kanso
claudeClaude Code skills that keep AI-written code short and honest. Delete before you add, earn every line.
12 skills · hooks
Agent-orchestration skills for Claude Code. Fan work out in parallel, pick winners, and delegate execution to cheaper models, all under a hard cost ceiling.
Plugin swarm from marketplace cyze in blakecyze/skills. Commands read from the repo's manifest — today.
swarm-bulldozeUse when the user wants to try several independent approaches to the same problem and keep the best one. Best-of-N generation. Expensive by design; respects the cost ceiling.
swarm-executeUse when the user wants to run plans written by /swarm-improve, execute a plans/ backlog, or dispatch mechanical work to a cheaper model. The pair of /swarm-improve: it planned, this executes.
swarm-exploreUse when the user wants to map a large codebase, gather context from many files at once, or investigate a problem space in parallel. Read-only fan-out. Never writes.
swarm-improveUse when the user wants to audit a whole codebase for latent work (bugs, performance, tech debt, missing tests, what to build next) and capture it as self-contained plans a cheaper agent can execute later. Spends the capable model on judgement, not execution. Read-only over code; writes plans only.
swarm-planUse when the user wants to break a large task into parallel workstreams, plan a multi-agent job, or decide what can run concurrently. Produces an orchestration plan, does not execute it.
swarm-principlesUse when orchestrating subagents, fanning work out in parallel, or running any /swarm-* skill. Sets standing rules for when to fan out, when not to, cost ceilings, and who judges. Auto-loads; not directly invoked by the user.
swarm-refineUse when the user has one artefact (code, doc, design, plan) and wants it hardened by attacking it from several angles at once. Parallel critics, then merge. Not to be confused with bulldoze, which generates many solutions.
Claude Code skills that keep AI-written code short and honest. Delete before you add, earn every line.
12 skills · hooks
Strip AI tells from writing and design for human readers, and compile token-efficient instructions for machine readers. Guidelines outrank the model.
6 skills
Refine product feedback, celebrations, characters, and progress in one scoped pass.
3 skills
Refine interface layout, type, colour, controls, accessibility, copy, and motion in one scoped pass.
3 skills
Evidence-led QA passes for web and mobile, with focused intermittent-failure diagnosis.
2 skills
A git-ignored map of what search cannot answer: computed duplicates, one image register, the choices search gets wrong, and pages that know when they have gone stale.
1 skill · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
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.