agentleFS
GlamgarOnDiscordGlamgarOnDiscord/claude-saas-blueprint/.claude/skills/feature/SKILL.md

feature

Skill2 starsChanged 6 months agoMITView on GitHub

Implémentation end-to-end d'une feature SaaS via le pattern **Prompt Discovery** (multi-step).

75 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use bug, bugfix and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • paulocsbSkill

    bug

    Investigation playbook for fixing a bug. Walks through 5 phases: reproduce → isolate → root cause → propose fix → validate. Forces concrete reasoning with code reads, log inspection, and git blame instead of pattern-matching guesses. Use for any non-trivial defect.

    Also in 8 projects that use this

  • team-attentionSkill

    bugfix

    Root cause based one-shot bug fix. debugger diagnosis → requirements.md generation → /execute. /bugfix "error description" Full investigation pipeline: debugger + gap-analyzer + standard verify. QA suggestion after successful fix.

    Also in 8 projects that use this

  • codebycoreySkill

    adopt

    Adopt an existing plan from conversation context into delta-spec format. Use when importing a plan, adopting planning that already happened, capturing plan mode output, or bringing in prior design work.

    Also in 4 projects that use this

  • marylinSkill

    recover

    Recover work from a crashed or interrupted session. Use when Claude crashed mid-task, after an unexpected exit, when you see 'stale sessions detected', or when you lost context and need to figure out what was happening.

    Also in 3 projects that use this

  • aegiswizardSkill

    context

    Also in 4 projects that use this

  • AWSSkill

    map

    Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.

    Also in 4 projects that use this

The file

Files
SKILL.md

Arguments

  • description : Description de la feature à implémenter

Architecture Multi-Step (Prompt Discovery)

Cette skill utilise des étapes séparées pour éviter le "Lost in the Middle". Chaque étape est dans un fichier distinct — l'instruction en cours est toujours la plus récente dans le contexte.

Orchestration

Étape 1 — EXPLORE (obligatoire)

Lire et exécuter .claude/skills/feature/steps/step-1-explore.md

  • Lancer 3 sous-agents en parallèle (codebase, doc externe, rules)
  • Synthétiser les résultats
  • Ne PAS passer à l'étape 2 tant que l'exploration n'est pas terminée

Étape 2 — PLAN (obligatoire)

Lire et exécuter .claude/skills/feature/steps/step-2-plan.md

  • Créer le plan d'architecture (core → adapters → UI → tests)
  • Si blast radius > 5 fichiers → EnterPlanMode pour approbation
  • Ne PAS passer à l'étape 3 sans plan validé

Étape 3 — EXECUTE

Lire et exécuter .claude/skills/feature/steps/step-3-execute.md

  • Implémenter étape par étape en respectant l'ordre strict
  • Lire la rule contextuelle AVANT chaque type de fichier modifié
  • Paralléliser la génération de tests via sous-agent

Étape 4 — VERIFY (obligatoire, jamais skip)

Lire et exécuter .claude/skills/feature/steps/step-4-verify.md

  • 6 checks : types, lint, tests, sécurité, architecture, visuel
  • Si erreur découverte → ajouter dans rules/_learned.md
  • Mettre à jour la memory (domains, roadmap, session)

Important

  • Chaque étape est un fichier séparé — lire le fichier de l'étape en cours, pas tous d'un coup
  • Ne JAMAIS sauter une étape — l'exploration et la planification sont obligatoires
  • Fail-stop : 2 échecs consécutifs sur une étape → arrêt + demande utilisateur

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.