<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs
Devsly

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated 1d ago

by dzhng

skills

Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compatible agents.

  • Active — Updated in the last 14 days
Works with
  • Claude
  • Codex
View on GitHub (opens in a new tab)

1.4k GitHub stars (1,402)

+398 in 30 days

Stars gained per day · daily snapshots since Sep 26
Stars gained per day, Sep 26 to Nov 5: +469 in total; the busiest day was Oct 13 with +205 stars.Sep 27: +2 starsSep 28: +6 starsSep 29: +26 starsSep 30: +5 starsOct 1: +1 starsOct 2: +2 starsOct 3: −1 starsOct 4: +2 starsOct 5: +2 starsOct 6: +26 starsOct 7: +9 starsOct 8: +3 starsOct 9: +4 starsOct 10: +2 starsOct 11: +3 starsOct 12: +15 starsOct 13: +205 starsOct 14: +76 starsOct 15: +13 starsOct 16: +6 starsOct 17: +6 starsOct 18: +1 starsOct 19: +2 starsOct 20: +23 starsOct 21: +4 starsOct 22: 0 starsOct 23: +2 starsOct 24: 0 starsOct 25: +1 starsOct 26: +4 starsOct 27: +1 starsOct 28: +1 starsOct 29: +3 starsOct 30: +1 starsOct 31: +1 starsNov 1: 0 starsNov 2: +4 starsNov 3: +2 starsNov 4: +2 starsNov 5: +4 stars
Stars gained between daily snapshots
PeriodNew stars
Sep 27+2
Sep 28+6
Sep 29+26
Sep 30+5
Oct 1+1
Oct 2+2
Oct 3−1
Oct 4+2
Oct 5+2
Oct 6+26
Oct 7+9
Oct 8+3
Oct 9+4
Oct 10+2
Oct 11+3
Oct 12+15
Oct 13+205
Oct 14+76
Oct 15+13
Oct 16+6
Oct 17+6
Oct 18+1
Oct 19+2
Oct 20+23
Oct 21+4
Oct 220
Oct 23+2
Oct 240
Oct 25+1
Oct 26+4
Oct 27+1
Oct 28+1
Oct 29+3
Oct 30+1
Oct 31+1
Nov 10
Nov 2+4
Nov 3+2
Nov 4+2
Nov 5+4
  • 30 skills (30 skills found in its SKILL.md files)
  • 85 forks (85 forks)
  • 1d ago last update (Last updated 1d ago)

Install

Skills CLI

npx skills add dzhng/skills

Asks which skills and agents to install. Just one: npx skills add dzhng/skills --skill audit-agents — add -g for every project.

Claude Code

git clone https://github.com/dzhng/skillscp -r "skills/skills/authoring/audit-agents" ~/.claude/skills/

Copies the audit-agents skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add dzhng/skills

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md — showing the first 30 of 34 files.

  • audit-agents

    Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.

    skills/authoring/audit-agents/SKILL.md on GitHub (opens in a new tab)

  • eval-skills

    Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expected outcome, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps missing Y", or hands a skill plus example input→expected-output pairs. Pairs wit…

    skills/authoring/eval-skills/SKILL.md on GitHub (opens in a new tab)

  • write-skills

    Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, improving trigger descriptions, or deciding what belongs in a skill versus references, scripts, assets, or ordinary docs.

    skills/authoring/write-skills/SKILL.md on GitHub (opens in a new tab)

  • audit-choices

    Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or comm…

    skills/engineering/audit-choices/SKILL.md on GitHub (opens in a new tab)

  • audit-performance

    Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the next simple performance fixes.

    skills/engineering/audit-performance/SKILL.md on GitHub (opens in a new tab)

  • audit-tests

    Audit whether tests earn their maintenance cost and which suite owns each contract. Use when pruning redundant tests, investigating implementation coupling or test-only production hooks, reviewing the value of proposed coverage, or auditing an entire subsystem. Use write-tests to implement the resulting test changes.

    skills/engineering/audit-tests/SKILL.md on GitHub (opens in a new tab)

  • auto-research

    Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, configurations, or other artifacts against a goal or benchmark, or when a long research run needs a planned hypothesis queue, focused trials, and durable findings.

    skills/engineering/auto-research/SKILL.md on GitHub (opens in a new tab)

  • claude

    Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude. Supports selecting `--model` and thinking/effort level with defaults of the current `opus` alias and `high`.

    skills/engineering/claude/SKILL.md on GitHub (opens in a new tab)

  • close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec…

    skills/engineering/close-spec/SKILL.md on GitHub (opens in a new tab)

  • code-review

    Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.

    skills/engineering/code-review/SKILL.md on GitHub (opens in a new tab)

  • codex

    Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task via `codex exec`, ONLY when the user explicitly asks for Codex to do it. Also covers how to prompt Codex.

    skills/engineering/codex/SKILL.md on GitHub (opens in a new tab)

  • eli5

    Explain a technical spec or proposed change in plain language: what problem it solves, how the solution works, and every schema change.

    skills/engineering/eli5/SKILL.md on GitHub (opens in a new tab)

