blossom

Convert loosely defined goals into structured, prioritized backlogs.

Updated Feb 20, 2026
One-click install
npx skills add https://github.com/supertyrelle/pelley --skill blossom-supertyrelle
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: blossom
Source: https://github.com/supertyrelle/pelley/tree/main/skills/blossom
Command: npx skills add https://github.com/supertyrelle/pelley --skill blossom-supertyrelle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Blossom turns an unclear, loosely defined objective into a structured and prioritized backlog, helping you move from uncertainty to actionable work without over-planning upfront.

Core Features & Use Cases

  • Spike-driven exploration: Breaks a broad goal into bounded investigation areas and dispatches focused discovery work.
  • Backlog creation: Converts verified findings into firm tasks, deeper follow-up spikes, and clean areas with no action needed.
  • Workflow orchestration: Supports epic seeding, consolidation, dependency wiring, prioritization, and final reporting for complex codebase exploration.
  • Use Case: Use it when you need to audit an unfamiliar subsystem, map a design decision, or research a codebase area and produce a ranked task list.

Quick Start

Use the blossom skill to explore the target area and return a prioritized backlog of findings and next steps.

Frequently Asked Questions about blossom

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I structure a vague codebase goal into a prioritized backlog?▼

Epic planning breaks a broad objective into bounded investigation areas, dispatching focused spike-driven discovery to convert verified findings into firm tasks, follow-up spikes, and clean areas requiring no action.

What is the best way to audit an unfamiliar codebase subsystem?▼

Auditing an unfamiliar subsystem requires dispatching sequential spikes to explore the codebase, deduplicating discovered tasks, wiring dependencies, and consolidating verified findings into a prioritized backlog of actionable work.

How does spike-driven exploration work for epic planning?▼

Spike-driven epic planning works by seeding broad epics, dispatching subagent-driven discovery into bounded investigation areas, deduplicating tasks, wiring dependencies, and consolidating verified findings into a structured, prioritized backlog.

Can I use this approach for design research and investigation workflows?▼

Yes, this approach supports design research and investigation workflows by mapping design decisions and converting loosely defined exploration goals into structured, prioritized backlogs with confidence-tagged findings.

Do I need to define dependencies before starting codebase discovery?▼

No, you do not need to define dependencies upfront; the workflow automatically wires dependencies, tags confidence levels, and deduplicates tasks during the consolidation and final report generation phases.