design — for Claude Code sdp_lab, community, for Claude Code, ide skills, bd show <id>, bd close <id>, ### 4. Create Beads issues, Append to, **ALWAYS verify counts match:**, dry-run

v2.1.0

À propos de ce Skill

Scenario recommande : Ideal for AI agents that need multi-agent design (arch + security + sre) with progressive discovery blocks. Resume localise : # @design Multi-agent design (Arch + Security + SRE) with progressive discovery blocks. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Fonctionnalités

Multi-agent design (Arch + Security + SRE) with progressive discovery blocks.
After @idea, or directly from a feature description. Creates workstream files with AC and scope.
docs/intent/{task id}.json or docs/drafts/idea- .md if available
Or: use the feature description directly
Progressive discovery — unless --quiet

# Sujets clés

fall-out-bug fall-out-bug
[0]
[0]
Mis à jour: 4/30/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Scenario recommande : Ideal for AI agents that need multi-agent design (arch + security + sre) with progressive discovery blocks. Resume localise : # @design Multi-agent design (Arch + Security + SRE) with progressive discovery blocks. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Pourquoi utiliser cette compétence

Recommandation : design helps agents multi-agent design (arch + security + sre) with progressive discovery blocks. @design Multi-agent design (Arch + Security + SRE) with progressive discovery blocks. This AI agent

Meilleur pour

Scenario recommande : Ideal for AI agents that need multi-agent design (arch + security + sre) with progressive discovery blocks.

Cas d'utilisation exploitables for design

Cas d'usage : Applying Multi-agent design (Arch + Security + SRE) with progressive discovery blocks
Cas d'usage : Applying After @idea, or directly from a feature description. Creates workstream files with AC and scope
Cas d'usage : Applying docs/intent/{task id}.json or docs/drafts/idea- .md if available

! Sécurité et Limitations

  • Limitation : --dry-run — Emit write plan only. Do NOT create, modify, or delete any file.
  • Limitation : Pre-flight Before creating draft: ls docs/drafts/idea- — do not duplicate
  • Limitation : Mark OOS only with explicit justification (e.g

About The Source

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Démo Labs

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ et étapes d’installation

These questions and steps mirror the structured data on this page for better search understanding.

? Questions fréquentes

Qu’est-ce que design ?

Scenario recommande : Ideal for AI agents that need multi-agent design (arch + security + sre) with progressive discovery blocks. Resume localise : # @design Multi-agent design (Arch + Security + SRE) with progressive discovery blocks. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Comment installer design ?

Exécutez la commande : npx killer-skills add fall-out-bug/sdp_lab. Elle fonctionne avec Cursor, Windsurf, VS Code, Claude Code et plus de 19 autres IDE.

Quels sont les cas d’usage de design ?

Les principaux cas d’usage incluent : Cas d'usage : Applying Multi-agent design (Arch + Security + SRE) with progressive discovery blocks, Cas d'usage : Applying After @idea, or directly from a feature description. Creates workstream files with AC and scope, Cas d'usage : Applying docs/intent/{task id}.json or docs/drafts/idea- .md if available.

Quels IDE sont compatibles avec design ?

Cette skill est compatible avec Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Utilisez la CLI Killer-Skills pour une installation unifiée.

Y a-t-il des limites pour design ?

Limitation : --dry-run — Emit write plan only. Do NOT create, modify, or delete any file.. Limitation : Pre-flight Before creating draft: ls docs/drafts/idea- — do not duplicate. Limitation : Mark OOS only with explicit justification (e.g.

Comment installer ce skill

  1. 1. Ouvrir le terminal

    Ouvrez le terminal ou la ligne de commande dans le dossier du projet.

  2. 2. Lancer la commande d’installation

    Exécutez : npx killer-skills add fall-out-bug/sdp_lab. La CLI détectera automatiquement votre IDE ou votre agent et configurera la skill.

  3. 3. Commencer à utiliser le skill

    Le skill est maintenant actif. Votre agent IA peut utiliser design immédiatement dans le projet.

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

design

# @design Multi-agent design (Arch + Security + SRE) with progressive discovery blocks. This AI agent skill supports Claude Code, Cursor, and Windsurf

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

@design

Multi-agent design (Arch + Security + SRE) with progressive discovery blocks.

When to Use

After @idea, or directly from a feature description. Creates workstream files with AC and scope.

Pre-flight

Before creating draft: ls docs/drafts/idea-* — do not duplicate. If an idea draft already covers this topic, reuse or extend it instead of creating a new one.

Beads from review: In scope by default. Mark OOS only with explicit justification (e.g. "duplicate", "superseded by prior work").

Workflow

1. Load requirements

  • docs/intent/{task_id}.json or docs/drafts/idea-*.md if available
  • Or: use the feature description directly

2. Progressive discovery — unless --quiet

3-5 discovery blocks, 2-3 questions each:

  • Architecture: What components change? What's the data model?
  • Security: Any auth, crypto, or boundary concerns?
  • Operations: Any monitoring, logging, or CI concerns?

