ai-coding-guardrails
Use when an AI coding agent is writing or refactoring production code and its known failure modes need to be held in check — over-engineering, silent scope…
Skill by OneWave-AI
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/onewave-ai-ai-coding-guardrails
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: writing, 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/ai-coding-guardrails
What's inside
- Skill name
ai-coding-guardrails- Description
- Use when an AI coding agent is writing or refactoring production code and its known failure modes need to be held in check — over-engineering, silent scope creep, invented APIs, claiming work is done without checking, deleting tests to make them pass. Trigger when the user asks for careful, production-grade, or reviewed code, or when a previous agent run produced confident output that turned out wrong.
- License
- MIT
- Instructions
- 52 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# AI Coding Guardrails Coding agents fail in a small number of predictable ways. This is the checklist that catches them before the diff lands. ## The Rules **1. Match the codebase, not your preferences.** Read two or three neighbouring files before writing. Use the project's existing patterns, naming, error handling, and comment density — even when you would have done it differently. A diff that reads like the rest of the repo is the goal. Introducing a new pattern is a decision the user makes, not a default. **2. Change the smallest thing that works.** No speculative abstraction. No config option nobody asked for. No "while I was in here" rewrite. If a fix is three lines, the diff is three lines. Refactors ride separately from behavior changes so a reviewer can see one thing at a time. **3. Never invent an API.** If you cannot see a function's signature in the repo, in installed source, or in the documentation, do not call it. Grep for it first. A plausible-looking method that does not exist is the single most common way agent code fails, and it fails at runtime, in front of the user. **4. Verify before claiming.** "Done" means you ran something and saw it pass. Build, test, hit the endpoint, load the page. If you did not run it, say "untested". Reporting success you did not observe is worse than reporting nothing. **5. Never make a test pass by weakening it.** Deleting an assertion, loosening a matcher, adding a skip, or special-casing the test input is fraud. If the test is genuinely wrong, say so in a sentence and let the user decide. **6. Do not swallow errors.** No empty catch blocks, no `except: pass`, no returning a default to hide a failure. If an error path is intentionally ignored, one comment says why. **7. Read the error before changing anything.** The stack trace usually names the file and the line. Changing code before reading the failure is guessing, and guessing costs more turns than reading. **8. Stay inside the ask.** Fixing an unrelated bug you noticed is a new task, not a bonus. Mention it in a line; do not bundle it. Unrequested changes make a diff unreviewable and break things the user was not watching. **9. Do not delete or rewrite what you did not read.** Before removing code, find out who calls it. Before overwriting a file, read it. "It looked unused" is not a reason. **10. Leave secrets alone.** Never print, commit, or copy keys and tokens. Never hardcode a credential to get something working. Use the env var the project already uses. ## Before Presenting a Diff Run down this list. Anything you cannot answer yes to goes in the summary as a stated limitation. - Did I read the surrounding code before writing? - Does every function I called actually exist? - Did I run it? What was the output? - Is anything in this diff outside what was asked? - Did any test get weaker? - Would a reviewer understand each change without me explaining it? ## Reporting State plainly what you changed, what you verified and how, and what you did not verify. One or two sentences. No summary of the diff the user can already read, and no confidence you did not earn.
From OneWave-AI/claude-skills, MIT.
More from OneWave-AI/claude-skills
- 0.625score
scout-pro
OneWave-AI
Enhanced skill navigator that maps conversation history, recommends multi-skill chains, identifies patterns from past usage, and learns from session outcomes.
SkillAFreshness: A★ 373Claude Code +9 - 0.623score
gillby-water
OneWave-AI
Plan Florida boating, fishing, paddling, surf and beach outings using Gillby's sourced marine forecasts, tides, coastal places and vessel-aware tools.
SkillAFreshness: A★ 373Claude Code +9 - 0.620score
scout
OneWave-AI
Analyzes current conversation context to recommend the best skills and subagents for the task at hand.
SkillAFreshness: A★ 373Claude Code +9 - 0.592score
landing-page-copywriter
OneWave-AI
Writes conversion-focused landing page copy - headlines, subheads, value propositions, feature and benefit blocks, social proof, FAQs, and CTA button text -…
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
design-export-repair
OneWave-AI
Fixes broken decks/PDFs exported from Claude's "Design" feature (or similar AI deck generators) — cut-off or clipped text, wrong/substituted fonts, and…
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
devils-advocate
OneWave-AI
Argues the strongest honest case against a decision, plan, belief, hire, pricing move, strategy, or piece of work the user is leaning toward.
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
csv-excel-merger
OneWave-AI
Merges, appends, joins, and deduplicates multiple CSV, TSV, and Excel files (including multi-sheet workbooks) with pandas - mapping mismatched column names to…
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
code-review-pro
OneWave-AI
Performs a deep code review of files, modules, a diff, or a branch - finding security vulnerabilities (mapped to OWASP Top 10:2025), correctness bugs…
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
crm-data-cleanup
OneWave-AI
Cleans up CRM data from HubSpot, Salesforce, Pipedrive, Zoho, Close, Attio, or any CRM CSV export.
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
bi-measure-builder
OneWave-AI
Writes, explains, debugs, and optimizes BI calculations - Power BI / Fabric DAX measures and calculated columns, Tableau calculated fields…
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
bookkeeping-close
OneWave-AI
Runs small and midsize business bookkeeping operations - categorizes bank and card transactions to a chart of accounts, reconciles a bank or card statement…
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
database-schema-designer
OneWave-AI
Designs relational and document database schemas from requirements or an existing app - tables and collections, keys, relationships, constraints, indexes…
SkillBFreshness: B★ 373Claude Code +9
Signals
- Stars
- 373
- Forks
- 60
- Open issues
- 1
- Last commit (this folder)
- Sep 20, 2026 (1 month ago)
- Last release
- Jun 8, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/OneWave-AI/claude-skills
- Website
- www.onewave-ai.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from OneWave-AI
- 0.625score
scout-pro
OneWave-AI
Enhanced skill navigator that maps conversation history, recommends multi-skill chains, identifies patterns from past usage, and learns from session outcomes.
SkillAFreshness: A★ 373Claude Code +9 - 0.623score
gillby-water
OneWave-AI
Plan Florida boating, fishing, paddling, surf and beach outings using Gillby's sourced marine forecasts, tides, coastal places and vessel-aware tools.
SkillAFreshness: A★ 373Claude Code +9 - 0.620score
scout
OneWave-AI
Analyzes current conversation context to recommend the best skills and subagents for the task at hand.
SkillAFreshness: A★ 373Claude Code +9 - 0.592score
csv-excel-merger
OneWave-AI
Merges, appends, joins, and deduplicates multiple CSV, TSV, and Excel files (including multi-sheet workbooks) with pandas - mapping mismatched column names to…
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
code-review-pro
OneWave-AI
Performs a deep code review of files, modules, a diff, or a branch - finding security vulnerabilities (mapped to OWASP Top 10:2025), correctness bugs…
SkillBFreshness: B★ 373Claude Code +9 - 0.592score
bi-measure-builder
OneWave-AI
Writes, explains, debugs, and optimizes BI calculations - Power BI / Fabric DAX measures and calculated columns, Tableau calculated fields…
SkillBFreshness: B★ 373Claude Code +9
Cite this page
ai-coding-guardrails skill. Agent Mart. https://agentmart.dev/skills/onewave-ai-ai-coding-guardrails (last updated 2026-10-24)