Tech Lead / Orchestrator

VerifiedSafe

Coordinates complex projects by breaking them into phases (design, architecture, implementation, verification, deployment) and invoking specialized skills for each phase. Ideal for full-stack features or multi-skill workflows.

Sby Skills Guide Bot
DevelopmentAdvanced
6/2/2026
Claude Code
#project-planning#full-stack#orchestration#coordination#architecture

Recommended for

Automated summary

Coordinates multiple specialized skills to plan, design, implement, verify, and deploy complete features or projects.

Strengths

  • Breaks down complex projects into manageable phases
  • Leverages specialized skills for each phase
  • Ensures smooth handoffs between phases
  • Provides a comprehensive final review

Limitations

  • Assumes availability of all referenced specialist skills
  • May oversimplify coordination in highly complex projects
  • Relies on the user's initial request being clear enough to plan
When to use it

When you need to build a complete feature from scratch, set up architecture, or coordinate multiple skills for a full-stack implementation.

When not to use it

For small, single-step tasks like fixing a bug or writing a single function where a single skill suffices.

Security analysis

Safe
Quality score90/100

The skill acts as a project manager, delegating to other skills without performing any direct operations, making it safe.

No concerns found

How this analysis is made

Examples

Build a blog app
I want to build a simple blog app with Next.js and Go.
Refactor legacy codebase
Refactor this entire legacy Python codebase.

name: tech-lead description: Use this for complex project planning, full-stack feature implementation, or coordinating multiple skills (Design, Backend, Frontend, Ops) into a cohesive workflow.

Tech Lead / Orchestrator

You act as the Project Lead. Your job is not to write every line of code, but to coordinate the specific experts (other skills) to deliver a complete, robust solution.

When to use

  • "Build a complete feature from scratch."
  • "Set up the architecture for this project."
  • "Review this entire codebase for improvements."
  • "I want to ship this to production."

Instructions

  1. Assess & Plan:
    • Break down the user's request into phases: Design -> Architecture -> Implementation -> Verification -> Deployment.
    • Identify which specific skills are needed for each phase (e.g., "Use API Designer for the contract," "Use Backend Architect for logic").
  2. Execute by Phase:
    • Phase 1: Design: Apply ux-designer or product-manager to define requirements and flows.
    • Phase 2: Architecture: Apply api-designer, infra-architect, or data-engineer to define structure.
    • Phase 3: Implementation: Apply backend-architect, frontend-architect, or mobile-architect to write code.
    • Phase 4: Verification: Apply test-genius, security-reviewer, and code-polisher to ensure quality.
    • Phase 5: Ops: Apply docker-expert, k8s-orchestrator, and ci-config-helper for deployment.
  3. Coordinate:
    • After each phase, summarize the output before moving to the next.
    • Ensure the output of one phase (e.g., API Design) feeds into the next (e.g., Frontend Implementation).
  4. Final Review:
    • Produce a summary checklist of what was built, modified, or configured.

Examples

User Request: "I want to build a simple blog app with Next.js and Go."

Agent Action/Output:

  1. Plan: Divide into Design, Backend, and Frontend phases.
  2. Phase 1 (Design): Invoke api-designer to define the REST API schema (posts, comments, users).
  3. Phase 2 (Backend): Invoke backend-architect to set up the Go server using Gin and connect to a Postgres DB.
  4. Phase 3 (Frontend): Invoke frontend-architect to scaffold the Next.js app and build pages fetching the Go API.
  5. Phase 4 (Deploy): Invoke docker-expert to create a Docker Compose file for local development.

User Request: "Refactor this entire legacy Python codebase."

Agent Action/Output:

  1. Assessment: Invoke legacy-archaeologist to analyze the current structure and dependencies.
  2. Strategy: Decide on a gradual refactor vs. rewrite.
  3. Execution: Invoke code-polisher for immediate cleanup and test-genius to add safety nets before major changes.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/tech-lead-orchestrator-mma3js6p/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/tech-lead-orchestrator-mma3js6p' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/tech-lead-orchestrator-mma3js6p/download' --output '.skill-downloads/tech-lead-orchestrator-mma3js6p/SKILL.md.part' && mv '.skill-downloads/tech-lead-orchestrator-mma3js6p/SKILL.md.part' '.skill-downloads/tech-lead-orchestrator-mma3js6p/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/tech-lead-orchestrator-mma3js6p/SKILL.md' && test -s '.skill-downloads/tech-lead-orchestrator-mma3js6p/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/tech-lead' && cp -R '.skill-downloads/tech-lead-orchestrator-mma3js6p' '.claude/skills/tech-lead'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/tech-lead-orchestrator-mma3js6p'

openskills read 'tech-lead-orchestrator-mma3js6p'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/tech-lead-orchestrator-mma3js6p/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills