prototype
Skill1 starsChanged 11 days agoNo licenceView on GitHub
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
247 other projects use a version of this, 79 of them edited; 43 of 78 edited versions we compared changed its rules; 8 new projects in the last 4 weeks, against 7 the 4 before.
How people change it
43 of 78 edited versions changed its rules, and some changes recur.
Of the 78 edited versions we compared: 34 keep every rule, 1 is an older text, 43 made changes of their own.
Not in older versions
- Skip the polish. No tests, no error handling beyond what makes the prototype _runnable_, no abstractions. The point is to learn something fast.missing from 1 of 1
Rules people drop
- Skip the polish. No tests, no error handling beyond what makes the prototype _runnable_, no abstractions. The point is to learn something fast.dropped by 5 of 43
- Surface the state. After every action (logic) or on every variant switch (UI), print or render the full relevant state so the user can see what changed.dropped by 4 of 43
Rules people add
- Delete or absorb when done. When the prototype has answered its question, either delete it or fold the validated decision into the real code — don't leave it rotting in the repo.added by 31 of 43
- A rule we can't quote: its licence doesn't allow itadded by 2 of 43
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Steady: 8 new projects took it in the last 4 weeks, 1.1× the 4 weeks before.
Most recently taken up by
- Robo-Co-op/robobuilder-standardedited, first seen Nov 16, 2026
- devdeepjs/kobayashi-maruedited, first seen Nov 16, 2026
- lhotwll217/owner-operatoredited, first seen Nov 16, 2026
- philoserf/claude-code-configedited, first seen Nov 15, 2026
- raphaeltm/simple-agent-managertheir own version, first seen Nov 15, 2026
- boraoztunc/skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use playtest-report, soak-test and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CoralGameSkillplaytest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
Also in 12 projects that use this
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 9 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 9 projects that use this
CoralGameSkillteam-polish
Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.
Also in 14 projects that use this
- +5 more from lilangMax
- +3 more from CoralGame
Other versions247 projects use a version of this.
Word for word · 92
- mattpocock/skills★ 325k100% same
- QuivrHQ/quivr★ 40k100% same
- The-Vibe-Company/quivr★ 40k100% same
- ArcReel/ArcReel★ 6.6k100% same
- withcoral/coral★ 4.9k100% same
- moeru-ai/xsai★ 667100% same
- mxyhi/ok-skills★ 511100% same
- aws/graph-explorer★ 492100% same
- itsmylife44/cliproxyapi-dashboard★ 285100% same
- tt-a1i/matt-skills-with-to-goal★ 192100% same
82 more not listed
Edited · 79
- GreyDGL/PentestGPT★ 16k62% same
- epicenter-md/epicenter★ 4.8k60% same
- EpicenterHQ/epicenter★ 4.8k60% same
- bestofjs/bestofjs★ 3.1k98% same
- CelestoAI/SmolVM★ 1.2k95% same
- mdiri-ai/SoduWork★ 93090% same
- nodetool-ai/nodetool★ 63776% same
- stevesolun/ctx★ 58316% same
- victorgarciaesgi/regle★ 50858% same
- Tiberriver256/mcp-server-azure-devops★ 40162% same
69 more not listed
Wrote their own version · 76
- emilkowalski/skills★ 57ksame name
- emilkowalski/skill★ 55ksame name
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- spree/spree★ 16ksame name
- usekaneo/kaneo★ 9.8ksame name
- podman-desktop/podman-desktop★ 8.1ksame name
- nightly-labs/openbot★ 7.9ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- plugin87/ux-ui-agent-skills★ 3.2ksame name
- leepokai/Codync★ 2.1ksame name
66 more not listed
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 repository85 other files it gives its agents.
- skills/repo-task-proof-loop/AGENTS.mdAGENTS.md
- skills/repo-task-proof-loop/CLAUDE.mdCLAUDE.md
- agent-desktop-cliSkill
- agents-best-practicesSkill
- agent-transcriptSkill
- ai-stage-gateSkill
- api-connector-builderSkill
- apifySkill
- audit-instruction-systemSkill
- auto-improveSkill
- balancedSkill
- brainstormingSkill
- browser-skillSkill
- china-fashion-shoppingSkill
- chrome-cdpSkill
- cicd-speedupSkill
- coaching-session-summarizerSkill
- codebase-designSkill
- cognitive-toolkitSkill
- data-scraper-agentSkill
- data-throughput-acceleratorSkill
- deep-researchSkill
- deslopSkill
- diagnosing-bugsSkill
- dispatching-parallel-agentsSkill
- documentation-lookupSkill
- domain-modelingSkill
- dreeke-trust-testSkill
- eval-harnessSkill
- evals-from-sessionsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- firecrawlSkill
- first-customer-finderSkill
- github-author-contextSkill
- github-deep-reviewSkill
- gmailSkill
- google-calendarSkill
- grillingSkill
- grill-with-docsSkill
- handoffSkill
- improve-codebase-architectureSkill
- karpathy-guidelinesSkill
- kill-ai-slopSkill
- lossless-doc-compressSkill
- loyalty-privileges-lookupSkill
- make-pr-easy-to-reviewSkill
- markdown-converterSkill
- ml-system-design-reviewSkill
- no-ai-slopSkill
- nutrient-document-processingSkill
- os-what-could-go-wrongSkill
- platform-source-researchSkill
- playwrightSkill
- ponytail-auditSkill
- ponytail-reviewSkill
- posthogSkill
- prompt-caching-playbookSkill
- receiving-code-reviewSkill
- regex-vs-llm-structured-textSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 140 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“Common” is measured: kept by at least 6 in 10 of the 140 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.
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.

