superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Iterative product and engineering work with explicit outcomes, evidence, authorization, TDD, and bounded batch coordination.
Plugin lusona from marketplace lusona-ai-skills in Lusona/ai-skills. Commands read from the repo's manifest — today.
architectResolve consequential technical decisions about boundaries, contracts and ownership for a product or change, and produce an ADR in `docs/lusona/adr/` without implementing code. Use when a technical decision with lasting consequences is open. Not for intended behavior or acceptance criteria; use spec
batchCoordinate explicitly authorized unattended work on a fixed selection of queue items through definition, architecture, implementation and independent review, with bounded concurrency, repair budgets and deferral. Produce integrated outcomes, a resumable batch record and an updated queue. Use when th
designCreate UI mockups, screen flows and Mermaid diagrams, and produce an inspectable draft or a chosen visual reference. Use when a screen, flow, state or relationship must be seen to be judged or chosen. Not for consequential boundaries, contracts or ownership; use architect. Not for production UI code
experimentTest an intervention or compare alternatives in a bounded empirical trial with declared criteria and a stopping condition. Produce a disposition of adopt, reject, refine or inconclusive with its evidence. Use when a decision to adopt, reject or refine an approach needs a trial. Not for finding a cau
exploreExplore ideas, decisions, scenarios and long-term possibilities through discussion, and produce clearer understanding, compared alternatives or a supported recommendation. Use when the user wants to reason about a direction, option or future before choosing it. Not for defining the behavior of a cho
frame-productFrame a product's audience, problem, long-term vision, outcomes and boundaries, and produce the product brief in `docs/lusona/product.md`. Use when a product is defined for the first time or its direction changes. Not for capability coverage or delivery order; use map-capabilities. Not for comparing
implementImplement an authorized bounded change in verified increments with explicit TDD, and produce the changed code, check evidence and an updated owning record. Use when a change is authorized for implementation, or when the user asks only for a plan, which ends with a proposed approach and does not auth
investigateReproduce a bug or resolve one bounded technical uncertainty with evidence and distinguishing experiments, and produce supported findings on cause, observed behavior or feasibility. Use when a cause, observed behavior or feasibility question needs evidence. Not for testing an intervention or compari
map-capabilitiesMap capability coverage, dependencies and delivery order toward a product vision, and produce the Capability map in `docs/lusona/product.md`. Use when coverage, dependencies or the next delivery need clarification or revision. Not for a change's detailed behavior; use specify. Not for an unresolved
measureEstablish magnitude, quality, cost or change with comparable observations, and produce a measurement result with its reference, method, uncertainty and the decision it supports. Use when a baseline, benchmark, evaluation or claimed gain needs comparable observations to inform a bounded decision. Not
refactorRestructure implemented product code in bounded, behavior-preserving increments, and produce the changed code, baseline and final regression evidence and an updated owning record. Use when existing code has a concrete structural problem. Not for new behavior or bug fixes; use implement.
reviewReview a specified diff against intended behavior, repository standards and failure cases, and produce a findings report of concrete defects and verification gaps without modifying the implementation. Use when a change needs review or independent review before completion. Not for correcting the find
specifySpecify one bounded feature, bug fix, refactor or other change, and produce a spec in `docs/lusona/specs/` with intended behavior, scope, acceptance criteria and TDD level. Split the spec into work items when the user asks. Use when intended behavior, scope or acceptance needs definition or revision
statusExplain the Lusona workflow, assess project progress from its queue and evidence, and produce a read-only status assessment with the next bounded action and all known remaining work. Use when the user asks for orientation, status, what is left, or how to resume work. Not for starting or continuing u
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.