菜单
Core rules for bkit — PDCA methodology, level detection, agent triggering, quality standards, Sprint management (8-phase container with 4 auto-pause triggers, v2.1.13), and Trust Level scope (L0-L4 gates PDCA + Sprint auto-run). Triggers: bkit rules, core rules, methodology
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/popup-studio-ai/bkit-claude-code --skill bkit-rules命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
bkend.ai authentication — email/social login, JWT tokens, RBAC, session management. Triggers: bkend auth, bkend login, bkend signup, bkend JWT, bkend RBAC
bkend.ai project tutorials (todo to SaaS) and common error troubleshooting. Triggers: bkend tutorial, bkend cookbook, bkend troubleshooting
bkend.ai database — CRUD, column types, filtering, sorting, relations, indexing. Triggers: bkend table, bkend CRUD, bkend column, bkend relation, bkend data
正在显示 SKILL.md
| name | bkit-rules |
| classification | workflow |
| classification-reason | Process automation persists regardless of model advancement |
| deprecation-risk | none |
| effort | low |
| description | Core rules for bkit — PDCA methodology, level detection, agent triggering, quality standards, Sprint management (8-phase container with 4 auto-pause triggers, v2.1.13), and Trust Level scope (L0-L4 gates PDCA + Sprint auto-run). Triggers: bkit rules, core rules, methodology |
| user-invocable | false |
| allowed-tools | ["Read","Glob","Grep"] |
Automatically applied rules that don't require user commands.
No Guessing: If unsure, check docs → If not in docs, ask user SoR Priority: Code > CLAUDE.md > docs/ design documents
| Request Type | Claude Behavior |
|---|---|
| New feature | Check docs/02-design/ → Design first if missing |
| Bug fix | Compare code + design → Fix |
| Refactoring | Current analysis → Plan → Update design → Execute |
| Implementation complete | Suggest Gap analysis |
| Document Type | Template Path |
|---|---|
| Plan | ${CLAUDE_PLUGIN_ROOT}/templates/plan.template.md |
| Design | ${CLAUDE_PLUGIN_ROOT}/templates/design.template.md |
| Analysis | ${CLAUDE_PLUGIN_ROOT}/templates/analysis.template.md |
| Report | ${CLAUDE_PLUGIN_ROOT}/templates/report.template.md |
None of the above conditions met.
| Aspect | Starter | Dynamic | Enterprise |
|---|---|---|---|
| Explanation | Friendly, avoid jargon | Technical but clear | Concise, use terms |
| Code comments | Detailed | Core logic only | Architecture only |
| Error handling | Step-by-step guide | Technical solutions | Brief cause + fix |
| PDCA docs | Simple | Feature-specific | Detailed architecture |
| Primary Agent | starter-guide | bkend-expert | enterprise-expert |
| Reference Skill | starter | dynamic | enterprise |
project/
├── CLAUDE.md # Project-wide (always reference)
├── services/CLAUDE.md # Backend work context
├── frontend/CLAUDE.md # Frontend work context
└── infra/CLAUDE.md # Infrastructure context
Rule: Area-specific rules > Project-wide rules
When user requests feature development:
| User Intent | Auto-Invoke Agent |
|---|---|
| "code review", "security scan" | bkit:code-analyzer |
| "design review", "spec check" | bkit:design-validator |
| "gap analysis" | bkit:gap-detector |
| "report", "summary" | bkit:report-generator |
| "QA", "log analysis" | bkit:qa-monitor |
| "pipeline", "which phase" | bkit:pipeline-guide |
After completing major tasks, suggest relevant agents.
DRY: Extract to common function on 2nd use SRP: One function, one responsibility No Hardcoding: Use meaningful constants Extensibility: Write in generalized patterns
Classify tasks to apply appropriate PDCA level:
| Classification | Content Size | PDCA Level | Action |
|---|---|---|---|
| Quick Fix | < 50 chars | None | Execute immediately |
| Minor Change | 50-200 chars | Lite | Show summary, proceed |
| Feature | 200-1000 chars | Standard | Check/create design doc |
| Major Feature | > 1000 chars | Strict | Require design, user confirmation |
Quick Fix: fix, typo, correct, adjust, tweak Minor Change: improve, refactor, enhance, optimize, update Feature: add, create, implement, build, new feature Major Feature: redesign, migrate, architecture, overhaul, rewrite
When project level is detected, automatically suggest the matching output style:
| Level | Suggested Style | Trigger Condition |
|---|---|---|
| Starter | bkit-learning | Level detected as Starter |
| Dynamic | bkit-pdca-guide | Level detected as Dynamic |
| Enterprise | bkit-enterprise | Level detected as Enterprise |
/starter init, /dynamic init, /enterprise init: Auto-suggest style for that levelbkit-pdca-guide if not already active/output-style at any time| Style | Best For | Key Features |
|---|---|---|
bkit-learning | Beginners, learning | Learning points, TODO(learner) markers, concept explanations |
bkit-pdca-guide | PDCA workflows | Status badges, checklists, phase progress, gap analysis suggestions |
bkit-enterprise | Architecture decisions | Tradeoff analysis, cost impact, deployment strategy, SOLID compliance |
Suggest Agent Teams when conditions are met:
| Condition | Suggestion |
|---|---|
| Major Feature (>= 1000 chars) AND Dynamic/Enterprise level | "Agent Teams can parallelize PDCA phases. Try /pdca team {feature}" |
| Match Rate < 70% AND Dynamic/Enterprise level | "Consider Agent Teams for faster parallel Check-Act iteration" |
| Enterprise project init | "Your project supports 4-teammate Agent Teams mode" |
| Dynamic project init | "Your project supports 2-teammate Agent Teams mode" |
| Level | Available | Teammates | Roles |
|---|---|---|---|
| Starter | No | - | - |
| Dynamic | Yes | 2 | developer, qa |
| Enterprise | Yes | 4 | architect, developer, qa, reviewer |
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1/pdca team {feature} to start team modeAgent Memory is automatically active for all bkit agents. No user action required.
memory: project scopestarter-guide, pipeline-guide) use memory: user for cross-project learning.claude/agent-memory/ (project) or ~/.claude/agent-memory/ (user)| Scope | Agents Using | Persistence |
|---|---|---|
project | 9 agents (code-analyzer, gap-detector, pdca-iterator, etc.) | Per-project, across sessions |
user | 2 agents (starter-guide, pipeline-guide) | Global, across all projects |
After modifying bkit plugin files, use /reload-plugins to apply changes without restarting Claude Code.
/clear to fully refreshCC 2.1.0+ supports Bash(pattern*) wildcard permissions.
Bash(npm *) - Allow all npm commandsBash(git log*) - Allow git log variantsBash(node *) - Allow node executionBash(npx *) - Allow npx executionBash(rm -rf*) - Deny recursive delete (dangerous)Bash(git push --force*) - Deny force pushAdd to .claude/settings.json:
{
"permissions": {
"allow": ["Bash(npm *)", "Bash(git log*)"],
"deny": ["Bash(rm -rf*)"]
}
}