Menu

#662 by GitHub stars

michaelshimeles/rstack

Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.

CodexEngineeringOperations

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

before-and-after/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

code-structure/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

evidence-driven-testing/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

greploop/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

greploop-apps/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

new-feature/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

unslop/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

11b15767d758 → 11b15767d758

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 11b15767d7587bab11f6c4957507b5f26d1785c7

git clone --filter=blob:none --no-checkout https://github.com/michaelshimeles/rstack.git .hotskills/michaelshimeles-rstack && git -C .hotskills/michaelshimeles-rstack checkout --detach 11b15767d7587bab11f6c4957507b5f26d1785c7 # Copy each selected skill directory from .hotskills/michaelshimeles-rstack into .agents/skills/<skill-name>/
1.5kGitHub stars
36stars in 7 days
7skills in this repository
3commits in 30 days

Heat

7.2
  • Star growth, last 7 daysAhead of 93% of tracked repositories
  • Star growth, last 24 hoursAhead of 92% of tracked repositories
  • Rank movement, last 7 daysAhead of 66% of tracked repositories
  • Commits, last 30 daysAhead of 64% 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 7, 20261,456

Individual skills in this repository

How it works

before-and-after

When your agent uses it

Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.

What it loads into context

Frontmatter

194 tokens

Always available to the agent

SKILL.md

1,156 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

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

The playbook

  1. Agent Behavior Rules
  2. Capture and delivery
  3. Quick Reference
  4. Image Upload
  5. Vercel Deployment Protection
  6. PR Integration
  7. Error Reference

Scripts executed separately

  • scripts/adapters/0x0st.sh
  • scripts/adapters/blob.sh
  • scripts/upload-and-copy.sh

Files

  • LICENSEasset1,231 bytes
  • SKILL.mdcore4,535 bytes
  • SKILL.mdcore4,535 bytes
  • SKILL.mdcore4,535 bytes
  • SKILL.mdcore4,535 bytes
  • SKILL.mdcore4,535 bytes
  • SKILL.mdcore4,535 bytes
  • scripts/adapters/0x0st.shruns728 bytes
  • scripts/adapters/blob.shruns1,336 bytes
  • scripts/upload-and-copy.shruns3,440 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

  • before-and-after
  • code-structure
  • evidence-driven-testing
  • greploop
  • greploop-apps
  • new-feature
  • unslop

Repository facts

License
No license detected
Created
Mar 5, 2026
Last pushed
Nov 5, 2026
Forks
245
Open issues
5
Project activity
Active

Rank over the last 12 weeks

Now #662 · best #567 · down 44 in 30 days

  1. #661 on Nov 1
  2. #660 on Nov 2
  3. #665 on Nov 3
  4. #662 on Nov 4
  5. #661 from Nov 5 to Nov 6
  6. #662 since Nov 7
70 earlier periods
  1. #847 on Aug 2
  2. #852 on Aug 8
  3. #900 on Aug 13
  4. #881 on Aug 14
  5. #874 on Aug 16
  6. #881 on Aug 17
  7. #881 on Aug 20
  8. #889 on Aug 21
  9. #947 on Aug 28
  10. #862 on Aug 29
  11. #865 on Aug 30
  12. #934 on Sep 1
  13. #874 on Sep 2
  14. #873 on Sep 3
  15. #824 on Sep 4
  16. #800 on Sep 5
  17. #819 on Sep 6
  18. #828 on Sep 7
  19. #847 on Sep 8
  20. #826 on Sep 9
  21. #828 on Sep 10
  22. #803 on Sep 11
  23. #796 on Sep 12
  24. #788 on Sep 13
  25. #768 on Sep 14
  26. #716 on Sep 15
  27. #706 on Sep 16
  28. #673 on Sep 17
  29. #663 on Sep 18
  30. #631 on Sep 19
  31. #639 on Sep 20
  32. #649 on Sep 21
  33. #654 on Sep 22
  34. #646 on Sep 23
  35. #614 on Sep 24
  36. #591 on Sep 25
  37. #579 on Sep 26
  38. #599 on Sep 27
  39. #600 on Sep 28
  40. #624 on Sep 29
  41. #607 on Sep 30
  42. #585 on Oct 1
  43. #590 on Oct 2
  44. #567 on Oct 3
  45. #579 on Oct 4
  46. #585 on Oct 5
  47. #594 on Oct 6
  48. #591 on Oct 7
  49. #618 on Oct 8
  50. #602 on Oct 9
  51. #587 on Oct 10
  52. #583 on Oct 11
  53. #591 on Oct 12
  54. #594 on Oct 13
  55. #606 on Oct 14
  56. #604 on Oct 15
  57. #611 on Oct 16
  58. #596 on Oct 17
  59. #588 on Oct 18
  60. #608 on Oct 19
  61. #618 on Oct 20
  62. #620 on Oct 21
  63. #606 on Oct 22
  64. #593 on Oct 23
  65. #588 on Oct 24
  66. #656 on Oct 25
  67. #659 on Oct 28
  68. #663 on Oct 29
  69. #658 on Oct 30
  70. #659 on Oct 31

