Score breakdown
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 dzhng/skills with an Anthropic / OpenAI / DeepSeek / Xiaomi Mimo / Claude / GPT API key for the model surface, an SKILL.md-compatible agent (Claude Code + Code
Who should use it
Who should skip it
Consider dzhng/skills lower priority if you already have a working solution in this category.
About this signal
dzhng/skills is tracked by RepoRadar as a 16 installable skills across 4 c 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 Silver tier and easy setup difficulty. Across RepoRadar's eight signals, dzhng/skills is strongest on workflow potential (9.4) and setup ease (8.8) and weakest on maturity (5.8) — a profile worth weighing against your own priorities. 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 dzhng/skills a composite score of 7.9 out of 10, placing it in the Silver 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 456* / 4848 KB repo is at active maintenance but the maintainer is a single individual (David Zhang / dzhng) -- treat the first evaluation cycle as a smoke test (install via `npx skills add dzhng/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 16 skills in production; the slice-graph + implement-spec loop (write-spec + implement-spec + implement-spec-with-codex + close-spec) writes a spec under specs/<feature>/ + builds it to completion -- the consumer SHOULD review the spec/ folder for sensitive data before deploying to a shared project; the visual review surface (compare-screenshots + screenshot-critique + preview-shots) includes an unprimed subagent that judges visual work -- the consumer SHOULD review the subagent's behavior before deploying to a production visual workflow; the skill authoring surface (write-skills + eval-skills) lets teams author + evaluate their own skills with golden cases -- the consumer SHOULD review the golden cases before deploying to a shared team.