Not in the top 1,000 by GitHub stars

denysdovhan/skills

A collection of custom skills for my workflows with AI-agents

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/agent-log/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

353db84e7c3c → a5441d3a5d40

A local comparison is unavailable. You can inspect the recorded versions on GitHub.

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 Not checked yet

First observation → 353db84e7c3c

No earlier version was observed for comparison.

Compare on GitHub

`skills/commit/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

353db84e7c3c → a5441d3a5d40

A local comparison is unavailable. You can inspect the recorded versions on GitHub.

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 Not checked yet

First observation → 353db84e7c3c

No earlier version was observed for comparison.

Compare on GitHub

`skills/interactive-debugging/SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Not checked yet → After Network or broad shell

353db84e7c3c → a5441d3a5d40

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 Not checked yet

First observation → 353db84e7c3c

No earlier version was observed for comparison.

Compare on GitHub

`skills/readable-code/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → a5441d3a5d40

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit a5441d3a5d40eb00d5c219404d3ae4406be048c7

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/denysdovhan/skills.git .hotskills/denysdovhan-skills && git -C .hotskills/denysdovhan-skills checkout --detach a5441d3a5d40eb00d5c219404d3ae4406be048c7
# Copy each selected skill directory from .hotskills/denysdovhan-skills into .claude/skills/<skill-name>/

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/denysdovhan/skills.git .hotskills/denysdovhan-skills && git -C .hotskills/denysdovhan-skills checkout --detach a5441d3a5d40eb00d5c219404d3ae4406be048c7
# Copy each selected skill directory from .hotskills/denysdovhan-skills into .agents/skills/<skill-name>/

21GitHub stars

0stars in 7 days

4skills in this repository

8commits in 30 days

Heat

1.5

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

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

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

agent-log skills/agent-log
commit skills/commit
interactive-debugging skills/interactive-debugging
readable-code skills/readable-code

How it works

Choose a skill

agent-log

When your agent uses it

Use this skill to maintain an agent log in .agents/log, a decision journal shared by the developer and agents. Trigger when the user explicitly asks to use agent-log or record/update an agent log entry; when planning, implementing, or finalizing a significant feature in a repo with an existing .agents/log; or before non-trivial changes or questions in areas covered by existing entries. Never initialize .agents/log unless the user explicitly asks for an agent log.

What it loads into context

Frontmatter

99 tokens

Always available to the agent

SKILL.md

2,090 tokens

When the skill is activated

Reference documents

60 tokens

Loaded on request

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

The playbook

Layout
Entry Format
Index Format
Recall: Read Before You Write
Write Workflow
Handling Feedback During Implementation
Guidelines

Files

../../.claude-plugin/marketplace.jsonasset472 bytes
../../.claude-plugin/plugin.jsonasset721 bytes
../../assets/dd-skills.svgasset1,355 bytes
README.mddoc225 bytes
SKILL.mdcore10,458 bytes
SKILL.mdcore10,458 bytes
agents/openai.yamlasset293 bytes
assets/agent-log.pngasset1,458 bytes

Read SKILL.md


# Agent Log

Maintain `.agents/log/` — a version-controlled journal of product and engineering decisions, tradeoffs, and directions, co-owned by the developer and agents. Entries capture _why_ — the reasoning that code and git history cannot recover.

## Layout

- `.agents/log/index.md` — index of all entries
- `.agents/log/YYYY-MM-DD-slug.md` — one entry per feature or standalone decision

Initialize `.agents/log/` only when the user explicitly asks — by invoking this skill or directly requesting an agent log. If `.agents/log/` is absent otherwise, do not create it, even when a plan is approved. When initializing, create `.agents/log/index.md` with the table header from Index Format; create an entry only if the current task records a decision.

