Menu

#726 by GitHub stars

amElnagdy/guard-skills

Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs

EngineeringDocumentation

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/clean-code-guard/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

ffa26036b7b5 → ffa26036b7b5

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → ffa26036b7b5

No earlier version was observed for comparison.

Compare on GitHub

skills/docs-guard/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

ffa26036b7b5 → ffa26036b7b5

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → ffa26036b7b5

No earlier version was observed for comparison.

Compare on GitHub

skills/test-guard/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

ffa26036b7b5 → ffa26036b7b5

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → ffa26036b7b5

No earlier version was observed for comparison.

Compare on GitHub

skills/woo-guard/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

ffa26036b7b5 → ffa26036b7b5

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → ffa26036b7b5

No earlier version was observed for comparison.

Compare on GitHub

skills/wp-guard/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

ffa26036b7b5 → ffa26036b7b5

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → ffa26036b7b5

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit ffa26036b7b5e77b20b5d679304a703b6fd1a43d

1.3kGitHub stars
10stars in 7 days
5skills in this repository
0commits in 30 days

Heat

4.8
  • Star growth, last 7 daysAhead of 79% of tracked repositories
  • Star growth, last 24 hoursAhead of 71% of tracked repositories
  • Rank movement, last 7 daysAhead of 26% of tracked repositories
  • Commits, last 30 daysAhead of 0% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 6, 20261,310

Individual skills in this repository

How it works

clean-code-guard

When your agent uses it

Review generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. Invoke it on your own initiative the moment you finish writing, editing, or refactoring non-trivial production code, before presenting or committing — don't wait to be asked. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).

What it loads into context

Frontmatter

211 tokens

Always available to the agent

SKILL.md

3,921 tokens

When the skill is activated

Reference documents

14,148 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Compatibility
  2. How to use this skill
  3. Examples
  4. Success criteria
  5. Why this skill exists
  6. Always-applied imperatives
  7. Self-check before delivery
  8. When the user pushes back on a rule
  9. Troubleshooting
  10. What this skill does not do

Files

  • SKILL.mdcore17,438 bytes
  • SKILL.mdcore17,438 bytes
  • SKILL.mdcore17,438 bytes
  • SKILL.mdcore17,438 bytes
  • SKILL.mdcore17,438 bytes
  • agents/openai.yamlasset232 bytes
  • references/ai-failure-modes.mddoc16,079 bytes
  • references/comments-and-formatting.mddoc5,203 bytes
  • references/dry-kiss-yagni.mddoc8,819 bytes
  • references/naming-and-functions.mddoc6,494 bytes
  • references/review-checklist.mddoc9,159 bytes
  • references/solid.mddoc10,279 bytes
  • references/sources.mddoc3,250 bytes
Read SKILL.md

# clean-code-guard

You are reviewing generated or changed code before it ships. Apply the rules below as a guard pass after the first implementation pass — and once this skill is active, keep applying it to every later code change in the same session, re-running the self-check before delivery after each edit rather than reverting to unguarded output because the skill loaded earlier. If the user explicitly invokes this skill before writing code, use the same rules while writing and still run the self-check before delivery.

## Compatibility

This is a portable instruction skill. It requires no MCP server, network access,
API key, shell command, local executable, or bundled script. It can be used in
any runtime that supports `SKILL.md` plus directly linked [references/](references/)
files; `agents/openai.yaml` is lightweight display metadata.

This skill does not replace project linters, formatters, type checkers, or test
runners. Use the project's own tools for mechanical verification; use this skill
for the judgement layer around code quality and review.
View the complete source on GitHub

Skills included

  • clean-code-guard
  • docs-guard
  • test-guard
  • woo-guard
  • wp-guard

Repository facts

License
MIT
Created
Jun 6, 2026
Last pushed
Jul 4, 2026
Forks
143
Open issues
1
Project activity
Slowing

