brainstorming
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).
metalExtract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboar…
Independent GitHub snapshot · Automated classification · Original documentation governs
提庫之概念 DNA——其角、程、合作模——成泛 agentskills.io 定。如取貴金於礦,分項目之是(質)與為(施),生可用之技、代理、團定,捕項目之組基因不複其碼。
survey(探+析)、extract(全程)、report(提+書報)(默:extract)提之中質:
此概念可存於異施乎?
若是——乃金(質)。提之。 若否——乃渣(施末)。棄之。
例:氣象應之概念「合外數源」乃金——施於諸取三方數之項目。「析 OpenWeatherMap v3 JSON 答」乃渣——專於一 API。
提之技述任之類,非具體例。提之代理述角非人。提之團述合作模非組圖。
無評探庫構。先繪地後採。
package.json、DESCRIPTION、setup.py、Cargo.toml、go.mod、MakefileREADME.md、CLAUDE.md、CONTRIBUTING.md、架構文.github/workflows/、Dockerfile、署配Project: [name]
Declared Purpose: [from README/manifest]
Languages: [primary, secondary]
Size: [file count, approx LOC]
Shape: [monorepo/library/app/framework/docs]
External Surface: [CLI/API/UI/library exports/none]
得:實測——何在、多大、自稱為何。未分類評。報如地測非評。
敗:無 README 或單→由目名、檔容、測述推旨。項目過大(>1000 源檔)→縮至最活目(用 git log 頻或 README 引)。
讀代表檔以解項目於概念之為。
得:項目之概念圖如域辭典,非碼漫遊。不知技堆者讀之亦解項目之為。
敗:碼隱(重元編、生碼、混淆)→倚測與文非源碼。無測→讀提交以見意。
停以清讀碼之認錨。
得:析報今無架語。諸見過礦試。概念可移——可施於他語他架之項目。
敗:偏存(見常引具技)→反問:「若此項目重書於異堆,何概念存?」唯彼為金。
提之核步。各本概念分為技、代理、團。
Classification Criteria:
+--------+----------------------------+----------------------------+----------------------------+
| Type | What to Look For | Naming Convention | Test Question |
+--------+----------------------------+----------------------------+----------------------------+
| SKILL | Repeatable procedures, | Verb-first kebab-case: | "Could an agent follow |
| | workflows, transformations | validate-input, | this as a step-by-step |
| | with clear inputs/outputs | deploy-artifact | procedure?" |
+--------+----------------------------+----------------------------+----------------------------+
| AGENT | Persistent roles, domain | Noun/role kebab-case: | "Does this require ongoing |
| | expertise, judgment calls, | data-engineer, | context, expertise, or a |
| | communication styles | quality-reviewer | specific communication |
| | | | style?" |
+--------+----------------------------+----------------------------+----------------------------+
| TEAM | Multi-role coordination, | Group descriptor: | "Does this need more than |
| | handoffs, reviews, | pipeline-ops, | one distinct perspective |
| | parallel workstreams | review-board | to accomplish?" |
+--------+----------------------------+----------------------------+----------------------------+
各提元:
identity-manager(代理)。「deployToAWS()」變 deploy-artifact(技)。防常分類誤:
得:分類冊各含類(技/代理/團)、泛名、一句述。無項引具技、API、結構。
敗:分類含糊(技乎代理乎?)問:「此關為(技)抑為人(代理)?」技乃方;代理乃廚。仍不明→默為技——技後合易。
評提誠否——非過非欠。
過提察:讀各提定問:
欠提察:唯顯提定(無源項目)問:
泛察:各定:
衡察:審提比:
得:信於正抽象層。各定為種可長於異土,非枝唯活原園。
敗:過提→升抽象——合具技為廣,合似代理為一角。欠提→返二取更多檔。泛敗→去技引重書述。
成 agentskills.io 標出文。
# Skill: [generalized-name]
name: [generalized-name]
description: [one-line, framework-agnostic]
domain: [closest domain from the 52 existing domains, or suggest a new one]
complexity: [basic/intermediate/advanced]
# Concept-level procedure (3-5 steps, NOT full implementation):
# Step 1: [high-level action]
# Step 2: [high-level action]
# Step 3: [high-level action]
# Derived from: [source concept in original project]
# Agent: [role-name]
name: [role-name]
description: [one-line purpose]
tools: [minimal tool set needed]
skills: [list of extracted skills this agent would carry]
# Derived from: [source role/module in original project]
# Team: [group-name]
name: [group-name]
description: [one-line purpose]
lead: [lead agent from extracted agents]
members: [list of member agents]
coordination: [hub-and-spoke/sequential/parallel/adaptive]
# Derived from: [source workflow/process in original project]
得:結構報含諸提定於 agentskills.io 式。各定為骨(概念非施),可作 create-skill、create-agent、create-team 之始。
敗:出逾 15→按中性排——留最專於本項目域之概念。常項目皆有之概念(如「manage-configuration」)若無異變則棄。
驗全提且成摘。
Temper Assessment:
+-----+---------------------------+----------+------------------------------------+
| # | Name | Type | Ore Test Result |
+-----+---------------------------+----------+------------------------------------+
| 1 | [name] | skill | PASS / FAIL (reason) |
| 2 | [name] | agent | PASS / FAIL (reason) |
| ... | ... | ... | ... |
+-----+---------------------------+----------+------------------------------------+
得:驗析報含摘表、信評、可行下步。報自足——未見源項目者亦可讀解所提概念。
敗:逾兩成提敗末礦試→返四(煉)以更高抽象再提。覆少於識域六成→返二(析)取更多檔。
create-skill 養之種,非成品。50 步提乃複非質athanorchrysopoeiatransmutecreate-skillcreate-agentcreate-teamobserveanalyze-codebase-for-mcpreview-codebase