Before you install

Network or broad shell

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 24 notes
  • before-and-after/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • before-and-after/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • before-and-after/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • before-and-after/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • before-and-after/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • evidence-driven-testing/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • greploop-apps/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 44 signals by file

before-and-after/LICENSE

  • Network accessline 27
    For more information, see https://polyformproject.org/licenses/shield/1.0.0

before-and-after/SKILL.md

  • Broad permissionsline 1
    Bash(npx @vercel/before-and-after *)
  • Network accessline 1
    --- name: before-and-after description: Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and
  • Network accessline 2
    name: before-and-after description: Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new
  • Network accessline 3
    description: Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document
  • Network accessline 8
    - Bash(npm install -g @vercel/before-and-after)   - Bash(*/upload-and-copy.sh *)   - Bash(curl -s -o /dev/null -w *)
  • Network accessline 9
    - Bash(*/upload-and-copy.sh *)   - Bash(curl -s -o /dev/null -w *)   - Bash(gh pr view *)
  • Network accessline 10
    - Bash(curl -s -o /dev/null -w *)

before-and-after/scripts/adapters/0x0st.sh

  • Executable scriptline 1
    #!/bin/bash
  • Network accessline 2
    # 0x0.st adapter - Free, no-signup file hosting # https://0x0.st
  • Network accessline 3
    # https://0x0.st
  • Network accessline 28
    URL=$(curl -s -A "before-after-cli/1.0" -F "file=@$FILE" https://0x0.st)

before-and-after/scripts/adapters/blob.sh

  • Executable scriptline 1
    #!/bin/bash
  • Network accessline 32
    echo "" >&2     echo "Set it with:" >&2     echo "  export BLOB_UPLOAD_URL='https://your-blob-service.com/upload'" >&2
  • Network accessline 33
    echo "Set it with:" >&2     echo "  export BLOB_UPLOAD_URL='https://your-blob-service.com/upload'" >&2     exit 1
  • Network accessline 34
    echo "  export BLOB_UPLOAD_URL='https://your-blob-service.com/upload'" >&2
  • Network accessline 39
    RESPONSE=$(curl -s -X POST -F "file=@$FILE" "$BLOB_UPLOAD_URL")

before-and-after/scripts/upload-and-copy.sh

  • Executable scriptline 1
    #!/bin/bash

evidence-driven-testing/SKILL.md

  • Network accessline 208
    When a display exists but the agent has no built-in computer-use capability, use [cua-driver](https://github.com/trycua/cua) (macOS / Windows / Linux) as
  • Network accessline 209
    use [cua-driver](https://github.com/trycua/cua) (macOS / Windows / Linux) as
  • Network accessline 277
    try {       const page = await context.newPage();       await page.goto("http://localhost:3000/path-under-test");
  • Network accessline 278
    const page = await context.newPage();       await page.goto("http://localhost:3000/path-under-test");       // Drive the flow and check each expected state here.
  • Network accessline 279
    await page.goto("http://localhost:3000/path-under-test");

