reviewSkill
- panelSkill
- product-discoverySkill
- project-verificationSkill
- runtime-validationSkill
- second-opinionSkill
- security-scannerSkill
- skill-scaffoldSkill
- supply-chain-investigationSkill
- synthesizeSkill
- unified-context-stackSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Default: 3 variants. User can override ("just compare these 2").
- Distinctive: line 35
Create the minimum artifacts defined in Step 1
- Distinctive: line 36
Keep each variant thin — enough to evaluate the approach, not production-ready
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prototype Lab
Build exactly 3 thin, comparable variants of a proposed design so the user can evaluate concrete alternatives before committing to a direction.
When to Use
During DESIGN phase when competing approaches are identified. Fires on trigger match alongside brainstorming (which remains the process driver). The user or DESIGN phase guidance may suggest prototyping; this skill does not depend on brainstorming internally escalating to it.
Relationship to design-debate:
- design-debate reasons about options (3 agents argue)
- prototype-lab builds comparable artifacts (3 thin variants)
- They are complementary. design-debate can precede prototype-lab.
Step 1: Identify Variant Scope
Determine what "a variant" means for this project:
| Project type | Variant contents |
| New skill | SKILL.md draft + routing entry + one behavioral test |
| New hook | Script draft + config entry + one syntax test |
| New feature | Implementation sketch + one test |
| Architecture decision | Thin proof-of-concept code + one integration test |
Default: 3 variants. User can override ("just compare these 2").
Step 2: Build Variants
For each variant (A, B, C):
- Create the minimum artifacts defined in Step 1
- Keep each variant thin — enough to evaluate the approach, not production-ready
- Label clearly: Variant A, Variant B, Variant C
- Note key trade-offs for each
Step 3: Write Comparison Artifact
Save to docs/plans/YYYY-MM-DD-<topic>-prototype-lab.md:
# Prototype Comparison: <Topic>
**Date:** YYYY-MM-DD
**Variants:** 3
## Variant A: <Name>
**Approach:** <1-2 sentences>
**Trade-offs:** <pros and cons>
**Artifact:** <path or inline>
## Variant B: <Name>
**Approach:** <1-2 sentences>
**Trade-offs:** <pros and cons>
**Artifact:** <path or inline>
## Variant C: <Name>
**Approach:** <1-2 sentences>
**Trade-offs:** <pros and cons>
**Artifact:** <path or inline>
## Recommendation
**Chosen:** Variant <X>
**Reasoning:** <why this over the others>
## Human Validation Plan
<REQUIRED — how the user will test the chosen option with real usage>
<AI-simulated testing may inform the draft but never replaces this section>
<Describe: who tests, what they test, what success looks like>
## Success Signals
<What to measure after shipping to confirm the choice was right>Step 4: Present to User
Show the comparison artifact. Ask the user to choose a variant. Only the chosen variant proceeds to writing-plans. The others are archived in the comparison artifact.
Constraints
- 3 variants is the default
- Human Validation Plan is mandatory — the skill must not proceed without it
- AI-simulated user testing may inform the draft but never replaces real-user validation
- For auto-claude-skills, "prototype" means repo-native artifacts (SKILL.md, bash scripts, routing config, tests)
- Variants are disposable — only the chosen variant survives
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

