architect
Design and implement consequential module, API, state, ownership, or cross-system changes through grounded alternatives and verified delivery.
Skill by lachieh
Chalk Labs
Need help deploying architect?
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.
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/lachieh-architect
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.
About
Use cases: design, backend
Reviews
Write a reviewNo 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 and code. Checked Nov 2, 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/architect
What's inside
- Skill name
architect- Description
- Design and implement consequential module, API, state, ownership, or cross-system changes through grounded alternatives and verified delivery.
- License
- unknown
- Instructions
- 42 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- design-package.md · references/
- design-review.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from lachieh/skills
- 0.565score
create-verification-skill
lachieh
Generate a project-local skill that launches an application, drives its real user surface, and captures behavioral proof.
SkillAFreshness: AClaude Code +9 - 0.561score
arena
lachieh
Produce several independent versions of one consequential artifact, select a base, integrate the strongest compatible ideas, and verify one result.
SkillAFreshness: AClaude Code +9 - 0.561score
interrogate
lachieh
Run an evidence-based, multi-provider adversarial review of a concrete diff, artifact, or existing subsystem against its stated intent.
SkillAFreshness: AClaude Code +9 - 0.561score
no-comments
lachieh
Run an independent review of the comments in a code diff before review, remove accepted findings, and offer executable checks for the constraints comments…
SkillAFreshness: AClaude Code +9 - 0.561score
how
lachieh
Explain how a subsystem works, trace runtime and data flow, and identify current ownership and boundaries.
SkillAFreshness: AClaude Code +9 - 0.561score
herdr-delegation
lachieh
Run a delegated agent or a long-running command in its own Herdr tab and coordinate with it until it reports a verified result.
SkillAFreshness: AClaude Code +9 - 0.559score
correct
lachieh
Find agent mistakes that recur in this repository and change the repository so each class cannot happen again.
SkillAFreshness: AClaude Code +9 - 0.556score
benchmark-checklist
lachieh
Vet a performance measurement before reporting it or acting on it.
SkillAFreshness: AClaude Code +9 - 0.556score
configure-models
lachieh
Resolve a Lachie agent role and size to a concrete model before delegating, or create and update the model configuration that maps roles to provider tiers.
SkillAFreshness: AClaude Code +9 - 0.556score
lachie-mode
lachieh
Lachie's engineering mode for boss-led delegation, strict principles, verified artifacts, and autonomous repository work.
SkillAFreshness: AClaude Code +9 - 0.556score
maintain-verification-skill
lachieh
Audit a project's verification skill and feature map through source coverage and live execution, then ship at most one set of proven corrections.
SkillAFreshness: AClaude Code +9 - 0.556score
principle-attack-the-premise
lachieh
Apply when repeated fixes rely on the same assumption and fail the same check.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (23 days ago)
- Last release
- Oct 23, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/lachieh/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lachieh
- 0.565score
create-verification-skill
lachieh
Generate a project-local skill that launches an application, drives its real user surface, and captures behavioral proof.
SkillAFreshness: AClaude Code +9 - 0.561score
interrogate
lachieh
Run an evidence-based, multi-provider adversarial review of a concrete diff, artifact, or existing subsystem against its stated intent.
SkillAFreshness: AClaude Code +9 - 0.561score
how
lachieh
Explain how a subsystem works, trace runtime and data flow, and identify current ownership and boundaries.
SkillAFreshness: AClaude Code +9 - 0.561score
no-comments
lachieh
Run an independent review of the comments in a code diff before review, remove accepted findings, and offer executable checks for the constraints comments…
SkillAFreshness: AClaude Code +9 - 0.561score
herdr-delegation
lachieh
Run a delegated agent or a long-running command in its own Herdr tab and coordinate with it until it reports a verified result.
SkillAFreshness: AClaude Code +9 - 0.561score
arena
lachieh
Produce several independent versions of one consequential artifact, select a base, integrate the strongest compatible ideas, and verify one result.
SkillAFreshness: AClaude Code +9
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 architect 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.
Cite this page
architect skill. Agent Mart. https://agentmart.dev/skills/lachieh-architect (last updated 2026-10-24)