Skill Claude Code
Create a prioritized backlog from the technical design.
Agentic system for building software.
This repository also configures its own agents. See what agentic-sdk tells them →
Skill Claude Code
Create a prioritized backlog from the technical design.
Skill Claude Code
Define testable, scoped requirements.
Skill Claude Code
Clarify the user problem, constraints, and success criteria.
Skill Claude Code
Design architecture, components, and data flows.
Skill Claude Code
Design a UI surface before it is implemented, the four-layer procedure (intent, information architecture, interaction, presentation) chosen from tokens, plus the full set of states. Invoked before write-ui when a new or changed UI surface needs a design.
Skill Claude Code
Establish UX guardrails and interaction patterns.
Skill Claude Code
The project's interactive eval loop. Connect once, evaluate small forms, read the value, adjust. The discipline the write-time recipes run inside.
Skill Claude Code
Fix one bug end to end, from reproducer to one commit.
Skill Claude Code
Produce a compact module brief for a dispatched agent, built from disk, returned as the final message, never written to disk.
Skill Claude Code
Build one change end to end on the current tip, review-clean and ready to land.
Skill Claude Code
Promote captured guidance from the inbox into its durable home, empty the inbox, one commit.
Skill Claude Code
Triage an incident to root cause and a follow-up plan.
Skill Claude Code
Toolchain maintenance. The pin, the doctor check, the bump ritual, and the investigated-ceiling cache. Invoked by the verifier agent and maintainer dispatches.
Skill Claude Code
Select and triage the next feature to implement.
Skill Claude Code
Turn a backlog item into slices, a Gherkin spec, and a plan.
Skill Claude Code
Turn a problem or idea into an approved backlog and feature plan.
Skill Claude Code
Decompose a chunk of the approved plan into a forward-only DAG of phases and tasks, write it to plan.edn, return a compact summary.
Skill Claude Code
Write an ADR when an architecture decision is made or work settles a real choice between alternatives.
Skill Claude Code
Run a blameless incident review with action items.
Skill Claude Code
Surface risky assumptions and missing acceptance criteria.
Skill Claude Code
The authoritative procedure for one review round: lanes, reviewer fan-out, spine triage, level-ordered editor waves, integrate, verify, advance.
Skill Claude Code
Run a risk spike: name the load-bearing unknown, time-box it, build a throwaway harness that exercises the seam at and beyond expected load, decide go or no-go or mitigate, feed the outcome forward.
Skill Claude Code
Cut a release end to end, from lane gate to tag and trunk advance.
Skill Claude Code
Turn noisy signals into structured analysis.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: