find-problems
Scan a codebase module-by-module with parallel subagents to find bugs, correctness and security defects, over-engineering, and lean refactoring opportunities…
Skill by LucaNerlich
Chalk Labs
Need help deploying find-problems?
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/lucanerlich-find-problems
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: documents, security
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/find-problems
What's inside
- Skill name
find-problems- Description
- Scan a codebase module-by-module with parallel subagents to find bugs, correctness and security defects, over-engineering, and lean refactoring opportunities, all through the Ponytail lazy-senior-dev lens. Reports only what clears the bar; a clean module — and a whole clean report — is a valid result, so it does not manufacture findings to look thorough. Each finding carries root cause, trigger, blast radius, reproduction, suggested fix, effort, and a cluster key that /create-issues groups by. Use for /find-problems, "find problems", "scan for bugs", "audit the codebase", "find refactoring opportunities".
- License
- unknown
- Instructions
- 227 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- ponytail.LICENSE · references/
- ponytail.md · references/
- usage.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from LucaNerlich/ai-rules-skills
- 0.565score
release-version
LucaNerlich
Cut a release in any repo — derive the next semver from history, promote the changelog, bump every version manifest and lockfile, commit, tag, and push.
SkillAFreshness: AClaude Code +9 - 0.565score
fix-findings
LucaNerlich
Fix every finding /review-issues posted on the pipeline's pull requests: verify the claim first, commit on-layer findings onto the reviewed branch, and file…
SkillAFreshness: AClaude Code +9 - 0.565score
fix-issues
LucaNerlich
Work through GitHub issues labelled priority:high, priority:medium, or priority:low, highest priority first, and land the fixes as file-disjoint stacked PR…
SkillAFreshness: AClaude Code +9 - 0.565score
merge-prs
LucaNerlich
Merge the pull requests the pipeline reviewed and fixed — a gh-stack chain bottom-up with gh stack merge, regular PRs with gh pr merge, or plain git when…
SkillAFreshness: AClaude Code +9 - 0.565score
review-issues
LucaNerlich
Review the pull requests the pipeline opened (the gh-stack chain from /fix-issues) in a fresh context with an adversarial subagent, and post each finding as a…
SkillAFreshness: AClaude Code +9 - 0.565score
session-summary
LucaNerlich
Write a structured session debrief into Obsidian and print a ready-to-paste ticket comment (and PR summary when relevant).
SkillAFreshness: AClaude Code +9 - 0.565score
sweep
LucaNerlich
Run the whole problem pipeline in one command.
SkillAFreshness: AClaude Code +9 - 0.561score
create-issues
LucaNerlich
File report, review, or scan findings as evidence-backed GitHub issues, one per root cause, labelled priority:high/medium/low.
SkillAFreshness: AClaude Code +9 - 0.554score
pstack
LucaNerlich
poteto's engineering stack — rigorous, unslopped agent workflows you can parallelize with confidence.
SkillAFreshness: AClaude Code +9 - 0.474score
ingest
LucaNerlich
Ingest fresh source documents into the AI Wiki knowledge base.
SkillCFreshness: CClaude Code +9 - 0.470score
search
LucaNerlich
Search the AI Wiki knowledge base by keyword and return all relevant pages and sources, ranked, with wikilinks and one-line descriptions.
SkillCFreshness: CClaude Code +9 - 0.405score
codebase-cleanup
LucaNerlich
Deep codebase cleanup and code quality improvement using 8 specialized subagents.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 20, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/LucaNerlich/ai-rules-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from LucaNerlich
- 0.565score
review-issues
LucaNerlich
Review the pull requests the pipeline opened (the gh-stack chain from /fix-issues) in a fresh context with an adversarial subagent, and post each finding as a…
SkillAFreshness: AClaude Code +9 - 0.565score
merge-prs
LucaNerlich
Merge the pull requests the pipeline reviewed and fixed — a gh-stack chain bottom-up with gh stack merge, regular PRs with gh pr merge, or plain git when…
SkillAFreshness: AClaude Code +9 - 0.565score
release-version
LucaNerlich
Cut a release in any repo — derive the next semver from history, promote the changelog, bump every version manifest and lockfile, commit, tag, and push.
SkillAFreshness: AClaude Code +9 - 0.565score
fix-findings
LucaNerlich
Fix every finding /review-issues posted on the pipeline's pull requests: verify the claim first, commit on-layer findings onto the reviewed branch, and file…
SkillAFreshness: AClaude Code +9 - 0.565score
fix-issues
LucaNerlich
Work through GitHub issues labelled priority:high, priority:medium, or priority:low, highest priority first, and land the fixes as file-disjoint stacked PR…
SkillAFreshness: AClaude Code +9 - 0.565score
session-summary
LucaNerlich
Write a structured session debrief into Obsidian and print a ready-to-paste ticket comment (and PR summary when relevant).
SkillAFreshness: AClaude 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 find-problems 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
find-problems skill. Agent Mart. https://agentmart.dev/skills/lucanerlich-find-problems (last updated 2026-10-24)