smithery.ai

iterate-check

迭代开发中的构建验证、功能检查、问题修复

First seen Mar 21, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Version1.0.0

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,173 B
  • docs SUMMARY.md 81 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Iterate-Check Skill (Validation & Verification)

This skill validates build status, checks functionality, and fixes issues during development iterations.

v1 edit scope (hard limit)

For validation pass, only modify:

  • Project code files to fix issues identified during validation
  • .create-together/context.json - update validation results
  • .create-together/state.json - update last_check timestamp

Do not:

  • Modify any files in templates/built-in/*
  • Change project structure or architecture
  • Introduce new features during validation
  • Modify MCP configuration files

Dev workflow (required)

  • Before starting: Read state.json to understand current phase
  • Before starting: Read context.json.dev_config to understand integration status
  • After validation:

- Update context.json.validationresults with latest check results - Update context.json.deliveryreport with delivery summary (if ready) - Update state.json.outputs.iterate-check.lastcheck - Update state.json.outputs.iterate-check.deliveryreport + delivery_ready - If issues found, apply fixes and re-run validation - Keep phase: "iterate-check" (repeatable)

Execution order

  1. Understand validation needs: references/00-iterate-guide.md
  2. Dispatch MCP based on request type: references/01-mcp-dispatch.md
  3. Execute validation:

- Build check: references/02-build-check.md - Function check: references/03-function-check.md

  1. Fix issues if found: references/04-issue-fix.md
  2. Final checklist: references/05-checklist.md

MCP dispatch logic

User request → Skill understands intent → Dispatch to appropriate MCP → Analyze results → Return status

Bundled script

  • dev/scripts/shipanyaiguard.py - ShipAny AI integration completeness check
  • TODO: scripts/run_check.py - validation automation