GitHub user
Agent skills by dzhng
- skills
- 28
- repositories
- 2
Repositories by dzhng
- skillsReusable 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.1k stars · 27 skills
- jevgrepFind code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.2.4k stars · 1 skill
Skills by dzhng, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.Jevgrep A skill your agent uses for questions about how, why, or where behavior works in a repository, including questions that name a function or setting. | dzhng/ | 2.4k | — | ~741 | Automated safety check: Pass | MIT | 5 days ago |
| 2 | Compare screenshots against the intended design, distinguishing approved references from historical baselines. | dzhng/ | 1k | — | ~2.6k | Automated safety check: Pass | MIT | 2 days ago |
| 3 | 3.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. | dzhng/ | 1k | — | ~1.3k | Automated safety check: Pass | MIT | 2 days ago |
| 4 | Refactor cleanly instead of layering sediment. An agent skill from dzhng/skills. | dzhng/ | 1k | — | ~3.1k | Automated safety check: Pass | MIT | 2 days ago |
| 5 | Create or revise agent skills. An agent skill from dzhng/skills. | dzhng/ | 1k | — | ~2.7k | Automated safety check: Pass | MIT | 2 days ago |
| 6 | 6.Codex Use the local Codex CLI as an independent second agent. An agent skill from dzhng/skills. | dzhng/ | 1k | — | ~2.4k | Automated safety check: Warn | MIT | 2 days ago |
| 7 | Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. | dzhng/ | 1k | 1 repo | ~543 | Automated safety check: Pass | MIT | 2 days ago |
| 8 | Audit or rewrite AGENTS.md so it holds only lasting principles. | dzhng/ | 1k | — | ~847 | Automated safety check: Pass | MIT | 2 days ago |
| 9 | 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. | dzhng/ | 1k | — | ~2.5k | Automated safety check: Pass | MIT | 2 days ago |
| 10 | Audit and prioritize performance work through bounded-work and forward-progress checks. | dzhng/ | 1k | — | ~1.3k | Automated safety check: Pass | MIT | 2 days ago |
| 11 | 11.Audit Tests Audit whether tests earn their maintenance cost and which suite owns each contract. | dzhng/ | 1k | — | ~2.4k | Automated safety check: Pass | MIT | 2 days ago |
| 12 | Run fast, progressive experiments to map tunable parameters and their effects. | dzhng/ | 1k | — | ~2.7k | Automated safety check: Pass | MIT | 2 days ago |
| 13 | 13.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… | dzhng/ | 1k | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 14 | Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. | dzhng/ | 1k | — | ~1.1k | Automated safety check: Pass | MIT | 2 days ago |
| 15 | 15.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… | dzhng/ | 1k | — | ~1.9k | Automated safety check: Pass | MIT | 2 days ago |
| 16 | Implement an existing spec through committed passes. An agent skill from dzhng/skills. | dzhng/ | 1k | — | ~3.9k | Automated safety check: Pass | MIT | 2 days ago |
| 17 | 17.Launch Video Make a showreel-grade motion-graphics launch video, with music, that introduces a CLI, library, or product from its repo. | dzhng/ | 1k | — | ~1.7k | Automated safety check: Pass | MIT | 2 days ago |
| 18 | Best-practice rulebook for a marketing site's pages, organized by page class — campaign landers, product pages, programmatic SEO trees, editorial. | dzhng/ | 1k | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 19 | Open image shots (screenshots, snapshot baselines, montages, renders) in ONE macOS Preview window so the user can eyeball them. | dzhng/ | 1k | — | ~509 | Automated safety check: Pass | MIT | 2 days ago |
| 20 | 20.Renderer Architecture rules for GPU rendering with TypeGPU/WebGPU — games, data visualisation, canvases, any app that draws with the GPU. | dzhng/ | 1k | — | ~2.7k | Automated safety check: Pass | MIT | 2 days ago |
| 21 | Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a visual change verified; primed eyes pass… | dzhng/ | 1k | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 22 | 22.Write Docs Write and edit project docs (README/markdown) as a glossary of principles, not a mirror of the code. | dzhng/ | 1k | — | ~930 | Automated safety check: Pass | MIT | 2 days ago |
| 23 | 23.Write Spec Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. | dzhng/ | 1k | — | ~4.7k | Automated safety check: Pass | MIT | 2 days ago |
| 24 | 24.Write Tests Write tests that pin real behavior instead of implementation details, config values, or lucky samples. | dzhng/ | 1k | — | ~2.4k | Automated safety check: Pass | MIT | 2 days ago |
| 25 | 25.Code Review Review changed code for naming, stale references, unnecessary complexity, and comment quality. | dzhng/ | 1k | — | ~5.6k | Automated safety check: Notes | MIT | 2 days ago |
| 26 | 26.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. | dzhng/ | 1k | — | ~470 | Automated safety check: Pass | MIT | 2 days ago |
| 27 | 27.Eli5 Explain a technical spec or proposed change in plain language: what problem it solves, how the solution works, and every schema change. | dzhng/ | 1k | — | ~808 | Automated safety check: Pass | MIT | 2 days ago |
| 28 | 28.Handoff Spec Hand a spec that is mid-implementation to another machine or another agent. | dzhng/ | 1k | — | ~349 | Automated safety check: Pass | MIT | 2 days ago |
Questions, answered from the data.
What is the best skill by dzhng?
Jevgrep from dzhng/jevgrep ranks first of the 28 skills by dzhng listed here, with the highest score: its repository has 2.4k GitHub stars, its SKILL.md loads about 741 tokens and it passes the automated safety check with no findings. Next come Compare Screenshots and Claude.
Are dzhng's skills official?
None yet. All 28 skills by dzhng listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.