architect
Skill9 starsChanged 5 months agoMITView on GitHub
Use when making architectural decisions for the Energy/NRG platform. Loads architecture from VISION.md and debates trade-offs using Socratic thinking.
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 145 edited versions we read keep these.
1
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 8
Read these files for architectural grounding:
“Common” is measured: kept by at least 6 in 10 of the 145 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
Context Loading
Read these files for architectural grounding:
docs/vision/VISION.mdlines 1-60 (Super TLDR)docs/vision/VISION.mdlines 203-1000 (How It Actually Works)
Decision Protocol
- State the question clearly — one sentence.
- List 3+ approaches — each with:
- Pros (why this works)
- Cons (what breaks at scale)
- Precedent (who does this already?)
- Second-order thinking — what happens when this scales 100x? What about 1000x?
- Third-order thinking — how does this affect the AutoLab loop? The GEA mesh?
- Recommend one approach with clear justification.
- Name what you're sacrificing — every choice has a cost. State it.
Reference Patterns
- Harness > model (same model, different scaffold → 42% vs 78%)
- Bootstrap memory ≤ 2,000 tokens (Level 1 always loaded)
- Progressive disclosure (load skills on demand, not upfront)
- Model routing by step complexity (Haiku for parsing, Sonnet for reasoning, Opus for architecture)
Other versions156 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- naman10parikh/pixel★ 090% same
- naman10parikh/turbo★ 090% same
Wrote their own version · 154
- agenticnotetaking/arscontexta★ 3.5ksame name
- backnotprop/pstack★ 2.7ksame name
- jsmastery-pro/skills★ 1.4ksame name
- SethGammon/Citadel★ 927same name
- DanMcInerney/architect-loop★ 626same name
- Hainrixz/the-architect★ 562same name
- Trevoke/org-gtd.el★ 485same name
- nagi-studio/skills★ 301same name
- YougLin-dev/Aha-Loop★ 181same name
- antonbabenko/deliberation★ 178same name
144 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.
Used alongsideProjects with it also use poteto-help, principle-explain-the-number 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.
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 9 projects that use this
juancamiloqhzSkillprinciple-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Also in 18 projects that use this
Xia-AtaraxiaSkillmake-bot-ui
Builds a small web page whose buttons wake an agent over a webhook: a local server keeps the sender key server-side and POSTs JSON to a webhook-triggered routine, and the page is exposed on the existing Tailscale node. Use for \"make a bot UI\", \"a dashboard with buttons that trigger the agent\", \"wake the bot from a page\", handing a webhook sender key to the server without pasting it in chat, or putting that UI on the tailnet. Not for general frontend work - use principle-frontend; not for tailnet health or reachability - use tailscale.
Also in 17 projects that use this
jtarorehSkillpoteto-mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Also in 5 projects that use this
jaydubya818Skillprinciple-attack-the-premise
Apply when repeated fixes fail and a shared assumption may be wrong.
Also in 28 projects that use this
- jaydubya818Skill
principle-test-behavior-not-implementation
Apply when tests mirror internals instead of asserting observable outcomes.
Also in 28 projects that use this
- +4 more from jaydubya818
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- agentgrid-orchestrateSkill
- agentgrid-sessionsSkill
- agentgridSkill
- agent-runtimeSkill
- frontend-designSkill
- deep-thinkSkill
- design-systemsSkill
- ecosystem-referenceSkill
- fractal-delegationSkill
- harness-reviewSkill
- heartbeatSkill
- integrate-resourcesSkill
- llm-council-critiqueSkill
- loop-createSkill
- mcp-setupSkill
- memory-compressionSkill
- memorySkill
- model-routingSkill
- oss-project-scaffoldSkill
- playwright-cliSkill
- repo-scoutSkill
- self-improveSkill
- skill-creatorSkill
- skill-routingSkill
- sprintSkill
- test-visualSkill
- troubleshootSkill
- ux-auditSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.