Menu

#498 by GitHub stars

mgechev/skills-best-practices

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.

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

skill/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

a0bfa56bbcd6 → a0bfa56bbcd6

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

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → a0bfa56bbcd6

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit a0bfa56bbcd676383f6ca57bb7e344d0856bc38e

2.3kGitHub stars
9stars in 7 days
1skill in this repository
0commits in 30 days

Heat

4.4
  • Star growth, last 7 daysAhead of 66% of tracked repositories
  • Star growth, last 24 hoursAhead of 70% of tracked repositories
  • Rank movement, last 7 daysAhead of 32% 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 7, 20262,292

Individual skills in this repository

How it works

skill-creator

When your agent uses it

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.

What it loads into context

Frontmatter

56 tokens

Always available to the agent

SKILL.md

990 tokens

When the skill is activated

Reference documents

837 tokens

Loaded on request

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

The playbook

  1. Step 1: Initialize and Validate Metadata
  2. Step 2: Structure the Directory
  3. Step 3: Draft Core Logic (SKILL.md)
  4. Step 4: Identify and Bundle Scripts
  5. Step 5: Skill Composition (Optional)
  6. Step 6: Final Logic Validation
  7. Error Handling

Scripts executed separately

  • scripts/validate-metadata.py

Files

  • SKILL.mdcore4,313 bytes
  • SKILL.mdcore4,313 bytes
  • assets/SKILL.template.mddoc974 bytes
  • references/checklist.mddoc2,441 bytes
  • scripts/validate-metadata.pyruns2,013 bytes

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

View the complete source on GitHub

Skills included

  • skill-creator

Repository facts

License
No license detected
Created
Feb 24, 2026
Last pushed
Jul 27, 2026
Forks
169
Open issues
0
Project activity
Slowing

Rank over the last 12 weeks

Now #498 · best #362 · down 66 in 30 days

  1. #488 on Nov 2
  2. #491 on Nov 3
  3. #494 on Nov 4
  4. #493 on Nov 5
  5. #496 on Nov 6
  6. #498 since Nov 7
58 earlier periods
  1. #340 on Aug 2
  2. #348 on Aug 8
  3. #347 on Aug 9
  4. #362 on Aug 11
  5. #356 on Aug 12
  6. #361 on Aug 13
  7. #359 on Aug 14
  8. #357 on Aug 15
  9. #364 on Aug 16
  10. #362 on Aug 17
  11. #369 on Aug 18
  12. #365 on Aug 19
  13. #368 on Aug 20
  14. #367 on Aug 21
  15. #365 on Aug 22
  16. #374 on Aug 24
  17. #375 from Aug 25 to Aug 26
  18. #378 on Aug 27
  19. #379 on Aug 28
  20. #377 on Aug 31
  21. #380 on Sep 2
  22. #385 on Sep 3
  23. #377 on Sep 4
  24. #381 on Sep 5
  25. #377 on Sep 6
  26. #386 on Sep 7
  27. #389 on Sep 8
  28. #387 on Sep 9
  29. #389 on Sep 11
  30. #393 on Sep 12
  31. #398 on Sep 14
  32. #401 on Sep 15
  33. #404 on Sep 20
  34. #402 on Sep 21
  35. #411 on Sep 22
  36. #402 on Sep 23
  37. #408 on Sep 27
  38. #413 on Sep 28
  39. #425 on Sep 29
  40. #407 on Oct 3
  41. #420 on Oct 6
  42. #432 on Oct 8
  43. #439 on Oct 9
  44. #426 on Oct 10
  45. #428 on Oct 11
  46. #438 on Oct 13
  47. #440 on Oct 14
  48. #441 on Oct 15
  49. #446 on Oct 16
  50. #437 on Oct 17
  51. #453 on Oct 19
  52. #454 on Oct 20
  53. #456 on Oct 22
  54. #474 on Oct 25
  55. #482 on Oct 28
  56. #485 on Oct 29
  57. #486 from Oct 30 to Oct 31
  58. #487 on Nov 1

Before you install

Local scripts

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 1 note
  • skill/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
  • 1 executable scriptin 1 file: skill/scripts/validate-metadata.py:1
  • No access to secrets
  • No requests to vote in Hot
Show the signal with its line

skill/scripts/validate-metadata.py

  • Executable scriptline 1
    Executable file

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.

Signal confidence: 1 fact

Works with

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

316.9kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.7kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.3kGitHub 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,…

230.4kGitHub stars

anthropics/skills

Public repository for Agent Skills

188.3kGitHub 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.

186kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

mgechev/skills-best-practices: #498 on hotskills, 2.3k stars

[![mgechev/skills-best-practices on hotskills](https://hotskills.dev/badge/mgechev-skills-best-practices.svg)](https://hotskills.dev/skill/mgechev-skills-best-practices/)