goal-driven-debugging
Focused Codex workflow for bugs, validation changes, vague fixes, and behavior-preserving refactors.
Skill by prmartinow
Chalk Labs
Need help deploying goal-driven-debugging?
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-goal-driven-debugging
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, 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/goal-driven-debugging
What's inside
- Skill name
goal-driven-debugging- Description
- Focused Codex workflow for bugs, validation changes, vague fixes, and behavior-preserving refactors. Use when success must be translated into concrete checks, reproduction steps, targeted tests, or explicit verification before claiming completion.
- License
- MIT
- Instructions
- 29 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Goal-Driven Debugging Use this skill to turn vague work into a concrete goal, a minimal change, and direct verification. ## Loop 1. Define the next concrete success condition. 2. Reproduce, inspect, or otherwise establish current behavior. 3. Make the smallest useful change. 4. Verify with the strongest realistic signal. 5. Repeat until the requested outcome is covered. ## Verification Guidance - Prefer targeted existing tests when they already prove the behavior. - Add focused tests when they are the clearest proof of a bug fix or behavior change. - Use builds, type checks, lint, repro commands, logs, or manual checks when tests are unavailable. - Avoid broad, slow checks when a narrow proof is stronger and faster. - State what remains unverified if full validation is not possible. ## Examples - "Fix the bug" -> reproduce the bug, patch it, verify the failure is gone. - "Add validation" -> define invalid inputs, implement handling, verify outputs. - "Refactor this" -> preserve behavior and verify before/after expectations. Do not declare a bug fixed based on confidence alone.
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
assumption-checking
prmartinow
Focused Codex guardrail for ambiguous or underspecified work.
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
assumption-checking
prmartinow
Focused Codex guardrail for ambiguous or underspecified work.
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 goal-driven-debugging 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
goal-driven-debugging skill. Agent Mart. https://agentmart.dev/skills/prmartinow-goal-driven-debugging (last updated 2026-10-24)