For vague, big, or risky requests, write down the plan (what, which files, how to verify) and get a yes before coding.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add HaipingShi/coderail --skill contract-draft --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Contract Draft?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/haipingshi-contract-draft)More formats (shields.io, HTML) on the badges page.
---
name: contract-draft
description: For vague, big, or risky requests, write down the plan (what, which files, how to verify) and get a yes before coding.
---
# Contract Draft
Do not write business code. Convert intent into a formal Coordinate Contract Draft.
## Read
- `docs/NORTH_STAR.md`
- `docs/TASKS.md`
- `docs/CONTRACTS.md` if present
- `docs/HARNESS_SPEC.md`
- `git status`
## Output
Write or propose a draft in `docs/CONTRACTS.md`:
```markdown
## CD-XXX Short title
Status: proposed
Created at:
Source:
Trace:
### Coordinate Contract Draft
G — Goal:
- North Star:
- Outcome served:
- Why now:
T — Task:
- Task ID:
- Exact task:
- What this task must not become:
S — Scope:
- Allowed:
-
- Forbidden:
-
V — Verify:
- TDD mode: required | optional | waived
- Red check:
- Green check:
- Refactor check:
- Regression check:
- CI check:
- Waiver reason:
- Harness:
-
- Manual acceptance:
-
X — Stop:
-
P — Persist:
- TASKS:
- HANDOFF:
- DECISIONS:
- LESSONS:
- ASSETS:
- TRACE:
Decision:
- proceed | revise | ask user | split task | backlog
```
## Rules
- If G cannot map to North Star, stop and ask or update `NORTH_STAR.md`.
- If V cannot be defined, create a harness task or manual acceptance before coding.
- If the request is a side branch, backlog it instead of folding it into the active task.
- After drafting, run or suggest `scripts/contract_check.py --target .`.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.