## Entry Format

```markdown

View the complete source on GitHub

commit

When your agent uses it

Use this skill when an agent needs to prepare a focused commit, follow repository commit-message conventions, write a clear commit message, and create the git commit cleanly.

What it loads into context

Frontmatter

39 tokens

Always available to the agent

SKILL.md

613 tokens

When the skill is activated

Reference documents

56 tokens

Loaded on request

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

The playbook

Goals
Workflow
Commit Message Style
Guidelines

Files

README.mddoc223 bytes
SKILL.mdcore2,862 bytes
SKILL.mdcore2,862 bytes
agents/openai.yamlasset272 bytes
assets/git.pngasset1,266 bytes

Read SKILL.md


# Commit Skill

Use this skill when the work is already implemented and the next step is to create a clean git commit.

## Goals

- Keep the commit scoped to the intended change
- Write a concise, descriptive commit message
- Avoid including unrelated modified files

## Workflow

1. Inspect the working tree before committing.
2. Confirm which files belong to the requested change.

View the complete source on GitHub

interactive-debugging

When your agent uses it

Use this skill when debugging runtime behavior requires live data from the running app, temporary instrumentation, or hypothesis verification through logs. Trigger for async timeouts, stale or incorrect state updates, race conditions, event ordering bugs, intermittent failures, browser/client behavior that static inspection cannot explain, or any issue where the agent should create a local debug HTTP server, insert temporary probes, ask the user to reproduce, inspect .debug/debug.log, then remove all debug instrumentation and assets.

What it loads into context

Frontmatter

101 tokens

Always available to the agent

SKILL.md

1,323 tokens

When the skill is activated

Reference documents

62 tokens

Loaded on request

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

The playbook

Required Paths
Steps
Log Reading Checklist

Scripts executed separately

scripts/debug_server.js
scripts/debug_server.py

Files

README.mddoc256 bytes
SKILL.mdcore5,751 bytes
SKILL.mdcore5,751 bytes
SKILL.mdcore5,751 bytes
SKILL.mdcore5,751 bytes
agents/openai.yamlasset309 bytes
assets/debug.pngasset10,034 bytes
scripts/debug_server.jsruns1,253 bytes
scripts/debug_server.pyruns1,724 bytes

Read SKILL.md


# Interactive Debugging

Use this skill to run a debug loop: hypothesize, instrument, reproduce, inspect runtime logs, fix, verify, and clean up.

## Required Paths

- Debug server: `.debug/debug_server.*`
- Debug log: `.debug/debug.log`
- Default endpoint: `http://localhost:3333/debug`

The bundled servers in this skill's `scripts/` directory (next to this SKILL.md, not in the project being debugged) are intentionally thin. They accept `POST /debug`, append the raw request body to `.debug/debug.log` with a timestamp, and return `ok`.

## Steps

View the complete source on GitHub

readable-code

When your agent uses it

Readable code rules inspired by The Art of Readable Code, for any language with TypeScript/JavaScript as the primary focus. Use when writing, reviewing, or refactoring code in TS, JS, React/JSX, Node, Python, or any other language, including when the user asks to clean up, simplify, untangle, or make code easier to follow. Enforces short functions, flat control flow, clear naming, readable structure, and language idioms.

What it loads into context

Frontmatter

104 tokens

Always available to the agent

SKILL.md

2,297 tokens

When the skill is activated

Reference documents

2,313 tokens

Loaded on request

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

The playbook

How to Apply
1. Keep Functions Short and Focused
2. Flatten Control Flow — No Deep Nesting
3. Name Things Clearly
4. Make Control Flow Easy to Follow
5. Break Down Giant Expressions
6. Extract Unrelated Subproblems
7. One Task at a Time
8. Reduce Variable Scope
9. No Magic Numbers or Strings
10. Fewer Function Arguments
11. Consistency
12. Write Less Code
13. Comments: Explain Why, Not What
14. Design Code to Survive Auto-Formatting

Files

README.mddoc271 bytes
SKILL.mdcore9,366 bytes
agents/openai.yamlasset308 bytes
assets/readable-code.pngasset1,674 bytes
references/python.mddoc3,217 bytes
references/typescript.mddoc5,556 bytes

Read SKILL.md


# Readable Code Rules (/readable-code)

Apply these rules when writing, reviewing, or refactoring code. Inspired by
_The Art of Readable Code_ by Dustin Boswell and Trevor Foucher.

**Core principle: Code should be easy to understand.** The time it takes someone
else (or future you) to understand the code is the ultimate metric.

## How to Apply

- The general rules below apply to every language. Examples use TypeScript.
- Load the language reference for idioms:
  - TypeScript / JavaScript / JSX: [references/typescript.md](references/typescript.md)
  - Python: [references/python.md](references/python.md)

View the complete source on GitHub

Skills included

agent-log
commit
interactive-debugging
readable-code

Repository facts

License: MIT
Created: Feb 4, 2026
Last pushed: Nov 2, 2026
Forks: 0
Open issues: 0
Project activity: Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

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

Show 5 notes

skills/agent-log/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/commit/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/interactive-debugging/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/interactive-debugging/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/interactive-debugging/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
30 network referencesin 4 files: interactive-debugging/SKILL.md:12 .claude-plugin/plugin.json:5 .claude-plugin/marketplace.json:3 and 1 more
No hidden or obfuscated text
No instruction overrides
2 executable scriptsin 2 files: interactive-debugging/scripts/debug_server.js:1 interactive-debugging/scripts/debug_server.py:1
No access to secrets
No requests to vote in Hot

Show all 32 signals by file

`.claude-plugin/marketplace.json`

Network accessline 3

"owner": {     "name": "Denys Dovhan",     "url": "https://github.com/denysdovhan",

Network accessline 4

"name": "Denys Dovhan",     "url": "https://github.com/denysdovhan",     "email": "denysdovhan@gmail.com"

Network accessline 5

