papadopouloskyriakos/agentic-chatops/plan
Claude Code and agent skill by papadopouloskyriakos/agentic-chatops
- community
Checking that the SKILL.md file is still in the repository.
Phase D of greenfield project bootstrap. Produce design.md + data-model.md + contracts/{openapi,asyncapi,schemas/*} + adr/NNNN-*.md. Validates contracts via swagger-cli/asyncapi/ajv before exit.
Install
npx vskill@latest install papadopouloskyriakos/agentic-chatops/planSKILL.md
/plan — design + contracts + ADRs
After /constitute locked in non-negotiables, this skill produces the technical design that workers will implement.
Artifacts to produce
spec/001-<slug>/design.md— architecture overview, sequence diagrams (mermaid), error handling strategyspec/001-<slug>/data-model.md— entities, relationships, persistence shapespec/001-<slug>/contracts/openapi.yaml— sync API contracts (HTTP endpoints)spec/001-<slug>/contracts/asyncapi.yaml— event contracts (queues/topics)spec/001-<slug>/contracts/schemas/*.json— shared JSON Schema for data shapesadr/NNNN-<decision>.md— one MADR file per arguable architectural choice
Templates
<bootstrap-pack>/templates/{design.md,data-model.md,openapi.yaml,asyncapi.yaml,adr-0001-record-architecture-decisions.md}.tmpl
Validation
Before exit, run:
If any contract fails to parse, iterate until clean.
ADR criteria
Write an ADR for any choice the operator (or a future contributor) might argue about in 6 months:
- Database choice (Postgres vs Mongo vs SQLite)
- Auth mechanism (JWT vs OAuth2 vs mTLS)
- Message bus (NATS vs Kafka vs Redis Streams)
- Frontend framework
- Deployment target (K8s vs containers-on-VMs vs serverless)
- Significant library choice with alternatives
Each ADR has: Status, Context, Decision, Consequences (positive + negative), Alternatives considered.
Definition of done
- [ ] All 6 artifact categories exist
- [ ] All contract files parse cleanly
- [ ] At least one ADR exists (always include ADR-0001 from template)
- [ ] Operator has skimmed design.md + reviewed top-level architecture
What's next
Operator runs /tasks to atomize the design into the work_units that parallel-dev workers will execute.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingbootstrap-pack/.claude/skills/plan/SKILL.md
Popularity
- Repository stars
- 107
- Repository forks
- 26
- 7-day trend score
- 23
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/papadopouloskyriakos/agentic-chatops/plan)