Rank over the last 12 weeks

Now #726 · best #503 · down 134 in 30 days

  1. #715 on Nov 1
  2. #716 on Nov 2
  3. #719 on Nov 3
  4. #722 from Nov 4 to Nov 5
  5. #723 on Nov 6
  6. #726 since Nov 7
67 earlier periods
  1. #494 on Aug 2
  2. #495 on Aug 8
  3. #497 on Aug 9
  4. #514 on Aug 11
  5. #513 on Aug 12
  6. #517 from Aug 13 to Aug 14
  7. #498 on Aug 15
  8. #507 on Aug 16
  9. #510 on Aug 17
  10. #519 on Aug 19
  11. #516 on Aug 20
  12. #521 on Aug 21
  13. #503 on Aug 22
  14. #524 on Aug 23
  15. #528 on Aug 24
  16. #537 on Aug 25
  17. #527 on Aug 26
  18. #538 on Aug 27
  19. #537 on Aug 28
  20. #520 on Aug 29
  21. #511 on Aug 30
  22. #537 on Aug 31
  23. #543 on Sep 1
  24. #535 on Sep 2
  25. #541 on Sep 3
  26. #524 on Sep 4
  27. #520 on Sep 5
  28. #535 on Sep 6
  29. #541 on Sep 7
  30. #556 on Sep 8
  31. #541 on Sep 9
  32. #549 on Sep 10
  33. #536 on Sep 12
  34. #559 on Sep 14
  35. #546 on Sep 15
  36. #558 on Sep 16
  37. #555 on Sep 17
  38. #559 on Sep 18
  39. #546 on Sep 19
  40. #574 on Sep 22
  41. #575 on Sep 23
  42. #556 on Sep 24
  43. #579 on Sep 28
  44. #600 on Sep 29
  45. #571 on Oct 1
  46. #580 on Oct 2
  47. #558 on Oct 3
  48. #571 on Oct 4
  49. #592 on Oct 6
  50. #608 on Oct 9
  51. #596 on Oct 11
  52. #612 on Oct 12
  53. #615 on Oct 13
  54. #627 on Oct 14
  55. #623 on Oct 15
  56. #629 on Oct 16
  57. #607 on Oct 18
  58. #636 on Oct 19
  59. #646 on Oct 20
  60. #652 on Oct 21
  61. #634 from Oct 22 to Oct 23
  62. #620 on Oct 24
  63. #697 on Oct 25
  64. #704 on Oct 28
  65. #705 on Oct 29
  66. #708 on Oct 30
  67. #712 on Oct 31

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 10 notes
  • skills/clean-code-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/clean-code-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/clean-code-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/clean-code-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/docs-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/docs-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/docs-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/docs-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/wp-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/wp-guard/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 58 signals by file

