RepoRadar
Leave a Tip
Item detail
github.com

davidondrej/skills

RepoRadar surfaced davidondrej/skills — a 30 installable agent skills acro — into the AI Agent Skills Library section, where it sits at Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.5 out of 10.

Open source →Back to radar
Score8.0
Popularity1.0
Risklow
TierGold
Score breakdown
Usefulness8.0
Novelty7.0
Momentum8.0
Maturity6.3
Open-source/build8.4
Evidence7.2
Workflow potential9.5
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for AI-coding power users, agent developers, automation builders, knowledge workers, technical writers, AI-curious readers, and any developer building a multi-skill agent workflow with an SKILL.md-compatible agent -- and who can pair davidondrej/skills with an Anthropic / OpenAI / DeepSeek / Xiaomi Mimo / Claude / GPT API key for the model surface, an SKILL.md-compatible agent (Claude Code,

Who should use it

AI-coding power users, agent developers, automation builders, knowledge workers, technical writers, AI-curious readers, and any developer building a multi-skill agent workflow with an SKILL.md-compatible agent -- and who can pair davidondrej/skills with an Anthropic / OpenAI / DeepSeek / Xiaomi Mimo / Claude / GPT API key for the model surface, an SKILL.md-compatible agent (Claude Code, Codex, Cursor, OpenCode, etc.) for the install surface, `npx skills add davidondrej/skills` (or `--list` for individual skills) for the skills-install surface, and the maintainer's stack as the reference surfaceEngineering teams that want a broad-scope personal agent skills library -- the 30 installable skills across 5 categories (agent-orchestration + ops-and-setup + research-and-web + skill-authoring + thinking-and-docs) form a coherent, well-organized set that covers most of the common agent workflows; the breadth is the durable differentiator vs. most other skills collections that stop at one or two categoriesEngineering teams that want agent-orchestration primitives -- the 8 skills in skills/agent-orchestration/ (agent-self-scheduling, cmux, codex-goal-loop, delegating-to-agents, fable-safe-prompt, handoff, markdown-rendering, run-deep-swe) cover running, scheduling, delegating to, and coordinating AI coding agents including agent-to-agent workflows, agent loops, and agent benchmarksEngineering teams that want research-and-web primitives -- the 6 skills in skills/research-and-web/ (browser-harness, deep-research, deepapi, pi-web-search, research-prompt, youtube-transcript) cover finding and pulling information from the web, research APIs, browsers, and YouTube; the right primitive for research agents that need to ingest + synthesize external contentEngineering teams that want skill-authoring primitives -- the 4 skills in skills/skill-authoring/ (distribute-skill-to-all-agents, effective-agent-skills, folder-specific-claude-and-agents-md, push-skill-to-github) cover creating, improving, distributing, and publishing Agent Skills and agent context files; the right primitive for teams that want to author their own skills

Who should skip it

Move on from davidondrej/skills if the licensing terms, language support, or platform requirements do not fit your project.

About this signal

davidondrej/skills is tracked by RepoRadar as a 30 installable agent skills acro in the AI Agent Skills Library section. It was first seen on 2026-07-06 and last updated on 2026-07-06. The current verdict is 'try now' with a Gold tier and easy setup difficulty. davidondrej/skills leads on workflow potential (9.5) and setup ease (8.8); its lowest signal is maturity (6.3), so factor that in before investing setup time. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned davidondrej/skills a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

The 1; 412* / 99 KB repo is at active maintenance but the maintainer is a single individual (davidondrej) -- treat the first evaluation cycle as a smoke test (install via `npx skills add davidondrej/skills` + run one of the skills in a target project + confirm the skill loads and the agent executes the workflow correctly) before relying on the 30 skills in production; the agent-orchestration skills (8 skills) wire multiple AI agents together -- the consumer SHOULD audit the agent-orchestration skills carefully before deploying to a multi-agent environment; the research-and-web skills (6 skills) make outbound network calls (browser-harness.

Evidence links
Closest alternatives / related signals
  • No close related item is available in the current public catalog.
open-sourcemitdavidondrej-skillsagent-skills-libraryskill-md30-skills5-categoriesagent-orchestration