Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

spec-first

Étoiles0

Forks0

Mis à jour12 juillet 2026 à 04:39

Turn a feature request or task into a written spec before any code is written. Use whenever the user asks to build, add, or implement something non-trivial (3+ steps or an architectural decision), or says "let's design", "write the spec", or "plan this". Produces the spec the human approves and the agent executes against.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

agentmc15

agentmc15/aesop

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	spec-first
description	Turn a feature request or task into a written spec before any code is written. Use whenever the user asks to build, add, or implement something non-trivial (3+ steps or an architectural decision), or says "let's design", "write the spec", or "plan this". Produces the spec the human approves and the agent executes against.

spec-first

The human owns the spec and the taste; the agent fills in the blanks. A written spec up front removes the ambiguity an agent would otherwise fill with a confident wrong guess (the classic: correlating accounts by email instead of a persistent user ID).

Steps

Restate the goal in one sentence as a checkable success criterion.
List the top-level decisions a human must own: identity/keys, data model, security boundaries, external dependencies, irreversible actions. Surface trade-offs; don't pick silently.
Draft the spec: scope, non-goals, interfaces/contracts, the verification plan (what proves it works), and open questions.
Get explicit human sign-off on the spec before writing code.
Keep the spec in the repo (docs/specs/ or tasks/) so the implementing agent reads it, not re-derives it.

Notes

A strong spec is what lets an agent run autonomously (and what a /goal loop needs). A weak spec ("make it work") forces constant clarification.
Don't over-spec trivial changes — match ceremony to stakes.

Plus depuis ce dépôt

même dépôt

lessons-loop

agentmc15/aesop

Capture a durable lesson every time the human corrects the agent, so the same mistake doesn't recur. Use immediately after any user correction, course-correction, or "no, do it this way". Also use at session start to load relevant past lessons. Trigger on corrections and on session start.

2026-07-120

verify-loop

agentmc15/aesop

Prove a change works before calling it done — build, test, lint, smoke-check, and report pass/fail. Use after any code change, before any commit/PR, and as the self-verify step inside an autonomous loop. Trigger whenever the agent is about to claim a task is complete.

2026-07-120

tdd-workflow

agentmc15/aesop

Write a failing test first, then the minimum code to pass it. Use for any bug fix or new behavior.

2026-06-110

agentic-rag-router

agentmc15/aesop

Choose the cheapest sufficient retrieval strategy for a query before answering. Use whenever the system has multiple retrievers (vector, hybrid, graph, metadata, summary) and needs to decide how to fetch evidence for a question. Trigger on any retrieval/QA task where query types are mixed.

2026-06-100

context-compaction

agentmc15/aesop

Keep a long agent session inside its context window without losing the plot. Use when a session is getting long, tool outputs are large, the agent starts "going off the rails" late in a task, or context usage is high. Trigger on big logs, long transcripts, or before a context-heavy step.

2026-06-100

llm-wiki

agentmc15/aesop

Incrementally compile messy source documents into a persistent, cross-linked Markdown knowledge base instead of re-reading raw docs every time. Use when the user has a pile of documents/notes/tickets and wants durable understanding, a project wiki, an onboarding doc, or asks "summarize everything we know about X" across many sources.

2026-06-100

name	spec-first
description	Turn a feature request or task into a written spec before any code is written. Use whenever the user asks to build, add, or implement something non-trivial (3+ steps or an architectural decision), or says "let's design", "write the spec", or "plan this". Produces the spec the human approves and the agent executes against.

spec-first

Steps

Restate the goal in one sentence as a checkable success criterion.
List the top-level decisions a human must own: identity/keys, data model, security boundaries, external dependencies, irreversible actions. Surface trade-offs; don't pick silently.
Draft the spec: scope, non-goals, interfaces/contracts, the verification plan (what proves it works), and open questions.
Get explicit human sign-off on the spec before writing code.
Keep the spec in the repo (docs/specs/ or tasks/) so the implementing agent reads it, not re-derives it.

Notes

A strong spec is what lets an agent run autonomously (and what a /goal loop needs). A weak spec ("make it work") forces constant clarification.
Don't over-spec trivial changes — match ceremony to stakes.