Skip to main content
تشغيل أي مهارة في Manus
بنقرة واحدة
مستودع GitHub

parade

يحتوي parade على 12 من skills المجمعة من JeremyKalmus، مع تغطية مهنية على مستوى المستودع وصفحات skill داخل الموقع.

skills مجمعة
12
Stars
27
محدث
2026-01-05
Forks
3
التغطية المهنية
9 فئات مهنية · 100% مصنفة
مستكشف المستودعات

Skills في هذا المستودع

run-tasks
المهن الحاسوبية الأخرى

Orchestrate task execution via beads and sub-agents. Gets ready work from beads, spawns appropriate agents based on labels, monitors completion, and updates status. Use after /approve-spec has created tasks.

2026-01-05
init-project
المديرون العامون ومديرو العمليات

Initialize a new project with guided configuration wizard. Checks for .parade/ scaffolding, creates comprehensive constitution, governance policies, design system, and custom agents. Supports single app and monorepo configurations. Use when setting up a new project or adding configuration to an existing one.

2026-01-05
approve-spec
المديرون العامون ومديرو العمليات

Approve a specification and export it to beads as an epic with tasks. Creates the epic, child tasks, dependencies, and agent assignment labels. Use after reviewing the spec from /start-discovery.

2026-01-05
discover
مديرو التسويق

Unified discovery flow that captures a feature idea, assesses complexity, runs appropriate discovery depth, and produces a spec. Replaces separate /create-brief and /start-discovery skills with a streamlined single-command workflow.

2026-01-05
evolve
مطوّرو البرمجياتالمهن الحاسوبية الأخرى

Capture positive evolutions from epic execution. Detects new components, fields, patterns, and capabilities added during implementation. Updates design registries and agent knowledge. Only proposes changes when truly new additions are found.

2026-01-05
parade-doctor
مديرو الشبكات وأنظمة الحاسوب

Diagnose and verify Parade project setup. Checks all required components and reports issues.

2026-01-05
retro
مطوّرو البرمجياتالمديرون العامون ومديرو العمليات

Analyze epic execution and generate improvement recommendations. Reads telemetry data, calculates efficiency score, and proposes workflow improvements. Use after epic completion or to review recent executions.

2026-01-05
workflow-status
مديرو الخدمات الإدارية

Display current workflow state across discovery.db and beads. Shows active briefs, open epics, blocked tasks, recent activity, and suggests next actions. Use when resuming work or checking project status.

2026-01-05
ascent-brand
متخصصو العلاقات العامة

Brand identity for Ascent Training - guided endurance training that shows its work. Use when creating marketing materials, product copy, or communications. Built around "You Climb. We Guide. We Learn." with emphasis on transparent AI that explains every decision.

2026-01-04
ascent-feature-brief
مديرو الإعلان والترويج

Creates concise feature briefs for handoff to Claude Code. Use when users want to document a feature for implementation, need a spec for coding, want to capture architecture decisions for handoff, or are planning features to be built by an AI coding agent. Generates token-efficient implementation directives that communicate intent while delegating schema discovery to the coding agent.

2026-01-04
ascent-frontend-design
مطوّرو الويب

Create distinctive, on-brand frontend interfaces for Ascent Training. Use this skill when building landing pages, marketing sites, app UI, React components, or any visual artifact for Ascent. Combines the mountain/guide brand identity with topographic map aesthetics and emerald/charcoal color system. Generates production-grade code that is immediately recognizable as Ascent.

2026-01-04
ascent-task-coordinator
مطوّرو البرمجيات

Multi-agent coordination pattern for Claude Code acting as Project Manager. Use when orchestrating background agents for feature implementation, when Claude Code should delegate rather than implement, or when running parallel investigation/implementation tasks. Provides task-list.json structure, progress tracking format, and agent role definitions. Keeps Claude Code in "coordinator mode" - dispatching work to specialized agents rather than writing code directly.

2026-01-04