Design the system before the code — choose the stack, define the module boundaries and the frontend/backend contract, and record the load-bearing decisions as ADRs. Mandatory "is there a simpler way" pass before committing to any design. Refuses to design from an empty or vague backlog. Trigger on /architecture-decision and proactively whenever the user asks how to structure something, which stack/library to pick, how to design an API or data model, or right after a backlog exists and before implementation starts.
Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively whenever debugging starts — user reports a bug, says something is broken/throwing/failing, asks to debug/diagnose/investigate an issue, or pastes a stack trace or error log.
Build a story to its acceptance criteria with a test-first discipline — read the contract, write the failing test, make it pass, run the suite before claiming done. Never silently changes an agreed API contract. Trigger on /implement and proactively whenever the user asks to build/code/implement a feature or story, or right after architecture-decision produces a contract to build against.
Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Engineer-audience, code identifiers welcome. Use after a debug session lands a fix, before closing the ticket. Trigger on /post-mortem, when the user says "write the post-mortem / postmortem / RCA / root cause analysis", "document this fix", "write up the root cause", "close out this bug with a writeup", or hands you a fixed-and-validated bug and asks for the writeup.
Adversarial verification of a built story against its acceptance criteria — try to break it, check every criterion explicitly, and report PASS/FAIL with reproducible evidence. Read-only by discipline: finds and reports, never fixes. Trigger on /qa-verify and proactively whenever the user says a feature is done/ready and asks to test/verify/QA it, or right after implement reports a story complete.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Agent skills that run a software team through the Scrum loop — planning, design,
build, verify, standup, review — in the same style as
thananon/9arm-skills.
Each skill is a discipline, not a persona. There is no "backend developer"
character to role-play. There is an implement discipline that builds test-first,
a qa-verify discipline that tries to break the result, a sprint-planning
discipline that refuses to plan from a vague one-liner. Claude loads the discipline
the work needs and carries its constraints through the session.
Skills live under skills/, grouped into buckets:
engineering/ — the delivery loop: plan, design, build, verifyproductivity/ — team rhythm and comms: standup, sprint reviewmisc/ — kept around but rarely usedpersonal/ — tied to a specific setup, not promotedin-progress/ — drafts not yet ready to shipdeprecated/ — no longer usedEach skill is its own directory containing a SKILL.md (with YAML frontmatter —
name and description) and any bundled scripts or reference files.
npx skills (recommended — works for every agent)npx skills add <your-org>/agile-skills
Symlink every shippable skill into ~/.claude/skills/:
./scripts/link-skills.sh
List every SKILL.md in the repo:
./scripts/list-skills.sh
Then, in a Claude Code session, run /agents-style discovery is not needed —
skills trigger on their /command or proactively from their description.
sprint-planning ──► architecture-decision ──► implement ──┐
▲ │
│ ┌─────────┤
│ ▼ ▼
│ scrutinize qa-verify
│ (9arm: review) (verify)
│ │ │
│ │ defect? ──► debug-mantra (9arm)
│ │ │ │
│ ▼ ▼ ▼
└──────────── sprint-review ◄──────── (merge) ◄── re-verify post-mortem (9arm)
│
├──► standup (daily, mid-sprint)
└──► management-talk (9arm: report up the org)
This package deliberately does not reimplement disciplines that
thananon/9arm-skills already covers.
Install both and they compose:
| Need | Skill | From |
|---|---|---|
| Plan a sprint | sprint-planning | agile-skills |
| Design + ADRs | architecture-decision | agile-skills |
| Build a story | implement | agile-skills |
| Review a change | scrutinize | 9arm-skills |
| Verify against criteria | qa-verify | agile-skills |
| Track down a defect | debug-mantra | 9arm-skills |
| Write up a fixed bug | post-mortem | 9arm-skills |
| Daily standup | standup | agile-skills |
| Close the sprint | sprint-review | agile-skills |
| Report up the org | management-talk | 9arm-skills |
npx claudepluginhub mbaho10/claude-code-skills-9arm-workspaceUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.