edenbuilds

progressive-disclosure

Split an oversized skill, CLAUDE.md, or spec into an entry file plus files that load only when they're needed.

Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples. Use when building an MCP server or tool definition, writing an agent-facing script, or when an agent keeps misusing a tool it already has.

context-audit

Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list. Use when an agent ignores its own instructions, when a CLAUDE.md has grown bloated, or when the user asks to audit or rightsize their agent context.

agentloop-core

Master agentloop orchestration for coding and product tasks. Use when the user wants harness mode, full autonomy with gates, or to enter agentloop.

blindspot-pass

Surface the user's unknown unknowns before work starts. Use when the user is entering an unfamiliar codebase area, an unfamiliar domain (design, video, infra), or explicitly asks for a "blindspot pass" or to find their "unknown unknowns."

brainstorm-prototypes

Generate several genuinely different throwaway variations (designs, approaches, drafts) for the user to react to. Use when the user can only recognize what they want by seeing it — visual design, UX flows, naming, tone — or asks to brainstorm or prototype before building.

change-quiz

After a working session, produce a report on what changed plus a quiz the user must pass before merging. Use when the user asks "what did we actually do," wants to review a large change, or invokes a quiz before merge.

contrasting

Enforce deliberate contrast — visual (WCAG-minded color/type contrast) and intellectual (steelman opposing views before deciding). Use in UI polish and warroom decisions.

deployment-audit

Audit deploy readiness — build, env, hosting, CI, rollback, observability, secrets. Use before go-live or when deploys feel brittle.

humanise

Make product copy, UI microcopy, and agent narration sound human — concrete, warm, and specific. Use after drafting or when text feels corporate/AI-flat.

implementation-notes

Keep a running implementation-notes.md during a build, logging every deviation from the plan and every discovered edge case. Use whenever implementing against an agreed plan or spec, especially in long autonomous sessions.

implementation-plan

Write an implementation plan that leads with the decisions the user is most likely to change, and buries the mechanical work at the bottom. Use when planning is requested before a build, especially after brainstorming or an interview.

interview-me

Interview the user one question at a time to resolve remaining ambiguity before implementation. Use when planning or brainstorming is done but unknowns remain, or when the user asks to be interviewed about a task or spec.

no-ai-slop

Strip generic AI writing, UI, and code patterns. Use when copy, design, or diffs feel templated, padded, or interchangeable with any other AI product.

optional-ponytail

Optional distinctive personality mode for product voice and agent narration. OFF by default. Use only when the user asks for character, founder energy, or “ponytail mode”.

pitch-packager

Package a finished piece of work (spec, prototype, implementation notes) into a single document that gets reviewers to understanding and approval fast. Use when the user needs buy-in, a review, or a shareable summary of what was built and why.

reference-hunt

Use existing source code as the specification when the user can't describe what they want in words. Use when the user points at a library, module, folder, or site and says "like this," even if it's in a different language or stack.

Web & Frontend Listed

ui-ux-audit

Structured UI/UX audit of a screen or flow — hierarchy, clarity, states, a11y, mobile. Use before shipping UI or when asking “what’s wrong with this page?”.

agent-loop

Run a disciplined think/act/observe/verify agent loop with hard stop conditions. Use for autonomous multi-step work.

context-compact

Compact long agent context using staged summarization and file-backed handoffs. Use when sessions grow large or approach window limits.

harness-design

Design a coding agent harness across provider, loop, tools, context, sandbox, and permissions. Use when building or auditing agent infrastructure.

pev-cycle

Plan-Execute-Verify cycle for feature work. Separates planning from execution and enforces external verification.

seo-copywriting

SEO-aware product and landing copy — intent, titles, meta, headings, scannability — without keyword stuffing. Use for landing pages, READMEs, and launch posts.