builder
Global methodology for executing large, multi-step software tasks with discipline.
Skill by leobar37
Chalk Labs
Need help deploying builder?
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. Read the repository before you give any tool access to your data.
npx agentmarket install skill/leobar37-builder
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: productivity
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. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/builder
Tools it pre-approves 7
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Write,Edit,Grep,Glob,Bash,Task
What's inside
- Skill name
builder- Description
- Global methodology for executing large, multi-step software tasks with discipline. Provides task breakdown, delegation patterns, temporary file conventions, checkpoint rules, and concise reporting. Use when approaching any non-trivial implementation, building features, or executing a plan from `planner`. Triggers: build, implement, execute, hacer, construir, implementar.
- License
- unknown
- Allowed tools
- Read,, Write,, Edit,, Grep,, Glob,, Bash,, Task
- Instructions
- 403 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Pre-approves some shell commands
Files (4)
- SKILL.md
- delegation-patterns.md · references/
- temp-file-convention.md · references/
- init-session.sh · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from leobar37/dotfiles
- 0.565score
artifacts-cli
leobar37
Manage and preview HTML artifacts with the artifact CLI (single daemon on port 7000, per-project /p/<id> dashboard URLs).
SkillAFreshness: AClaude Code +9 - 0.565score
orchestration-guide
leobar37
Repo-local navigation guide to phased execution, beta RPC, Climier tracking and the canonical session-broker operations skill.
SkillAFreshness: AClaude Code +9 - 0.560score
climier
leobar37
Execute large plans from planner using climier as task DAG + OMP RPC sessions as workers.
SkillAFreshness: AClaude Code +9 - 0.529score
avileo-storefront
leobar37
Build and integrate a customer-facing Avileo catalog or ecommerce app with the public SDK, Client Keys, TanStack Start, React Query, cart, checkout, and the…
SkillBFreshness: BClaude Code +9 - 0.526score
avileo-catalog
leobar37
Safely connect an external agent to one Avileo business; inspect or manage its profile, products, variants, categories, tags, images, inventory, Client Keys…
SkillBFreshness: BClaude Code +9 - 0.524score
analysis-techniques
leobar37
Lightweight techniques for software analysis when reasoning materially reduces uncertainty: competing root-cause hypotheses, risky cross-layer changes…
SkillBFreshness: BClaude Code +9 - 0.524score
code-review
leobar37
Run a deep, orchestrated code review of a feature, branch, folder, diff, or set of changes using subagent delegation with double-check validation to reduce…
SkillBFreshness: BClaude Code +9 - 0.524score
fal-generate
fal-ai
Generate images and videos using fal.ai AI models with queue support.
SkillBFreshness: BClaude Code +9 - 0.524score
browser-cdp
leobar37
Controla el navegador REAL del usuario (Brave/Chrome con sus sesiones iniciadas) vía el relay CDP local ws://127.0.0.1:9224/cdp desde scripts Bun.
SkillBFreshness: BClaude Code +9 - 0.524score
artifact-base
leobar37
Shared logic for generating visual HTML artifacts from conversation, prompt, or @docs and saving output to docs/artifacts/[slug]/index.html.
SkillBFreshness: BClaude Code +9 - 0.521score
avileo-key-routing
leobar37
Selects the safe Avileo credential boundary for public storefront, Tienda catalog-agent, and System Admin requests.
SkillBFreshness: BClaude Code +9 - 0.519score
build-agents
leobar37
Expert in creating agents for OpenCode AND Claude Code platforms.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/leobar37/dotfiles
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from leobar37
- 0.565score
artifacts-cli
leobar37
Manage and preview HTML artifacts with the artifact CLI (single daemon on port 7000, per-project /p/<id> dashboard URLs).
SkillAFreshness: AClaude Code +9 - 0.565score
orchestration-guide
leobar37
Repo-local navigation guide to phased execution, beta RPC, Climier tracking and the canonical session-broker operations skill.
SkillAFreshness: AClaude Code +9 - 0.560score
climier
leobar37
Execute large plans from planner using climier as task DAG + OMP RPC sessions as workers.
SkillAFreshness: AClaude Code +9 - 0.529score
avileo-storefront
leobar37
Build and integrate a customer-facing Avileo catalog or ecommerce app with the public SDK, Client Keys, TanStack Start, React Query, cart, checkout, and the…
SkillBFreshness: BClaude Code +9 - 0.526score
avileo-catalog
leobar37
Safely connect an external agent to one Avileo business; inspect or manage its profile, products, variants, categories, tags, images, inventory, Client Keys…
SkillBFreshness: BClaude Code +9 - 0.524score
code-review
leobar37
Run a deep, orchestrated code review of a feature, branch, folder, diff, or set of changes using subagent delegation with double-check validation to reduce…
SkillBFreshness: BClaude 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 builder 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
builder skill. Agent Mart. https://agentmart.dev/skills/leobar37-builder (last updated 2026-10-24)