"url": "https://github.com/denysdovhan",

`.claude-plugin/plugin.json`

Network accessline 5

"author": {     "name": "Denys Dovhan",     "url": "https://github.com/denysdovhan",

Network accessline 6

"name": "Denys Dovhan",     "url": "https://github.com/denysdovhan",     "email": "denysdovhan@gmail.com"

Network accessline 7

"url": "https://github.com/denysdovhan",

Network accessline 8

"email": "denysdovhan@gmail.com"   },   "repository": "https://github.com/denysdovhan/skills",

Network accessline 9

},   "repository": "https://github.com/denysdovhan/skills",   "license": "MIT",

Network accessline 10

"repository": "https://github.com/denysdovhan/skills",

Network accessline 12

"displayName": "DD Skills",   "icon": "./assets/dd-skills.svg",   "homepage": "https://github.com/denysdovhan/skills#readme",

Network accessline 13

"icon": "./assets/dd-skills.svg",   "homepage": "https://github.com/denysdovhan/skills#readme",   "keywords": ["agent-skills", "git", "debugging", "code-readability", "decision-log"],

Network accessline 14

"homepage": "https://github.com/denysdovhan/skills#readme",

Network accessline 15

"keywords": ["agent-skills", "git", "debugging", "code-readability", "decision-log"],   "documentationUrl": "https://github.com/denysdovhan/skills#readme",   "supportUrl": "https://github.com/denysdovhan/skills/issues"

Network accessline 16

"documentationUrl": "https://github.com/denysdovhan/skills#readme",

Network accessline 17

"supportUrl": "https://github.com/denysdovhan/skills/issues"

`assets/dd-skills.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512" fill="none">

`skills/interactive-debugging/SKILL.md`

Network accessline 12

- Debug server: `.debug/debug_server.*` - Debug log: `.debug/debug.log` - Default endpoint: `http://localhost:3333/debug`

Network accessline 14

- Default endpoint: `http://localhost:3333/debug`

Network accessline 42

- The server is a long-running foreground process; start it in the background (or another terminal) so it does not block your shell. - Use another port only if `3333` is occupied. - Verify it with `curl http://localhost:3333/health`.

Network accessline 43

- Use another port only if `3333` is occupied. - Verify it with `curl http://localhost:3333/health`. - Clear `.debug/debug.log` before reproduction if it already exists.

Network accessline 44

- Verify it with `curl http://localhost:3333/health`.

Network accessline 53

// #region DEBUG fetch("http://localhost:3333/debug", {

Network accessline 54
```
fetch("http://localhost:3333/debug", {
```
Network accessline 73
```
try:     urllib.request.urlopen(
```
Network accessline 74
```
urllib.request.urlopen(
```
Network accessline 75
```
urllib.request.Request(
```
Network accessline 76
```
"http://localhost:3333/debug",
```

Network accessline 94

begin   Net::HTTP.post(     URI("http://localhost:3333/debug"),

Network accessline 95

Net::HTTP.post(     URI("http://localhost:3333/debug"),     { event: "function-entry", value: value }.to_json,

Network accessline 96
```
URI("http://localhost:3333/debug"),
```

`skills/interactive-debugging/scripts/debug_server.js`

Executable scriptline 1
```
#!/usr/bin/env node
```

`skills/interactive-debugging/scripts/debug_server.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.

Signal confidence: 16 facts

Network access in prose of the SKILL.mdinteractive-debugging/SKILL.md:12Low confidence
Network access in prose of the SKILL.mdinteractive-debugging/SKILL.md:14Low confidence
Network access in prose of the SKILL.mdinteractive-debugging/SKILL.md:42Low confidence
Network access in prose of the SKILL.mdinteractive-debugging/SKILL.md:43Low confidence
Network access in prose of the SKILL.mdinteractive-debugging/SKILL.md:44Low confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:53High confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:54High confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:73High confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:74High confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:75High confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:76High confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:94High confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:95High confidence
Network access in code of the SKILL.mdinteractive-debugging/SKILL.md:96High confidence
Executable script in code of a file that runsinteractive-debugging/scripts/debug_server.js:1High confidence
Executable script in code of a file that runsinteractive-debugging/scripts/debug_server.py:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Manifest .claude-plugin/marketplace.json	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md skills/agent-log/SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md skills/agent-log/SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md skills/agent-log/SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md skills/agent-log/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.

denysdovhan/skills

History

skills/agent-log/SKILL.md

skills/commit/SKILL.md

skills/interactive-debugging/SKILL.md

skills/readable-code/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

agent-log

Frontmatter

SKILL.md

Reference documents

The playbook

Files

commit

Frontmatter

SKILL.md

Reference documents

The playbook

Files

interactive-debugging

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

readable-code

Frontmatter

SKILL.md

Reference documents

The playbook

Files

Skills included

Repository facts

Before you install

.claude-plugin/marketplace.json

.claude-plugin/plugin.json

assets/dd-skills.svg

skills/interactive-debugging/SKILL.md

skills/interactive-debugging/scripts/debug_server.js

skills/interactive-debugging/scripts/debug_server.py

How the signals fit together

Works with

You might also use

fabricioctelles/skills

backnotprop/pstack

mxyhi/ok-skills

aiskillstore/marketplace

tobihagemann/turbo

seb1n/awesome-ai-agent-skills

`skills/agent-log/SKILL.md`

`skills/commit/SKILL.md`

`skills/interactive-debugging/SKILL.md`

`skills/readable-code/SKILL.md`

`.claude-plugin/marketplace.json`

`.claude-plugin/plugin.json`

`assets/dd-skills.svg`

`skills/interactive-debugging/SKILL.md`

`skills/interactive-debugging/scripts/debug_server.js`

`skills/interactive-debugging/scripts/debug_server.py`