  • explore-unknowns

    Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a refe…

    skills/engineering/explore-unknowns/SKILL.md on GitHub (opens in a new tab)

  • handoff-spec

    Hand a spec that is mid-implementation to another machine or another agent.

    skills/engineering/handoff-spec/SKILL.md on GitHub (opens in a new tab)

  • implement-spec-with-codex

    Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.

    skills/engineering/implement-spec-with-codex/SKILL.md on GitHub (opens in a new tab)

  • implement-spec-with-goal

    Implement a spec using the harness's goal feature.

    skills/engineering/implement-spec-with-goal/SKILL.md on GitHub (opens in a new tab)

  • implement-spec

    Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat before drift accumulates.

    skills/engineering/implement-spec/SKILL.md on GitHub (opens in a new tab)

  • marketing-pages

    Best-practice rulebook for a marketing site's pages, organized by page class — campaign landers, product pages, programmatic SEO trees, editorial. Use when writing or updating a landing/marketing page, wiring a campaign lander to an attribution identifier, changing site-wide nav/footer links, touching sitemap/robots/agent-readable surfaces, or auditing a public site's indexing, reachability, and…

    skills/engineering/marketing-pages/SKILL.md on GitHub (opens in a new tab)

  • ratchet-files

    Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing. Use when a commit is blocked because a file is over the size budget, when asked to find or split oversized/long/god files, when a file you need to change is too large to read in…

    skills/engineering/ratchet-files/SKILL.md on GitHub (opens in a new tab)

  • refactor-clean

    Refactor cleanly instead of layering sediment. Use for rename requests, stale or misleading names, legacy leftovers, changed scope, or when a change reveals duplicated concepts, local adapters, obsolete owners, redundant inputs or guards, compatibility wrappers, parallel abstractions, an over-large module that has accreted many responsibilities, or "just tack this on" pressure in any code area.

    skills/engineering/refactor-clean/SKILL.md on GitHub (opens in a new tab)

  • retro

    Conduct a retrospective on a coding session.

    skills/engineering/retro/SKILL.md on GitHub (opens in a new tab)

  • review

    Closeout pass on a finished substantive change — sequence refactor-clean (shape), code-review (diff), and write-docs (docs) so all three run, in the order where each feeds the next. Use after implementing a slice or feature and before calling it done or committing; when the user asks for a final review, a cleanup-and-document pass, or to "review everything." For a diff-only audit, reach code-revi…

    skills/engineering/review/SKILL.md on GitHub (opens in a new tab)

  • write-docs

    Write and edit project docs (README/markdown) as a glossary of principles, not a mirror of the code. Use when creating or revising a README; when a doc enumerates exact scenes, scenarios, helpers, class ids, file lists, or command/flag matrices the code already holds; when trimming narrative or changelog out of a doc; or when deduplicating overlapping docs and wiring a root doc to its sub-docs.

    skills/engineering/write-docs/SKILL.md on GitHub (opens in a new tab)

  • write-spec

    Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use for risky or multi-step feature work that needs upfront questioning, API seams, browser-playable checkpoints, HTML visualizations, screenshot gates, staged implementation plans, recursive fog-of-war reslicing, or proactive research into reference implementations/best practices befo…

    skills/engineering/write-spec/SKILL.md on GitHub (opens in a new tab)

  • write-tests

    Write tests that pin real behavior instead of implementation details, config values, or lucky samples. Use when adding tests for new behavior, writing a regression test, fixing a brittle or flaky test, reviewing a test diff, or when a test breaks after a refactor or config change that didn't change behavior.

    skills/engineering/write-tests/SKILL.md on GitHub (opens in a new tab)

  • cinematic-shot

    Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. Use when asked for a launch video, product film, feature trailer, teaser, promo clip, hero shot, or any "c…

    skills/graphics/cinematic-shot/SKILL.md on GitHub (opens in a new tab)

  • isometric-motion

    Build animations and interactive elements (explainers, figures, hero visuals, step-through walkthroughs) in the crafted isometric "Anatomy" style, with many small precise solid parts, four-tone shading, correct painter's order, a framed card with title, hint and live readout, and calm eased motion. Works for physical machines and for abstract concepts (e.g. how an LLM picks its next token), as SV…

    skills/graphics/isometric-motion/SKILL.md on GitHub (opens in a new tab)

  • launch-video

    Make a showreel-grade motion-graphics launch video, with music, that introduces a CLI, library, or product from its repo. Use when asked for a launch, promo, sizzle, or showreel video, an animated intro for a project, or a video to post on X/social.

    skills/graphics/launch-video/SKILL.md on GitHub (opens in a new tab)

  • renderer

    Architecture rules for GPU rendering with TypeGPU/WebGPU. Use when adding or changing render passes, shaders, frame orchestration, GPU resources, culling, terrain, shadows, or visual performance work.

    skills/graphics/renderer/SKILL.md on GitHub (opens in a new tab)

  • xiaohei-illustrations

    Generate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and opinions. Use when the user asks for weird, hand-drawn, Xiaohei, article, editorial, body illustrations, illustration ideas, shot lists, title removal, image edits, or image regeneration. By default, all image text and annotations are English, ev…

    skills/graphics/xiaohei-illustrations/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.