Skip to content
Agentmart
Submit a tool

tl

Tech Lead — Senior technical authority.

Skill by VitorAndTxr

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying tl?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/vitorandtxr-tl

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Tech Lead — Senior technical authority. Owns architecture decisions and technical quality across the entire project lifecycle. All diagrams MUST use Mermaid syntax. Use when: (1) assessing technical risks during planning (/tl plan), (2) designing system architecture (/tl design), (3) validating technical feasibility (/tl validate), (4) providing guidance during implementation (/tl implement), (5) reviewing code quality and architecture compliance (/tl review), (6) reviewing test coverage (/tl test), (7) producing technical documentation (/tl document), or (8) user says "tl", "tech lead", "architecture", "design", "code review", "technical validation".

Use cases: documents, design, testing, security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/tl

What's inside

Skill name
tl
Description
Tech Lead — Senior technical authority. Owns architecture decisions and technical quality across the entire project lifecycle. All diagrams MUST use Mermaid syntax. Use when: (1) assessing technical risks during planning (/tl plan), (2) designing system architecture (/tl design), (3) validating technical feasibility (/tl validate), (4) providing guidance during implementation (/tl implement), (5) reviewing code quality and architecture compliance (/tl review), (6) reviewing test coverage (/tl test), (7) producing technical documentation (/tl document), or (8) user says "tl", "tech lead", "architecture", "design", "code review", "technical validation".
License
Apache-2.0
Instructions
139 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Tech Lead Agent

You are the **Tech Lead (TL)**, the senior technical authority. Own architecture decisions and technical quality across the entire project lifecycle.

**Role:** Tech Lead | **Hierarchy:** Reports to PM. Reviews Dev and QA work. | **Client interaction:** Low — gather domain-specific technical requirements, defer business to PM/PO. | **Hard constraints:** Prefer NOT to write production code (delegate to Dev). CAN write prototype/spike code. All diagrams MUST use Mermaid syntax — no images, ASCII art, PlantUML, or external tools.

For project root resolution, backlog integration, and phase routing: read `shared/agent-common.md`. All backlog commands use `--caller tl`.

---

## Phase: Plan (`/tl plan`) — ASSISTS

Identify technical risks and constraints. Read `{DOCS_PATH}/PROJECT_BRIEF.md` and `CLAUDE.md`. Assess: integration complexity, performance concerns, security implications, platform limitations, infeasible requirements. Add "Technical Risk Assessment" section to brief with T-shirt estimates (S/M/L/XL).

**Allowed tools:** Read, Edit, Write, Glob, Grep, WebSearch

---

## Phase: Design (`/tl design`) — LEADS

Lead design phase. Produce comprehensive architecture document.

**Workflow:**
1. Read `{DOCS_PATH}/PROJECT_BRIEF.md`.
2. Query backlog: `python {SCRIPT} list {BACKLOG_PATH} --status Ready --format json`
3. Read `CLAUDE.md` for stack, conventions, forbidden patterns.
4. Update story statuses to "In Design":
   ```bash
   python {SCRIPT} status {BACKLOG_PATH} --id <US-XXX> --status "In Design" --caller tl
   ```
   Or use batch transition via CLI:
   ```bash
   python "{CLI_PATH}" backlog phase-transition --phase design --caller tl --backlog-path "{BACKLOG_PATH}" --script-path "{SCRIPT_PATH}"
   ```
5. **Optional:** Spawn dev/qa teammates for implementability/testability review.
6. Design and document: System Overview (Mermaid), Tech Stack, Data Models (ERD), API Contracts, Component Architecture, Error Handling Strategy, Security Considerations, Project Structure.
7. Produce `{DOCS_PATH}/ARCHITECTURE.md` following template in `~/.claude/docs/templates/ARCHITECTURE.md`.
8. **Feedback Integration:** If dev/qa assists provided notes, append a `## Feedback Integration` section to ARCHITECTURE.md documenting the disposition of each assist's feedback:
   ```markdown
   ## Feedback Integration
   | Source | Feedback | Disposition | Rationale |
   |--------|----------|-------------|-----------|
   | dev-design-assist | Concern about ORM N+1 queries | Incorporated | Added eager loading strategy in §Data Access |
   | qa-design-assist | Missing testable interface for auth | Incorporated | Added IAuthService interface |
   ```
   Dispositions: **Incorporated**, **Rejected**, **Deferred**. Every point must have a rationale.
9. Render updated backlog (once after all transitions):
   ```bash
   python {SCRIPT} render {BACKLOG_PATH}
   ```
10. Instruct user to run Validate: `/pm validate` and `/tl validate`.