skills/clean-code-guard/references/sources.md

  • Network accessline 14
    - **Clean Code sample chapters**: https://ptgmedia.pearsoncmg.com/images/9780132350884/samplepages/9780132350884.pdf
  • Network accessline 15
    - **Command Query Separation, Fowler**: https://martinfowler.com/bliki/CommandQuerySeparation.html
  • Network accessline 16
    - **Refactoring, Fowler**: https://martinfowler.com/books/refactoring.html
  • Network accessline 17
    - **YAGNI, Fowler**: https://martinfowler.com/bliki/Yagni.html
  • Network accessline 18
    - **DRY, The Pragmatic Programmer excerpt**: https://media.pragprog.com/titles/tpp20/dry.pdf
  • Network accessline 19
    - **The Wrong Abstraction, Sandi Metz**: https://sandimetz.com/blog/2016/1/20/the-wrong-abstraction
  • Network accessline 20
    - **SOLID principles, Uncle Bob archive**: http://butunclebob.com/ArticleS.UncleBob.PrinciplesOfOod
  • Network accessline 21
    - **SRP, Uncle Bob**: https://blog.cleancoder.com/uncle-bob/2014/05/08/SingleReponsibilityPrinciple.html
  • Network accessline 22
    - **OCP, Uncle Bob**: https://blog.cleancoder.com/uncle-bob/2014/05/12/TheOpenClosedPrinciple.html
  • Network accessline 23
    - **LSP, Liskov/Wing paper mirror**: https://www.labri.fr/perso/clement/enseignements/ao/LSP.pdf
  • Network accessline 24
    - **DIP, Object Mentor archive**: https://web.archive.org/web/20150924054349/http://www.objectmentor.com/resources/articles/Principles_and_Patterns.pdf
  • Network accessline 28
    - **GitClear AI code quality 2025**: https://www.gitclear.com/ai_assistant_code_quality_2025_research
  • Network accessline 29
    - **Package Hallucinations, Spracklen et al., USENIX Security 2025**: https://www.usenix.org/system/files/conference/usenixsecurity25/sec25cycle1-prepub-742-spracklen.pdf
  • Network accessline 30
    - **AI-Generated Code Considered Harmful**: https://arxiv.org/abs/2409.19182
  • Network accessline 31
    - **A Deep Dive Into LLM Code Generation Mistakes**: https://arxiv.org/abs/2411.01414
  • Network accessline 32
    - **Patterns for Reducing Friction in AI-Assisted Development, Fowler**: https://martinfowler.com/articles/reduce-friction-ai/
  • Network accessline 33
    - **Claude Code issue 6984, mock data generation bias**: https://github.com/anthropics/claude-code/issues/6984
  • Network accessline 34
    - **Karpathy on exception suppression**: https://x.com/karpathy/status/1976077806443569355
  • Network accessline 35
    - **Code Needs Comments**: https://arxiv.org/html/2402.13013v1
  • Network accessline 36
    - **Evaluating the Code Quality of AI-Assisted Code Generation Tools (Copilot, CodeWhisperer, ChatGPT)**: https://arxiv.org/abs/2304.10778
  • Network accessline 37
    - **On Mitigating Code LLM Hallucinations with API Documentation**: https://arxiv.org/abs/2407.09726
  • Network accessline 38
    - **LLM Hallucinations in Practical Code Generation (taxonomy)**: https://arxiv.org/abs/2409.20550
  • Network accessline 39
    - **When Names Disappear: Revealing What LLMs Actually Understand About Code**: https://arxiv.org/abs/2510.03178
  • Network accessline 40
    - **Neural Variable Name Repair**: https://arxiv.org/abs/2512.01141
  • Network accessline 41
    - **Vibe Coding in Practice**: https://arxiv.org/abs/2512.11922
  • Network accessline 45
    - **McCabe NIST 235r**: https://www.mccabe.com/pdf/mccabe-nist235r.pdf
  • Network accessline 46
    - **Cognitive Complexity, SonarSource**: https://www.sonarsource.com/docs/CognitiveComplexity.pdf
  • Network accessline 47
    - **ReSharper cyclomatic complexity threshold guidance**: https://github.com/JetBrains/resharper-cyclomatic-complexity/blob/master/docs/ThresholdGuidance.md

skills/docs-guard/references/code-samples.md

  • Access to secretsline 31
    [Credential-related source omitted]

skills/docs-guard/references/sources.md

  • Network accessline 12
    - Kabir et al., "Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions", CHI 2024 — 52% of answers contained incorrect information; evaluators missed AI errors 39% of the time:
  • Network accessline 13
    - CloudAPIBench, "On Mitigating Code LLM Hallucinations with API Documentation" (AWS, 2024) — 38.58% valid invocations for low-frequency APIs: https://arxiv.org/abs/2407.09726
  • Network accessline 14
    - De-Hallucinator (2024) — LLMs routinely invent non-existent APIs; project-API grounding fixed 63.2% of hallucination-caused failures: https://arxiv.org/abs/2401.01701
  • Network accessline 15
    - Spracklen et al., "We Have a Package for You!" (USENIX Security 2025) — package hallucination averages 19.6% across 16 models: https://www.usenix.org/conference/usenixsecurity25/presentation/spracklen
  • Network accessline 19
    - Diátaxis — the four documentation modes (tutorial, how-to, reference, explanation): https://diataxis.fr/
  • Network accessline 20
    - Write the Docs — style guide collection: https://www.writethedocs.org/guide/writing/style-guides/
  • Network accessline 21
    - RFC 5737 — IPv4 address blocks reserved for documentation: https://www.rfc-editor.org/rfc/rfc5737
  • Network accessline 22
    - Google developer documentation style guide: https://developers.google.com/style

