github.com/EpicenterHQ/epicenter
| Skill | Added | Review |
|---|---|---|
abstraction .agents/skills/abstraction/SKILL.md Shape a complex idea, workflow, design, or report on work into the smallest complete surface a person needs for the next judgment. Use when summarizing, reporting on, or explaining complex work to someone who must judge or act on it, when proposing a change that is easier to judge shown than described, or when an explanation obscures its point or makes the user carry unnecessary complexity. | 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
adversarial-review .agents/skills/adversarial-review/SKILL.md Independently form and test models of what a system should do, challenge the design against them, and work as a review group toward an agreed direction. Use when asking for an adversarial review, an independent architecture review, or an adversarial checkpoint on a plan or cumulative implementation. Do not use for routine final code inspection, which belongs to post-implementation-review. | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
agent-goal .agents/skills/agent-goal/SKILL.md Draft a `/goal` line that gives long-running Codex or Claude Code work an objective, validation evidence, and a stop condition. Use when the user explicitly asks for `/goal`, an agent goal, or a completion condition. | 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
agent-instructions .agents/skills/agent-instructions/SKILL.md Write and maintain repository guidance across AGENTS.md, CLAUDE.md, and .agents/skills. Use when creating or editing skills, deciding where instructions belong, or diagnosing instruction sprawl and skill selection. Do not use merely because another skill is being executed. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 7cc869b | |
arktype .agents/skills/arktype/SKILL.md Arktype: runtime validation, discriminated unions with .merge()/.or(), spread keys. Use when mentioning arktype, type(), union types, command/event schemas. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
asymmetric-wins .agents/skills/asymmetric-wins/SKILL.md Evaluate whether refusing a small promise would eliminate disproportionate complexity. Use when judging asymmetric wins or a proposed refusal of fidelity, compatibility, fallbacks, modes, or duplicate paths; use product-collapse to develop simpler product workflows. | 67 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
auth .agents/skills/auth/SKILL.md Epicenter account package: `@epicenter/account`, the auth client Svelte reads through `reactive`, OAuth sign-in for browser and desktop apps, the Account lifetime, account-bound fetch, and hosted resource authorization. Use when editing Epicenter auth clients, session state, hosted sign-in, or how a route boots from auth. | 71 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 04f87cb | |
autumn .agents/skills/autumn/SKILL.md Autumn billing in Epicenter: `autumn.config.ts`, `autumn-js` credit checks, `atmn` CLI, plan gates, and metered AI usage. Use when changing billing, pricing, credits, plan access, refunds, or usage events. | 69 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 04f87cb | |
better-auth-best-practices .agents/skills/better-auth-best-practices/SKILL.md Better Auth server/client setup: `auth.ts`, generated schema, DB adapters, sessions, cookies, env vars, and plugins. Use when mentioning Better Auth, betterauth, auth handlers, OAuth, email/password, or session configuration. | 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
better-auth-security-best-practices .agents/skills/better-auth-security-best-practices/SKILL.md Better Auth security hardening: rate limits, secrets, CSRF, trusted origins, cookies, sessions, OAuth tokens, and audit logging. Use when reviewing auth security, brute-force protection, token handling, or deployment safety. | 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
cloudflare-workers .agents/skills/cloudflare-workers/SKILL.md Cloudflare Workers patterns for Worker runtime APIs, Durable Objects, KV, R2, D1, Queues, WebSockets, streaming responses, bindings, wrangler configuration, and deployment limits. Use when users mention Cloudflare Workers, Durable Objects, KV, R2, D1, Queues, wrangler, or edge runtime behavior. | 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
code-audit .agents/skills/code-audit/SKILL.md Find recurring Epicenter code smells and scope the cleanup they require. Use for periodic audits, cleanup PRs, post-refactor reviews, or reviews of a primitive’s consumers. | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
code-prose .agents/skills/code-prose/SKILL.md Apply Orwell's rules to the prose inside code — identifiers and comments — without changing behavior. Use when names, word choice, or comments need an editorial pass. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
cohesion-over-testability .agents/skills/cohesion-over-testability/SKILL.md Collapse test-shaped production boundaries while preserving behavior and coverage. Use when a helper, wrapper, injected dependency, or export exists mainly to let a unit test reach internals. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
collapse-pass .agents/skills/collapse-pass/SKILL.md Find and carry through worthwhile code simplifications across recent edits, named files, or a subsystem. Use when asked for a collapse pass, a refactoring pass, another simplification pass, "simplify this", to clean up code, or to hunt for indirection and dead abstractions. Specific transformations, planning requests, review-only requests, and explicit file limits determine the work. Use control-flow for a request limited to one function's branching. | 72 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 04f87cb | |
computer-use-driven-iteration .agents/skills/computer-use-driven-iteration/SKILL.md Improve an interactive product through repeated computer-use simulations, bounded Claude implementation, verification, and reflection to find opportunities to collapse complexity. Use when asked to keep exercising and improving a UI across implementation waves. Skip one-off browser actions, routine fixes, and API-only work without an interactive product to exercise. | 66 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
consult-claude .agents/skills/consult-claude/SKILL.md Give Claude Opus 5.5 responsibility for reasoning, design judgment, read-only investigations, recommendations, or finished text drafts. Use when the result benefits from thoughtful reasoning or taste, when asked to consult Claude, or when supplying the Claude seat of an independent review. Completed edits and executable experiments belong to delegate-claude. | 63 Impact — No eval scenarios have been run Securityby Medium Suggest reviewing before use Version: 04f87cb | |
control-flow .agents/skills/control-flow/SKILL.md Linearize complex control flow with early returns, guard clauses, nested ifs, and natural-language conditions. Use when flattening nested conditions, linearizing try/catch logic, or separating mixed throw-and-return handlers, not for a broad "simplify this" pass over a diff or package, which belongs to collapse-pass. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb | |
conversation-hygiene .agents/skills/conversation-hygiene/SKILL.md Triage and archive accumulated Codex conversations without losing wanted work. Use when cleaning up old Codex threads, deciding which conversations still need attention, or resuming a large conversation cleanup. Do not use for ordinary backlog capture, feature implementation, or issue-tracker cleanup. | 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 04f87cb | |
delegate-claude .agents/skills/delegate-claude/SKILL.md Delegate a bounded implementation, prototype, benchmark, or file artifact to Claude Code, which owns the reasoning and delivery in the current checkout or a selected standalone clone, directing a Codex helper as sole code writer for substantial changes. Use when an authorized task benefits from Claude's reasoning, design judgment, or taste, or when asked to delegate execution to Claude. Answer-only investigations, recommendations, and text drafts belong to consult-claude. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 04f87cb |