design
Take a feature idea from fuzzy to build-ready — grill, prototype, then plan.
Skill by thunter009
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thunter009-design
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/design
What's inside
- Skill name
design- Description
- Take a feature idea from fuzzy to build-ready — grill, prototype, then plan.
- License
- MIT
- Instructions
- 74 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /design — idea to build-ready plan Three phases that progressively de-risk a feature before a line of production code is written. Wrapper delegates to focused skills; each phase gates the next. **When NOT to use:** small well-understood changes — just write the code. ## Phase 1 — Grill the plan Run Step 5 (grill mode) from the **plan-review** skill: - In this repo: `skills/plan-review/SKILL.md` - Outside this repo: `~/.claude/skills/plan-review/SKILL.md` Key constraints for this phase: - Ask **one question at a time**. Never fire a numbered list of questions. - Explore the codebase to answer questions yourself before asking the user — only escalate genuine ambiguities that require product judgment. - As decisions crystallise, write them inline: update `CONTEXT.md`, ADRs, or a `DESIGN.md` scratchpad so the plan stays in the repo, not just in the conversation. - Continue until the plan can answer: *what changes, why, how it fits the existing architecture, and what "done" looks like*. Exit criterion: no HIGH-severity open questions remain (security, data model, public API shape, or irreversible architectural choices). LOW questions are acceptable; note them. ## Phase 2 — Prototype (conditional) If one or more **load-bearing uncertainties** remain after Phase 1 — state model ambiguity, novel UI interaction, performance unknown — build a throwaway prototype to answer the question before committing to a design. Follow the **prototype** skill: - In this repo: `skills/prototype/SKILL.md` - Outside this repo: `~/.claude/skills/prototype/SKILL.md` The prototype is disposable. Capture only the answer it produced (e.g. "state machine with 4 states is sufficient; event sourcing not needed") in the design doc. Delete or clearly mark the prototype code as throwaway before Phase 3. Skip this phase if no load-bearing uncertainty exists after Phase 1. ## Phase 3 — Convert to tracker items Present the validated plan to the user and ask: > "Should I create beads for this plan, or stop at the written design doc?" **If beads:** use the `br` CLI conventions to create issues, set types/priorities, and wire dependencies: ```bash br create "..." --type feature --priority 2 br dep add <issue-id> <depends-on-id> br sync --flush-only git add .beads/ && git commit -m "chore(beads): ..." ``` Group work into logical epics → tasks → sub-tasks. Every bead needs: goal, why, current state, next action, and an acceptance criterion that is testable at runtime (not just "code exists"). **If no beads:** leave the finalized `DESIGN.md` / ADR as the deliverable and note the file path in the session summary. ## Guardrails - Never start implementation during `/design`. The output is a plan or beads, not code. - If the user changes scope mid-grill, restart Phase 1 grill on the revised scope. - Design docs that change after beads are created are stale — re-run Phase 3 on the delta.
From thunter009/skills, MIT.
More from thunter009/skills
- 0.570score
decision-canvas
thunter009
Present batched user decisions as an interactive atrium canvas with inline grounding — code snippets with real line numbers, click-to-open file links, and…
SkillAFreshness: AClaude Code +9 - 0.529score
clean
thunter009
End-of-work cleanup sweep for a multi-agent repo — safely land genuine unpushed commits, squash open PRs, prune merged branches and worktrees, clean the…
SkillBFreshness: BClaude Code +9 - 0.526score
autoreview
thunter009
Run a structured code review (Codex default, Claude optional) as a closeout check on a local or PR branch before commit or ship.
SkillBFreshness: BClaude Code +9 - 0.520score
bug-hunt
thunter009
Run a multi-phase bug hunt with Codex, Gemini, or Claude.
SkillBFreshness: BClaude Code +9 - 0.518score
create-pull-request
thunter009
Open a GitHub pull request with repo-specific PR conventions.
SkillBFreshness: BClaude Code +9 - 0.514score
agents-md
thunter009
Create repo-specific AGENTS.md guardrails from the codebase.
SkillBFreshness: BClaude Code +9 - 0.479score
enrich-ticket-detail
thunter009
Flesh out thin or empty beads/Todoist items by mining git history, code-at-HEAD, closed tickets, and the session journal, then verify every drafted claim…
SkillCFreshness: CClaude Code +9 - 0.476score
codebase-knowledge-graph
thunter009
Build an interactive knowledge graph of any codebase via the Understand-Anything pipeline, with a batch-integrity guard the raw plugin lacks.
SkillCFreshness: CClaude Code +9 - 0.476score
docs-organize
thunter009
Reorganize loose files already in a folder into its subfolder taxonomy, with hash-based dedup, dry-run preview, and collision-safe moves.
SkillCFreshness: CClaude Code +9 - 0.474score
devbox-cleanup
thunter009
Clean up a project checkout on a remote dev box — tear down a stale agent swarm, verify unpushed work is superseded, reset the checkout to origin, and restart…
SkillCFreshness: CClaude Code +9 - 0.470score
domain-modeling
thunter009
Build and sharpen a project's ubiquitous language — a CONTEXT.md glossary plus sparse ADRs — challenging terms against the glossary and cross-referencing code…
SkillCFreshness: CClaude Code +9 - 0.469score
beads-linear-sync
thunter009
Sync beads and Linear so agent state and human tracker stay aligned.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 14, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/thunter009/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thunter009
- 0.570score
decision-canvas
thunter009
Present batched user decisions as an interactive atrium canvas with inline grounding — code snippets with real line numbers, click-to-open file links, and…
SkillAFreshness: AClaude Code +9 - 0.529score
clean
thunter009
End-of-work cleanup sweep for a multi-agent repo — safely land genuine unpushed commits, squash open PRs, prune merged branches and worktrees, clean the…
SkillBFreshness: BClaude Code +9 - 0.526score
autoreview
thunter009
Run a structured code review (Codex default, Claude optional) as a closeout check on a local or PR branch before commit or ship.
SkillBFreshness: BClaude Code +9 - 0.520score
bug-hunt
thunter009
Run a multi-phase bug hunt with Codex, Gemini, or Claude.
SkillBFreshness: BClaude Code +9 - 0.518score
create-pull-request
thunter009
Open a GitHub pull request with repo-specific PR conventions.
SkillBFreshness: BClaude Code +9 - 0.514score
agents-md
thunter009
Create repo-specific AGENTS.md guardrails from the codebase.
SkillBFreshness: BClaude Code +9
Cite this page
design skill. Agent Mart. https://agentmart.dev/skills/thunter009-design (last updated 2026-10-24)