smol-auto
Full pipeline non-stop — plan, build every atomic task, review.
Skill by Poorgramer-Zack
Chalk Labs
Need help deploying smol-auto?
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/poorgramer-zack-smol-auto
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: data, productivity, agent-building
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/smol-auto
What's inside
- Skill name
smol-auto- Description
- Full pipeline non-stop — plan, build every atomic task, review. No mid-pipeline pauses. Use when you trust the agent to take a feature from idea to reviewed implementation in one shot.
- License
- MIT
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
--- name: smol-auto description: Full pipeline non-stop — plan, build every atomic task, review. No mid-pipeline pauses. Use when you trust the agent to take a feature from idea to reviewed implementation in one shot. --- # /smol-auto Conductor enters Auto mode: 1. Invoke `planner` → produce `.smol/plans/<date>-<topic>.md` (via `smol_plan` tool). 2. For each atomic task in plan order: - Invoke `coder` to run RED → GREEN. - On test failure that the coder cannot resolve in one retry, halt the pipeline and report. 3. Invoke `reviewer` once across the full diff. 4. Emit a single final summary: - Tasks completed / skipped - Files changed - Reviewer verdict and issues - Wiki entries appended Do not pause for user confirmation between tasks.
From Poorgramer-Zack/opencode-smol, MIT.
More from Poorgramer-Zack/opencode-smol
- 0.524score
create-opencode-plugin
Poorgramer-Zack
Create OpenCode plugins using the @opencode-ai/plugin SDK.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-build
Poorgramer-Zack
Execute the next pending atomic task from the latest plan in .smol/plans/, using strict TDD.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-fast
Poorgramer-Zack
Skip planning.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-map
Poorgramer-Zack
Build or incrementally update the project codemap at .smol/.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-plan
Poorgramer-Zack
Turn a fuzzy idea into an atomic, TDD-ready task plan saved at .smol/plans/.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-review
Poorgramer-Zack
Review current git diff (staged + unstaged) for correctness, minimalism violations, and security.
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Apr 28, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Poorgramer-Zack/opencode-smol
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Poorgramer-Zack
- 0.524score
create-opencode-plugin
Poorgramer-Zack
Create OpenCode plugins using the @opencode-ai/plugin SDK.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-build
Poorgramer-Zack
Execute the next pending atomic task from the latest plan in .smol/plans/, using strict TDD.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-fast
Poorgramer-Zack
Skip planning.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-map
Poorgramer-Zack
Build or incrementally update the project codemap at .smol/.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-plan
Poorgramer-Zack
Turn a fuzzy idea into an atomic, TDD-ready task plan saved at .smol/plans/.
SkillCFreshness: C★ 4Claude Code +9 - 0.511score
smol-review
Poorgramer-Zack
Review current git diff (staged + unstaged) for correctness, minimalism violations, and security.
SkillCFreshness: C★ 4Claude 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 smol-auto 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
smol-auto skill. Agent Mart. https://agentmart.dev/skills/poorgramer-zack-smol-auto (last updated 2026-10-24)