agent-skills / architect
CLAUDE.md5 starsChanged 8 months agoMITView on GitHub
In this repository29 other files it gives its agents.
- skills/council/CLAUDE.mdCLAUDE.md
- agent-browserSkill
- app-store-screenshotsSkill
- architectSkill
- architecture-reviewerSkill
- c-cpp-analyzerSkill
- councilSkill
- c-to-rust-migrationSkill
- demo-pipelineSkill
- e2e-pipelineSkill
- founder-modeSkill
- full-evalSkill
- hackathon-jurySkill
- idea-labSkill
- ios-glass-ui-designerSkill
- learn-by-mistakeSkill
- maestro-mobile-testingSkill
- migration-validatorSkill
- mobile-design-systemSkill
- noricum-devSkill
- oss-readinessSkill
- pdf-presentationSkill
- playwright-recordingSkill
- post-run-analysisSkill
- rust-migrationSkill
- ui-ux-polishSkill
- vc-evaluatorSkill
- webreelSkill
- youtube-devrelSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 40
All evaluators respond in the same language the user writes in.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Architect - Multidisciplinary Idea & Project Evaluator
Overview
Architect is a multidisciplinary evaluation system that assesses ideas and existing projects from multiple angles — commercial, educational, social, technical, risk, resource, and innovation perspectives. It uses parallel specialist agents that evaluate independently, then synthesizes their outputs into a unified assessment with scores, recommendations, and actionable next steps.
Data Locations (absolute paths)
- Context:
./data/context.md- Evaluator preferences and skills - Tracking:
./data/tracking/<domain>.md(market, technical, risk, impact, resources, innovation) - Journal:
./data/journal/- Session logs (YYYY-MM-DD-architect-<slug>.md) - Frameworks:
./references/frameworks.md - Scoring Rubrics:
./references/scoring-rubrics.md - Agents:
./agents/- Evaluator and synthesizer agent files - Commands:
./commands/architect*.md- Slash commands
Dual Mode
- New Idea mode: Input is a description/concept. Evaluate from scratch.
- Existing Project mode: Input references a path/codebase. Scan project first, then evaluate both health AND strategic direction.
Evaluator Roster
| Evaluator | Agent File | Auto-Include Rule |
| Risk Assessor | evaluator-risk.md | Always included |
| Technical Architect | evaluator-technical.md | Auto for software ideas/projects |
| Market Analyst | evaluator-market.md | Auto for revenue-generating ideas |
| Impact Evaluator | evaluator-impact.md | Selected by relevance |
| Resource Strategist | evaluator-resources.md | Selected by relevance |
| Innovation Scout | evaluator-innovation.md | Selected by relevance |
Session Protocol
- Read context.md first
- Detect mode (new idea vs existing project)
- For existing projects: run Project Discovery (Explore agent)
- Select and dispatch evaluators in parallel
- Synthesize with synthesizer agent
- Present results
- Discuss and refine
- Save journal + update tracking files
Language
All evaluators respond in the same language the user writes in. Detected automatically.
Key Artifacts
- Value Matrix: Commercial / Educational / Social scores table
- Opportunity Score: 1-10 overall with 6 sub-scores
- Risk Assessment: Go/No-Go recommendation
- Architecture Proposal: For software ideas/projects
- Project Health Score: For existing projects only
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.