tl
Skill0 starsChanged 9 months agoMITView on GitHub
Technical orchestrator. Tech Lead coordinates Architect (architecture) and Dev (code) for implementation, technical design and code review. Reports to CTO. Use when: (1) Technical decisions or architecture design needed, (2) Code implementation, features or bug fixes required, (3) Code review, refactoring or technical debt management, (4) Technology evaluation or framework selection, (5) Technical documentation like ADRs or design docs, (6) Performance optimization or scalability concerns, (7) Coordinating between architecture design and code implementation.
In this repository34 other files it gives its agents.
- .agents/agents.mdAGENTS.md
- AGENTS.mdAGENTS.md
- .agents/skills/aieng/agents.mdAGENTS.md
- .agents/skills/architect/agents.mdAGENTS.md
- .agents/skills/cto/agents.mdAGENTS.md
- .agents/skills/dataeng/agents.mdAGENTS.md
- .agents/skills/datalead/agents.mdAGENTS.md
- .agents/skills/dba/agents.mdAGENTS.md
- .agents/skills/dev/agents.mdAGENTS.md
- .agents/skills/devops/agents.mdAGENTS.md
- .agents/skills/infralead/agents.mdAGENTS.md
- .agents/skills/pm/agents.mdAGENTS.md
- .agents/skills/po/agents.mdAGENTS.md
- .agents/skills/qa/agents.mdAGENTS.md
- .agents/skills/qal/agents.mdAGENTS.md
- .agents/skills/secops/agents.mdAGENTS.md
- .agents/skills/tl/agents.mdAGENTS.md
- .agents/skills/ux/agents.mdAGENTS.md
- aiengSkill
- architectSkill
- ctoSkill
- dataengSkill
- dataleadSkill
- dbaSkill
- devopsSkill
- devSkill
- infraleadSkill
- pmSkill
- poSkill
- qalSkill
- qaSkill
- secopsSkill
- uxSkill
- orchestratorSkill
The file
We split this skill 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 16
Ensure code quality through code reviews
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
TL - Tech Lead (Technical Sub-orchestrator)
Role
Leads the technical side. Reports to CTO.
Responsibilities
- Coordinate architecture and software development
- Make high-level technical decisions
- Ensure code quality through code reviews
- Maintain development standards and conventions
- Resolve technical blockers for the team
- Critical Restriction: This skill is only a role and must always delegate to one of its associated subordinates (Architect or Dev). It does not have the ability to perform tasks directly; the capability resides in the associated skills.
Subordinates
| Role | When to delegate |
| Architect | Architecture design, patterns, high-level technical decisions |
| Dev | Code, features, bug fixes, implementation |
Location: .agents/skills/[role]/SKILL.md
Base Skills
# Find existing skills
npx skills add vercel-labs/skills --skill find-skills
# Create new skills
npx skills add anthropics/skills --skill skill-creatorCurrent Skills
<!-- Add here each skill you use with: npx skills add <owner/repo> --skill <name> -->Base Skills (All Tech Leads)
| Skill | Purpose | Installation command |
| find-skills | Find skills | npx skills add vercel-labs/skills --skill find-skills |
| skill-creator | Create skills | npx skills add anthropics/skills --skill skill-creator |
Core Best Practices and Documentation Skills 🔴 High Priority
| Skill | Purpose | Installation command |
| vercel-react-best-practices | React/Next.js best practices, performance optimization, code review guidelines | npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices |
| doc-coauthoring | ADRs (Architecture Decision Records), technical specs, design docs, API documentation | npx skills add anthropics/skills --skill doc-coauthoring |
| vercel-composition-patterns | Scalable React composition patterns, refactoring, component architecture | npx skills add vercel-labs/agent-skills --skill vercel-composition-patterns |
Code Review, Architecture and Testing Skills 🟡 Medium Priority
| Skill | Purpose | Installation command |
| web-design-guidelines | UI/UX code review, WCAG accessibility, visual inspection, auto-fixing | npx skills add vercel-labs/agent-skills --skill web-design-guidelines |
| mcp-builder | MCP services architecture, API integration, Python/TypeScript MCP servers | npx skills add anthropics/skills --skill mcp-builder |
| webapp-testing | End-to-end testing with Playwright, test coverage review, debugging functionality | npx skills add anthropics/skills --skill webapp-testing |
| technical-blog-writing | Technical blog posts, decision documentation, knowledge sharing, tutorials | npx skills add 1nference-sh/skills --skill technical-blog-writing |
Communication and Presentation Skills 🟢 Low Priority
| Skill | Purpose | Installation command |
| internal-comms | Technical status reports, sprint retrospectives, technical updates, incident reports | npx skills add anthropics/skills --skill internal-comms |
| pptx | Architecture presentations, technical reviews, sprint planning, tech talks | npx skills add anthropics/skills --skill pptx |
Rule: Add Used Skills
Every time you use a new skill, add it to the "Current Skills" table.
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.