After each block: Continue / Skip / Done

3. Generate workstream files

When source is beads (review findings): For each bead, run bd show <id> and grep the codebase for the fix. If already fixed, run bd close <id> and remove from scope. Do not create WS for beads that are already addressed.

Create docs/workstreams/backlog/00-FFF-SS.md for each deliverable.

Required sections:

markdown
1# 00-FFF-SS: Feature Name — Step Description 2 3Feature: FFFF (sdp_dev-XXXX) 4Phase: N 5Status: Backlog 6 7## Goal 8 9One paragraph: what and why. 10 11## Scope Files 12 13List exact file paths or directory prefixes this workstream touches. 14Used by sdp-guard for boundary checking and CI scope-compliance. 15 16- internal/evidence/ 17- cmd/sdp-evidence/main.go 18 19## Dependencies 20 21- 00-FFF-01: prerequisite workstream (if any) 22 23## Acceptance Criteria 24 25Specific, testable, binary (pass/fail): 26 27- [ ] Criterion 1 28- [ ] Criterion 2 29- [ ] go build ./... passes 30- [ ] go test ./internal/evidence/... passes

4. Create Beads issues

bash
1bd create --title="WS FFF-SS: Short title" --type=task

Append to .beads-sdp-mapping.jsonl:

json
1{"sdp_id":"00-FFF-SS","beads_id":"sdp_dev-XXXX","updated_at":"2026-..."}

ALWAYS verify counts match:

bash
1echo "Mapping: $(wc -l < .beads-sdp-mapping.jsonl)" 2echo "Backlog: $(ls docs/workstreams/backlog/*.md | wc -l)"

5. Update INDEX.md

Add new workstreams to the appropriate phase table in docs/workstreams/INDEX.md.

Write Plan (F101)

Before modifying any file, emit a write plan covering workstream files, design docs, and INDEX.md:

  1. Enumerate — List every file the skill will CREATE / MODIFY / DELETE with a one-line reason. Covers workstream files, design docs, and INDEX.md updates.
  2. Flags:
    • --dry-run — Emit write plan only. Do NOT create, modify, or delete any file.
    • --yes — Skip confirmation prompt. Execute immediately. Intended for CI/non-interactive.
  3. Confirm — Present the plan to the user and wait for explicit approval (unless --yes).
  4. Log — Append write plan event to .sdp/log/events.jsonl (sanitize file paths before logging: strip newlines, ensure valid JSON escaping):
    json
    1{"spec_version":"v1.0","event_id":"<uuid>","timestamp":"<ISO-8601>","source":{"system":"sdp-lab","component":"design"},"event_type":"decision.made","payload":{"decision_type":"write_plan","plan":[{"path":"...","action":"CREATE|MODIFY|DELETE","reason":"..."}]},"context":{"feature_id":"<F-id if known>","workstream_id":"<ws-id if applicable>"}}
    Include context fields only when the ID is known at plan time. Omit unavailable fields rather than inventing placeholders.

    Note: Phase 1 uses prompt-level write boundaries (CLI out of scope). Aligns with schema/contracts/orchestration-event.schema.json via event_type: "decision.made". Phase 2 CLI will emit natively.

Output format:

WRITE PLAN for @design <target>:
  CREATE: path/to/new/file — <reason>
  MODIFY: path/to/existing/file — <reason>
  DELETE: path/to/removed/file — <reason>

Proceed? [y/n]

Modes:

  • No flag: Show plan → Confirm → Execute
  • --dry-run: Show plan → STOP
  • --yes: Show plan → Execute immediately (no prompt)

Modes

ModeBlocks
Default3-5 discovery blocks
--quiet2 blocks (Architecture + Data only)

Output

  • Workstream files in docs/workstreams/backlog/
  • docs/drafts/{task_id}-design.md (architecture notes)
  • Updated docs/workstreams/INDEX.md
  • Updated .beads-sdp-mapping.jsonl

Recovery

SymptomFix
Skill produces no outputCheck working directory is project root with docs/workstreams/backlog/
"checkpoint not found"Run sdp-orchestrate --feature <ID> to create initial checkpoint
"workstream files missing"Run sdp-orchestrate --index to verify, then @feature to regenerate
Skill hangs / no progressCheck .sdp/log/events.jsonl for last event; use sdp reset --feature <ID> if stuck
Review loop exceeds 3 roundsUse @review --override "reason", @review --partial, or @review --escalate

See Also

  • @idea — Requirements
  • @feature — Full planning orchestrator
  • @build — Execute single workstream
  • @oneshot — Execute all workstreams

Compétences associées

Looking for an alternative to design or another community skill for your workflow? Explore these related open-source skills.

Voir tout

openclaw-release-maintainer

Logo of openclaw
openclaw

Resume localise : 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

widget-generator

Logo of f
f

Resume localise : Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and

flags

Logo of vercel
vercel

Resume localise : The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
Navigateur

pr-review

Logo of pytorch
pytorch

Resume localise : Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
Développeur