evidence-driven-testing/scripts/evidence.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 76
    [Credential-related source omitted]
  • Access to secretsline 172
    [Credential-related source omitted]
  • Access to secretsline 188
    [Credential-related source omitted]
  • Access to secretsline 189
    [Credential-related source omitted]
  • Access to secretsline 410
    [Credential-related source omitted]
  • Access to secretsline 466
    [Credential-related source omitted]
  • Access to secretsline 468
    [Credential-related source omitted]

evidence-driven-testing/scripts/playwright/package-lock.json

  • Network accessline 14
    "node_modules/playwright": {       "version": "1.63.0",       "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.63.0.tgz",
  • Network accessline 15
    "version": "1.63.0",       "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.63.0.tgz",       "integrity": "sha512-+7ziBLidS4NaNCdt57SUDT+wYmmd5fmiQejUic/kb+YsYSCPyOOE9sebzMjNmQrsnNpDJqd4WHvV/8lfKfUDUg==",
  • Network accessline 16
    "resolved": "https://registry.npmjs.org/playwright/-/playwright-1.63.0.tgz",
  • Network accessline 29
    "node_modules/playwright-core": {       "version": "1.63.0",       "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.63.0.tgz",
  • Network accessline 30
    "version": "1.63.0",       "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.63.0.tgz",       "integrity": "sha512-rYCsBF/M5HjUch52bbtVONEFjv6Xu8sm8h72dNlR5bzIE1fvC/bxgspzkjSfU+MweEMmPM8KJebG6nnyxo5mCg==",
  • Network accessline 31
    "resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.63.0.tgz",

evidence-driven-testing/scripts/playwright/package.json

  • Executable scriptline 1
    Executable file

evidence-driven-testing/scripts/run-playwright.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Dangerous shell operationline 14
    trap 'rm -rf -- "$CAPTURE_DIR"' EXIT

greploop/references/github.md

  • Network accessline 72
    API fields: [check runs](https://docs.github.com/en/rest/checks/runs),
  • Network accessline 73
    [PR reviews](https://docs.github.com/en/rest/pulls/reviews).

greploop/references/gitlab-api.md

  • Network accessline 61
    Field definitions: [GitLab discussions API](https://docs.gitlab.com/api/discussions/).

greploop/scripts/github_review.py

  • Executable scriptline 1
    #!/usr/bin/env python3

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.

Declared and executed: 1 fact
Signal confidence: 37 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md before-and-after/SKILL.md.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md before-and-after/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md before-and-after/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md before-and-after/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md before-and-after/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

dagoSte/squadra

Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall less…

1.1kGitHub stars

NoobyGains/godmode

Engineering discipline for AI coding agents: question the request, verify against current docs, plan, build test-first on the cheapest capable model, review with a second model fa…

118GitHub stars

Da7-Tech/SureForge

Agent Skill for complex work: research before asking, ask before planning, plan before building, verify before delivering, independent review before calling it done. Plain text, n…

137GitHub stars

dengyie/awesome-skills

Production-ready, modular Agent Skills for software engineering, code quality review, network tunneling, and UI components. Compatible with Claude Code, Codex, and Cursor.

78GitHub stars

ComposioHQ/awesome-claude-skills

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

79kGitHub stars

FrancyJGLisboa/agent-skills-platform

Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

2.4kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

michaelshimeles/rstack: #662 on hotskills, 1.5k stars

[![michaelshimeles/rstack on hotskills](https://hotskills.dev/badge/michaelshimeles-rstack.svg)](https://hotskills.dev/skill/michaelshimeles-rstack/)