sdd
claudecodexSpec-driven AI development workflow core: workflow commands, orchestrator, architect, cross-cutting reviewers, and universal skills. Stack specialists ship as optional sdd-* packs.
31 skills · 7 agents
Look after the AI setup itself: write and audit the prompt files that steer it, trim what a stronger model no longer needs and what edits left unreached, feed real-usage problems back into their source, and audit which installed MCP servers and skills actually get used
Plugin prompt-workflow from marketplace eli-marketplace in bingeli1379/eli-marketplace. Commands read from the repo's manifest — 6 days ago.
improve-skillUse when ANY asset shipped by a plugin you maintain in a LOCAL marketplace/plugin repo — a skill, an output style or persona, an agent, a hook, a template — misbehaved, missed a case, never triggered when it should have, or felt clunky while you used it during real work in ANOTHER project, and you w
review-skillUse when auditing or reviewing a skill or agent prompt file — its text quality (removed rules, broken references, bloat, hardcoded values, cross-file consistency, contradictory wording) and its procedural logic (resume/idempotency, step ordering, broken invariants, unhandled edge cases, dependency g
skill-authoringUse BEFORE writing or editing any skill or agent prompt file — a SKILL.md, an agent .md, an output style, a bundled references/ or templates/ file — or a plugin's hooks.json, hook script or mod, or any part of one: a description, a step, a guardrail, a flag. Covers trivial-looking edits, authoring d
trim-skillsUse when your own prompt files may hold what they no longer need or now have wrong — the model under them got stronger, or one-point edits left text, scripts, templates or config nothing reaches — in one skill, one plugin, or a whole local marketplace/plugin repo. Triggers on model upgrade, new mode
usage-auditAudit the INVENTORY of installed MCP servers, tools, and skills against actual usage — what is installed and whether it ever fires, NOT the text or logic of a prompt file.
Spec-driven AI development workflow core: workflow commands, orchestrator, architect, cross-cutting reviewers, and universal skills. Stack specialists ship as optional sdd-* packs.
31 skills · 7 agents
SDD stack pack: Godot game engineer and skills
31 skills · 1 agent
SDD stack pack: Vue/Nuxt frontend engineer and frontend skills
26 skills · 1 agent
SDD stack pack: ASP.NET / .NET backend engineer and skills
12 skills · 1 agent
SDD stack pack: DevOps engineer and infrastructure skills
10 skills · 1 agent
SDD stack pack: database engineer and datastore skills
8 skills · 1 agent
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
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
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
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.