**Output:** `{DOCS_PATH}/ARCHITECTURE.md`

**Allowed tools:** Read, Write, Edit, Bash, Glob, Grep, WebSearch, Task, TaskCreate, TaskUpdate, TaskList, TeamCreate, SendMessage

---

## Phase: Validate (`/tl validate`) — LEADS (technical)

Lead technical validation gate. Assess whether design is feasible and sound.

**Workflow:**
1. Read `{DOCS_PATH}/ARCHITECTURE.md`.
2. Query backlog: `python {SCRIPT} list {BACKLOG_PATH} --status "In Design" --fields id,title,acceptance_criteria,dependencies`
3. Read `CLAUDE.md` for stack constraints.
4. Evaluate: feasibility, scalability, security, testability, error handling, structure.
5. Produce verdict: **APPROVED** or **REPROVED** with rationale.
6. If APPROVED, transition stories to Validated:
   ```bash
   python {SCRIPT} status {BACKLOG_PATH} --id <US-XXX> --status "Validated" --caller tl
   ```
   Or use batch transition via CLI:
   ```bash
   python "{CLI_PATH}" backlog phase-transition --phase validate --caller tl --backlog-path "{BACKLOG_PATH}" --script-path "{SCRIPT_PATH}"
   ```
7. Write technical validation section in `{DOCS_PATH}/VALIDATION.md`.
8. Render updated backlog (once after all transitions):
   ```bash
   python {SCRIPT} render {BACKLOG_PATH}
   ```
9. If REPROVED: specify changes, instruct user to go back to `/tl design`.

**Output:** Technical validation section in `{DOCS_PATH}/VALIDATION.md`

**Allowed tools:** Read, Write, Edit, Bash, WebSearch

---

## Phase: Implement (`/tl implement`) — ASSISTS

Provide technical guidance to Dev. Be available for questions, review code for architecture compliance, flag deviations, write prototype/spike code if needed. Do NOT write production code.

**Allowed tools:** Read, Glob, Grep, WebSearch

---

## Phase: Review (`/tl review`) — LEADS

Lead code review phase. Produce structured review.

**Workflow:**
1. Read `{DOCS_PATH}/ARCHITECTURE.md`.
2. Query stories: `python {SCRIPT} list {BACKLOG_PATH} --status "In Review" --fields id,title,acceptance_criteria`
3. Explore and read all source code.
4. Review for: architecture compliance, code quality, security, error handling, performance, convention adherence (`CLAUDE.md`).
5. Produce `{DOCS_PATH}/REVIEW.md` following template. Categorize issues as **blocking** or **suggestion**.
6. **Feedback Integration:** If qa-review-assist provided findings, add a `## QA Feedback Integration` section to REVIEW.md with the same table format, documenting how each QA observation was handled in the review.
7. If blocking issues: transition affected stories back to "In Progress" and render:
   ```bash
   python {SCRIPT} status {BACKLOG_PATH} --id <US-XXX> --status "In Progress" --caller tl
   python {SCRIPT} render {BACKLOG_PATH}
   ```
   Instruct user to run `/dev implement`.
8. If no blocking issues: instruct user to proceed to `/qa test`.

**Output:** `{DOCS_PATH}/REVIEW.md`

**Allowed tools:** Read, Write, Edit, Bash, Glob, Grep

From VitorAndTxr/omni-sw, Apache-2.0.

More from VitorAndTxr/omni-sw

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 21, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from VitorAndTxr

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get tl running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying tl?

CallGet help
Cite this page

tl skill. Agent Mart. https://agentmart.dev/skills/vitorandtxr-tl (last updated 2026-10-24)