skills/woo-guard/references/sources.md

  • Network accessline 11
    - HPOS (High-Performance Order Storage): https://developer.woocommerce.com/docs/features/high-performance-order-storage/
  • Network accessline 12
    - HPOS recipe book (compatibility patterns): https://developer.woocommerce.com/docs/features/high-performance-order-storage/recipe-book/
  • Network accessline 13
    - CRUD objects: https://developer.woocommerce.com/docs/category/data-management/crud-objects/
  • Network accessline 14
    - Store API: https://developer.woocommerce.com/docs/apis/store-api/
  • Network accessline 15
    - Cart and Checkout Blocks — extensibility: https://developer.woocommerce.com/docs/category/cart-and-checkout-blocks/
  • Network accessline 16
    - Action Scheduler: https://actionscheduler.org/
  • Network accessline 17
    - Payment gateway API: https://developer.woocommerce.com/docs/woocommerce-payment-gateway-api/

skills/wp-guard/SKILL.md

  • Access to secretsline 47
    [Credential-related source omitted]

skills/wp-guard/references/sources.md

  • Network accessline 12
    - Plugin Handbook — Security: https://developer.wordpress.org/plugins/security/
  • Network accessline 13
    - Common APIs Handbook — Sanitizing Data: https://developer.wordpress.org/apis/security/sanitizing/
  • Network accessline 14
    - Common APIs Handbook — Escaping Data: https://developer.wordpress.org/apis/security/escaping/
  • Network accessline 15
    - Nonces: https://developer.wordpress.org/apis/security/nonces/
  • Network accessline 16
    - WordPress Coding Standards (WPCS ruleset): https://github.com/WordPress/WordPress-Coding-Standards
  • Network accessline 17
    - Plugin Handbook — Internationalization: https://developer.wordpress.org/plugins/internationalization/
  • Network accessline 18
    - wpdb::prepare() reference: https://developer.wordpress.org/reference/classes/wpdb/prepare/
  • Network accessline 19
    - REST API Handbook — Adding Custom Endpoints: https://developer.wordpress.org/rest-api/extending-the-rest-api/adding-custom-endpoints/
  • Network accessline 20
    - Options autoloading (WP 6.6+): https://make.wordpress.org/core/2024/06/18/options-api-disabling-autoload-for-large-options/
  • Network accessline 21
    - Script loading strategies (WP 6.3+): https://make.wordpress.org/core/2023/07/14/registering-scripts-with-async-and-defer-attributes-in-wordpress-6-3/
  • Network accessline 25
    - Veracode, 2025 GenAI Code Security Report — 45% of AI-generated samples contained OWASP Top 10 vulnerabilities; XSS failed in 86% of XSS-prone tasks: https://www.veracode.com/resources/analyst-reports/2025-genai-code-security-report/
  • Network accessline 26
    - Perry et al., "Do Users Write More Insecure Code with AI Assistants?", ACM CCS 2023: https://arxiv.org/abs/2211.03622
  • Network accessline 27
    - GitGuardian, State of Secrets Sprawl 2025 — 40% higher secret-leak incidence in Copilot-active repos: https://www.gitguardian.com/state-of-secrets-sprawl-report-2025

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

No combined signals at this commit.

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/clean-code-guard/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/clean-code-guard/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/clean-code-guard/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/clean-code-guard/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/clean-code-guard/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/clean-code-guard/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

michael-denyer/pstack-claude

Antigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for o…

4.1kGitHub stars

Djarvur/go-ultimate

Opinionated Go skill for Claude Code, Codex, Cursor, Copilot & OpenCode — architecture, modern Go, testing, code review, MCP & agent patterns.

31GitHub stars

WatermelonBros/reado

Inverted code review: a read-first IDE where you comment on the lines that matter and your coding agent (Claude Code, Codex, Cursor, Copilot) resolves them. Free and open source.

31GitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.3kGitHub stars

ComposioHQ/awesome-claude-skills

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

79kGitHub stars

asgeirtj/system_prompts_leaks

Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, Op…

71kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

amElnagdy/guard-skills: #726 on hotskills, 1.3k stars

[![amElnagdy/guard-skills on hotskills](https://hotskills.dev/badge/amelnagdy-guard-skills.svg)](https://hotskills.dev/skill/amelnagdy-guard-skills/)