assumption-checking
Focused Codex guardrail for ambiguous or underspecified work.
Skill by prmartinow
Chalk Labs
Need help deploying assumption-checking?
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/prmartinow-assumption-checking
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: backend, data, 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/assumption-checking
What's inside
- Skill name
assumption-checking- Description
- Focused Codex guardrail for ambiguous or underspecified work. Use when a hidden assumption could materially change correctness, safety, user-visible behavior, API shape, data/privacy boundaries, implementation scope, or verification strategy.
- License
- MIT
- Instructions
- 21 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Assumption Checking Use this skill to make important uncertainty visible without turning every ambiguity into a blocking question. ## Rules - Identify the assumption required to move forward. - If the assumption is low-risk, reversible, and locally conventional, state it briefly when useful and proceed. - If the assumption materially changes correctness, safety, scope, data exposure, API contract, or verification, ask one concise narrowing question or present the viable interpretations. - Do not pretend ambiguity does not exist. - Do not ask questions by reflex when a safe assumption is available. - Prefer the simpler interpretation when it satisfies the request and has lower blast radius. ## Good Output - Names the ambiguity early. - Explains why it matters only when useful. - Chooses a path visibly or asks a single targeted question. - Avoids long speculative designs for every possible interpretation.
From prmartinow/karpathy-codex-skill, MIT.
More from prmartinow/karpathy-codex-skill
- 0.479score
karpathy-guidelines
prmartinow
High-frequency Codex behavior guardrail for non-casual technical work, including planning, implementation, debugging, refactoring, review, and completion…
SkillCFreshness: CClaude Code +9 - 0.474score
goal-driven-debugging
prmartinow
Focused Codex workflow for bugs, validation changes, vague fixes, and behavior-preserving refactors.
SkillCFreshness: CClaude Code +9 - 0.474score
simplicity-first
prmartinow
Focused Codex guardrail for avoiding overengineering.
SkillCFreshness: CClaude Code +9 - 0.474score
surgical-changes
prmartinow
Focused Codex guardrail for narrow, reviewable edits.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 11, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from prmartinow
- 0.479score
karpathy-guidelines
prmartinow
High-frequency Codex behavior guardrail for non-casual technical work, including planning, implementation, debugging, refactoring, review, and completion…
SkillCFreshness: CClaude Code +9 - 0.474score
goal-driven-debugging
prmartinow
Focused Codex workflow for bugs, validation changes, vague fixes, and behavior-preserving refactors.
SkillCFreshness: CClaude Code +9 - 0.474score
simplicity-first
prmartinow
Focused Codex guardrail for avoiding overengineering.
SkillCFreshness: CClaude Code +9 - 0.474score
surgical-changes
prmartinow
Focused Codex guardrail for narrow, reviewable edits.
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 assumption-checking 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
assumption-checking skill. Agent Mart. https://agentmart.dev/skills/prmartinow-assumption-checking (last updated 2026-10-24)