design-split-options
Compare 2-3 materially different initiative decompositions in `SPLIT_OPTIONS.md` when task boundaries or sequencing are still ambiguous before authoring…
Skill by siarhei-belavus
Chalk Labs
Need help deploying design-split-options?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/siarhei-belavus-design-split-options
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, productivity
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-split-options
What's inside
- Skill name
design-split-options- Description
- Compare 2-3 materially different initiative decompositions in `SPLIT_OPTIONS.md` when task boundaries or sequencing are still ambiguous before authoring `TASK_GRAPH.md`.
- License
- MIT
- Instructions
- 36 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# design-split-options Use only when jumping straight to `split-initiative` would lock in a weak task graph. ## Read first - `../references/initiative-packet-contract.md` - `../references/initiative-workflow-contract.md` - `../references/final-state-authoring-policy.md` - initiative `BRIEF.md`, `UBIQUITOUS_LANGUAGE.md`, `DECISIONS.md`, `INVARIANTS.md`, `REPO_MAP.md`, `CONTRACTS.md`, `OPEN_QUESTIONS.md` - `../../references/communication-mode.md` ## Workflow 1. Enter initiative `Status: split_drafting` if split drafting has not already started. 2. Produce 2-3 materially different decomposition options. 3. Compare options on: - ownership clarity - coupling - validation fit - sequencing / uncertainty reduction - risk of hidden shared context - ease of handing each child to a fresh agent 4. Recommend one direction explicitly. 5. Write `SPLIT_OPTIONS.md`. ## Writing rule Write compared options as candidate final task graphs, not as changelog commentary about prior split attempts. ## Do not - produce cosmetic variants of the same split - defer the recommendation when the evidence already favors one option - reference outside Atelier skill files for option-design heuristics ## Communication Honor active caveman mode for user-facing replies per `../../references/communication-mode.md`. Keep durable artifacts normal unless the human asks otherwise. Drop caveman for safety/clarity when needed, then resume.
From siarhei-belavus/agent-public, MIT.
More from siarhei-belavus/agent-public
- 0.512score
code-implementer-agent
siarhei-belavus
Implement development tasks in safe, reviewable increments.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
atelier-orchestrator
siarhei-belavus
Orchestrate the full atelier workflow in one task window using pi teams runtime teams plus predefined agents, spawning right-side worker panes only when a…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
extract-artifact-candidates
siarhei-belavus
Mine the current chat/history for forgotten durable-residue candidates and backfill `.plans/<task>/ARTIFACT_CANDIDATES.md` without touching tracked `AGENTS.md`.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
distill-knowledge
siarhei-belavus
Curate durable residue from a completed task packet into canonical tracked `AGENTS.md` files or choose an explicit no-op.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
split-initiative
siarhei-belavus
Turn a framed initiative into a reviewed child-task graph in `TASK_GRAPH.md`, using vertical slices, explicit dependencies, canonical child statuses, and…
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
stabilize-initiative-language
siarhei-belavus
Populate `UBIQUITOUS_LANGUAGE.md` inside an initiative packet with canonical terms, aliases to avoid, flagged ambiguities, and term relationships before…
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
sync-initiative
siarhei-belavus
Fold a child loop back into the parent initiative packet, update canonical parent truth, record the sync log, and route the next durable-distill timing…
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
design-child-contract
siarhei-belavus
Compare 2-3 materially different child-level contract/interface shapes and write the chosen direction into `CONTRACT_DECISION.md` before planning when local…
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
implement-task
siarhei-belavus
Implement a planned task from `.plans/<task-slug>/` with strict plan adherence, explicit amendments, and no direct writes to tracked `AGENTS.md`.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
plan-task
siarhei-belavus
Plan a development task into a self-sufficient execution contract stored in `.plans/<task-slug>/` for later fresh-context implementation and review.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
review-agents-tree
siarhei-belavus
Audit the tracked `AGENTS.md` tree against best practices, write `.agents/AGENTS_TREE_REVIEW.md`, and propose cleanup, compaction, conflict resolution, or…
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
review-code-maintainability
siarhei-belavus
Review implementation for maintainability, evolvability, anti-slop, and human complexity; emit `M#` findings and durable residue candidates when needed.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 29, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/siarhei-belavus/agent-public
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from siarhei-belavus
- 0.512score
code-implementer-agent
siarhei-belavus
Implement development tasks in safe, reviewable increments.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
atelier-orchestrator
siarhei-belavus
Orchestrate the full atelier workflow in one task window using pi teams runtime teams plus predefined agents, spawning right-side worker panes only when a…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
extract-artifact-candidates
siarhei-belavus
Mine the current chat/history for forgotten durable-residue candidates and backfill `.plans/<task>/ARTIFACT_CANDIDATES.md` without touching tracked `AGENTS.md`.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
implement-task
siarhei-belavus
Implement a planned task from `.plans/<task-slug>/` with strict plan adherence, explicit amendments, and no direct writes to tracked `AGENTS.md`.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
distill-knowledge
siarhei-belavus
Curate durable residue from a completed task packet into canonical tracked `AGENTS.md` files or choose an explicit no-op.
SkillCFreshness: C★ 2Claude Code +9 - 0.504score
design-child-contract
siarhei-belavus
Compare 2-3 materially different child-level contract/interface shapes and write the chosen direction into `CONTRACT_DECISION.md` before planning when local…
SkillCFreshness: C★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get design-split-options running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
design-split-options skill. Agent Mart. https://agentmart.dev/skills/siarhei-belavus-design-split-options (last updated 2026-10-24)