Chalk Labs
Need help deploying sbs-coplan?
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/balmasi-sbs-coplan
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: testing, 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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/sbs-coplan
What's inside
- Skill name
sbs-coplan- Description
- Co-plans through a deep, one-question-at-a-time interview. Use when the user wants to make a plan, clarify an approach, choose among options, or stress-test a proposal before acting.
- License
- MIT
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Run a deep interview, starting with the highest-leverage unresolved question. Ask one question at a time and wait for feedback; on request, batch any number of independent questions in parallel (default 3). For each decision, offer one or more recommendations with trade-offs. Think deeply; present sharply. Close the loop on each decision before moving on: trace its material consequences, reconcile it with earlier choices, and resolve resulting questions. Challenge vague language, contradictions, and hidden assumptions with concrete input–outcome examples and boundary cases. Keep it grounded: inspect the project instead of asking questions it can answer. Continue until confident you and the user share a complete, actionable understanding.
From balmasi/skill-or-be-skilled, MIT.
More from balmasi/skill-or-be-skilled
- 0.529score
sbs-context-audit
balmasi
Measures a coding agent's first-prompt context cost by tool and agent-specific group from its captured API request.
SkillBFreshness: BClaude Code +9 - 0.529score
sbs-reflect
balmasi
Reviews agent conversations to find repeated friction, missed skill opportunities, and workflow loops worth improving.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 27, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/balmasi/skill-or-be-skilled
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from balmasi
- 0.529score
sbs-reflect
balmasi
Reviews agent conversations to find repeated friction, missed skill opportunities, and workflow loops worth improving.
SkillBFreshness: BClaude Code +9 - 0.529score
sbs-context-audit
balmasi
Measures a coding agent's first-prompt context cost by tool and agent-specific group from its captured API request.
SkillBFreshness: BClaude Code +9 - 0.474score
substack-seo-geo
balmasi
Pre-review SEO/AEO/GEO and editorial-polish audit of a single Substack post draft.
SkillCFreshness: CClaude Code +9 - 0.474score
slop-mop
balmasi
Prevent, detect, and remove AI-sounding prose in public-facing writing.
SkillCFreshness: CClaude Code +9 - 0.474score
docling-convert
balmasi
Convert PDF, DOCX, PPTX, HTML, and image documents to normalized Markdown with extracted images and optional VLM auto-captions.
SkillCFreshness: CClaude Code +9 - 0.474score
transcribe
balmasi
Run local speech transcription from audio or video files with ffmpeg media prep and a local Parakeet (default) or Voxtral model.
SkillCFreshness: CClaude 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 sbs-coplan 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
sbs-coplan skill. Agent Mart. https://agentmart.dev/skills/balmasi-sbs-coplan (last updated 2026-10-24)