Menu

#923 by GitHub stars

poteto/how

Explain how something works in this codebase by exploring code and producing a clear architectural explanation. Optionally critique the architecture for issues.

Engineering

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/how/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

b1ef42969ea7 → b1ef42969ea7

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → b1ef42969ea7

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit b1ef42969ea7a2bb50aa26c2480274828a0385e7

958GitHub stars
24stars in 7 days
1skill in this repository
0commits in 30 days

Heat

6.0
  • Star growth, last 7 daysAhead of 93% of tracked repositories
  • Star growth, last 24 hoursAhead of 91% of tracked repositories
  • Rank movement, last 7 daysAhead of 47% 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 5, 2026958

Individual skills in this repository

How it works

how

When your agent uses it

Explain how something works in this codebase by exploring code and producing a clear architectural explanation. Optionally critique the architecture for issues.

What it loads into context

Frontmatter

32 tokens

Always available to the agent

SKILL.md

1,635 tokens

When the skill is activated

Reference documents

2,346 tokens

Loaded on request

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

The playbook

  1. Explain Mode
  2. Critique Mode

Files

  • SKILL.mdcore7,543 bytes
  • SKILL.mdcore7,543 bytes
  • references/critic-prompt.mddoc2,413 bytes
  • references/critique-rubric.mddoc3,036 bytes
  • references/explainer-prompt.mddoc3,286 bytes
  • references/explorer-prompt.mddoc2,774 bytes
Read SKILL.md

# How

Explore the codebase to answer "how does X work?" questions. Produce clear architectural explanations at the level of a senior engineer onboarding onto a subsystem — enough to build a working mental model, not so much that it reads like annotated source code.

Two modes:

1. **Explain** (default) — explore the codebase and produce a clear explanation
2. **Critique** — explain first, then spawn multiple models to independently identify architectural issues

## Explain Mode

### Step 1 — Understand the Question and Assess Complexity

Parse what the user is asking about. They might say:
View the complete source on GitHub

Skills included

  • how

Repository facts

License
MIT
Created
Apr 14, 2026
Last pushed
Apr 14, 2026
Forks
50
Open issues
0
Project activity
Slowing

Rank over the last 12 weeks

Now #923 · best #670 · down 171 in 30 days

  1. #916 on Oct 30
  2. #919 on Oct 31
  3. #917 on Nov 1
  4. #916 on Nov 2
  5. #922 on Nov 3
  6. #923 since Nov 4
67 earlier periods
  1. #671 on Aug 2
  2. #712 on Aug 6
  3. #702 on Aug 10
  4. #711 on Aug 11
  5. #702 from Aug 12 to Aug 13
  6. #706 on Aug 17
  7. #722 on Aug 18
  8. #703 on Aug 19
  9. #700 on Aug 20
  10. #701 on Aug 21
  11. #670 on Aug 22
  12. #696 on Aug 23
  13. #723 on Aug 24
  14. #728 on Aug 25
  15. #705 on Aug 26
  16. #717 on Aug 27
  17. #737 on Aug 28
  18. #682 on Aug 29
  19. #721 on Aug 31
  20. #724 on Sep 2
  21. #730 on Sep 3
  22. #702 on Sep 4
  23. #689 on Sep 5
  24. #718 on Sep 6
  25. #752 on Sep 8
  26. #737 on Sep 9
  27. #728 on Sep 11
  28. #722 on Sep 12
  29. #721 on Sep 13
  30. #750 on Sep 14
  31. #741 on Sep 15
  32. #749 on Sep 16
  33. #751 on Sep 17
  34. #748 on Sep 21
  35. #771 on Sep 22
  36. #762 on Sep 23
  37. #728 on Sep 24
  38. #711 on Sep 25
  39. #740 on Sep 27
  40. #760 on Sep 28
  41. #790 on Sep 29
  42. #775 on Sep 30
  43. #715 on Oct 1
  44. #731 on Oct 2
  45. #711 on Oct 3
  46. #734 from Oct 4 to Oct 5
  47. #743 on Oct 6
  48. #752 on Oct 7
  49. #790 on Oct 8
  50. #758 on Oct 9
  51. #743 on Oct 10
  52. #764 on Oct 12
  53. #768 on Oct 13
  54. #778 on Oct 14
  55. #768 on Oct 15
  56. #771 on Oct 16
  57. #750 on Oct 17
  58. #736 on Oct 18
  59. #781 on Oct 19
  60. #784 on Oct 20
  61. #797 on Oct 21
  62. #778 on Oct 22
  63. #783 on Oct 23
  64. #747 on Oct 24
  65. #902 on Oct 25
  66. #912 on Oct 28
  67. #917 on Oct 29

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 4, 2026

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

Show 1 note
  • skills/how/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • No broad tool permissions
  • No dangerous shell commands
  • No network access
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot

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/how/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/how/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/how/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/how/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/how/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/how/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

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

316kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.3kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230kGitHub stars

anthropics/skills

Public repository for Agent Skills

187.9kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

185.5kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

poteto/how: #923 on hotskills, 958 stars

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