GitHub - dzhng/skills · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
dzhng
skills
Public
Notifications<br>You must be signed in to change notification settings
Fork<br>42
Star<br>606
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>39 Commits<br>39 Commits
.claude-plugin
.claude-plugin
assets
assets
skills
skills
LICENSE
LICENSE
README.md
README.md
View all files
Repository files navigation
Skills
AI skills for building software factories. My personal library of<br>domain-agnostic agent skills, reused across every project. Small, composable,<br>and hackable — works with any harness that supports skills: Claude Code, Codex,<br>opencode, Cursor, duet, and<br>70+ others.
npx skills add dzhng/skills
Add --list to pick individual skills, or copy any skills///<br>folder into your harness's skills directory (e.g. .claude/skills/).
Why
Software is moving from tasks to factories : agents that pursue a goal<br>autonomously until the output can be trusted. The hard part isn't breaking the<br>goal into tasks — it's breaking it into independently verifiable pieces , and<br>knowing where the pieces even are.
These skills run that loop. Treat the unknown as fog of war : map the<br>terrain, carve it into territories that build and verify in isolation, and<br>recursively re-slice whatever hides more map. And re-planning doesn't stop when<br>planning ends — the spec is a living document, updated and re-sliced<br>mid-implementation whenever the work teaches the agent that the plan is stale.<br>Every piece must prove itself — architecture review, code review, and visual<br>review against a baseline — before the loop moves on. Each iteration gets less<br>wrong, until the goal is done.
Proof: one unattended Codex run pursuing a single goal for 1d 16h on top<br>of these skills, slicing and iterating until done.
How to use
Plan. Ask your agent to /write-spec the goal. It interviews you,<br>researches the unknowns, and materializes a spec under specs// —<br>a slice graph where every slice is independently verifiable.
Build. Kick off the loop:
">/goal /implement-spec specs/
Add whatever framing fits: on the xyz branch, or using /codex as the implementer while you stay the parent orchestrator and reviewer.
The rest fires on its own. The spec tells the loop when to call the<br>other skills — a /review pass at the end of every slice,<br>/screenshot-critique and /compare-screenshots on anything<br>visual, /close-spec when the last slice lands — and to update and<br>re-slice the plan whenever implementation proves it stale. Every skill is<br>also independently useful: invoke any of them manually whenever you want.
Skills
Engineering — slice, build, verify, repeat
Skill<br>What it does
explore-unknowns<br>Walk the user through mapping a task's unknowns quadrant by quadrant — known knowns first, then interviews, reactable artifacts, and blindspot passes — ending with a complete four-quadrant map.
write-spec<br>Break a large feature into independently verifiable, human-reviewable slices with API seams and playable checkpoints.
implement-spec<br>Build an existing spec to completion, one reviewable pass at a time, delegating independent slices in parallel.
implement-spec-with-codex<br>Run implement-spec with Codex writing the code — you orchestrate, integrate, and review every pass.
close-spec<br>Archive a shipped spec and rewrite it from a build plan into a durable rationale record that points back at the code.
refactor-clean<br>Refactor by moving ownership to one clean concept instead of layering compatibility sediment beside the problem.
write-tests<br>Write tests one tracer bullet at a time that pin real behavior — not implementation details, config values, or lucky samples.
write-docs<br>Write docs as a glossary of principles and pointers, never a mirror of the code that will rot.
code-review<br>Audit a diff for stale names, dead references, needless complexity, and comments that narrate instead of explain — ending on a clean/not-clean verdict.
audit-choices<br>Audit the choices an implementer made, not its diff — a pure, never-blocking audit whose ledger discloses the architecture and...