team-development-skills

Build robust backend systems — APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), databases, performance optimization, security (OWASP Top 10), scalability patterns (microservices, caching, sharding), and testing. Use when designing APIs, implementing auth, optimizing queries, handling security vulnerabilities, building microservices, or developing production-ready backend systems.

Explore and debate solutions before writing code. Use when the user poses a design question, asks "how should I approach X", wants to think through options before committing, or says anything like "let's brainstorm", "what's the best way to...", "I'm not sure how to tackle this", or "should I use X or Y". Always runs before /ck:plan for novel or ambiguous features. No code is written — only: explore → clarify → spec → report.

Implement a feature phase by phase from a phased JSON master or Markdown plan. Before each phase, confirm whether to create/run unit tests and whether to run ck:quality, unless explicit flags supply those choices. Supports token-budgeted execution, resumable state, and TDD handoff to ck:test.

Fix a bug using Scout → Diagnose → Fix → Review → Finalize. Use when the user pastes an error message, stack trace, or test failure, or says "fix this bug", "something's broken", "tests are failing", "I'm getting an error". Also accepts `--from-quality <report>` or `--from-test <report>` to fix exactly the findings/failures a report lists. Modes (pick one): --fast (trivial errors — lint, type, build — skip scout and review), --hard (mandatory review, no auto-approve).

Create a machine-readable phased JSON plan bundle from a spec or feature description. Produces a compact master manifest plus per-phase step files for resumable ck:cook execution.

Plan a feature or system before implementation. Use when the user says "plan this", "I want to build X", "how do I implement Y", or when /ck:brainstorm produces a spec.md. Always run before /ck:cook. Modes (pick one): --fast (simple, single-file), --hard (research + red-team + validate). Composable flag (combine with any mode): --tdd — propagates into the cook pipeline. Every phase gets Design Constraints and Quality/Testing State; ck:cook confirms optional test and quality checks per phase.

Independent senior-engineering quality auditor — architecture, ownership, domain integrity, abstraction, and maintainability. Use as `--gate` inside the ck:cook pipeline (blocks a phase on BLOCKER/HIGH/current-change MEDIUM findings) or call directly with `--audit`, `--diff`, `--changed` on any repository, directory, or file. Never writes tests and never edits production code — it returns structured findings only; ck:cook or ck:fix apply the fix.

Standalone testing skill — owns writing and running tests, verifying behavior, and two-pass TDD orchestration. Default mode analyzes changed scope and runs the relevant tests; `--unit`/`--integration`/`--e2e`/`--all` scope by test type; `--verify` reruns exactly the prior failures; `--all-phases <plan>` sweeps every completed phase for regression. `--tdd --prepare`/`--tdd --verify` bracket `ck:cook` for red-green TDD. Never edits production code, and blocks until a phase's `ck:quality` gate is APPROVED (except `--tdd --prepare`, which runs before any implementation exists).

Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, architecture diagrams, or any of 24+ diagram types. Supports JavaScript API integration, CLI rendering to SVG/PNG/PDF, theming, configuration, and accessibility features. Essential for documentation, technical diagrams, project planning, system architecture, and visual communication.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

Phase 1 of the SRS workflow. User gives a project topic → AI runs a deep, categorized brainstorm (5 mandatory rounds) to fully understand actors, features, scope boundary, tech constraints, and business rules before writing anything.

Phase 6 of the SRS workflow. Reads approved plan files and generates a complete IEEE 830-compliant SRS — one file per section, no word limit. A full SRS may span 300+ pages across all files.

Phase 4 of the SRS workflow. Reads spec.md and writes one detailed plan file per SRS section (§1–§3 + Appendices). Each file is a complete blueprint for the corresponding SRS section. No word limit.

Phase 9 of the SRS workflow. Saves all project context to _context/ files so future sessions can resume without re-reading the full SRS.

Phase 7 of the SRS workflow. Runs srs_validator.py --dir on the generated SRS files, reports errors and warnings, auto-fixes ERRORs, and outputs a COMPLIANT / PARTIALLY COMPLIANT / NON-COMPLIANT verdict.

Generate IEEE 830 SRS from raw requirements. Use when the user says "write SRS", "generate requirements doc", "analyze requirements", "I have raw requirements from a client", or pastes a client email/chat/PRD.

Full SRS workflow: Brainstorm → Spec → Plan (per-section files) → User Review → SRS Generation → Validation → Improvement Report → Context Save. Use when user provides a project topic and wants a complete requirements pipeline.

Full-pipeline orchestrator. Runs all 7 roles (BA → TechLead → PM → BE Dev → FE Dev → Tester → QA/QC) in sequence by loading and following each per-role skill. Uses pre_write_validator.py hook enforcement and each role's self-validation. Use per-agent commands ($team-ba, $team-techlead, etc.) for manual control.

Implement a feature phase by phase from a phased JSON master or Markdown plan. Before each phase, confirm whether to create/run unit tests and whether to run ck:quality, unless explicit flags supply those choices. Supports token-budgeted execution, resumable state, and TDD handoff to ck:test.

Implement a feature phase by phase from a phased JSON master or Markdown plan. Before each phase, confirm whether to create/run unit tests and whether to run ck:quality, unless explicit flags supply those choices. Supports token-budgeted execution, resumable state, and TDD handoff to ck:test.

Create a machine-readable phased JSON plan bundle from a spec or feature description. Produces a compact master manifest plus per-phase step files for resumable ck:cook execution.

Plan a feature or system before implementation. Use when the user says "plan this", "I want to build X", "how do I implement Y", or when /ck:brainstorm produces a spec.md. Always run before /ck:cook. Modes (pick one): --fast (simple, single-file), --hard (research + red-team + validate). Composable flag (combine with any mode): --tdd — propagates into the cook pipeline. Every phase gets Design Constraints and Quality/Testing State; ck:cook confirms optional test and quality checks per phase.

Standalone testing skill — owns writing and running tests, verifying behavior, and two-pass TDD orchestration. Default mode analyzes changed scope and runs the relevant tests; `--unit`/`--integration`/`--e2e`/`--all` scope by test type; `--verify` reruns exactly the prior failures; `--all-phases <plan>` sweeps every completed phase for regression. `--tdd --prepare`/`--tdd --verify` bracket `ck:cook` for red-green TDD. Never edits production code, and blocks until a phase's `ck:quality` gate is APPROVED (except `--tdd --prepare`, which runs before any implementation exists).

Create a machine-readable phased JSON plan bundle from a spec or feature description. Produces a compact master manifest plus per-phase step files for resumable ck:cook execution.

Plan a feature or system before implementation. Use when the user says "plan this", "I want to build X", "how do I implement Y", or when /ck:brainstorm produces a spec.md. Always run before /ck:cook. Modes (pick one): --fast (simple, single-file), --hard (research + red-team + validate). Composable flag (combine with any mode): --tdd — propagates into the cook pipeline. Every phase gets Design Constraints and Quality/Testing State; ck:cook confirms optional test and quality checks per phase.

Standalone testing skill — owns writing and running tests, verifying behavior, and two-pass TDD orchestration. Default mode analyzes changed scope and runs the relevant tests; `--unit`/`--integration`/`--e2e`/`--all` scope by test type; `--verify` reruns exactly the prior failures; `--all-phases <plan>` sweeps every completed phase for regression. `--tdd --prepare`/`--tdd --verify` bracket `ck:cook` for red-green TDD. Never edits production code, and blocks until a phase's `ck:quality` gate is APPROVED (except `--tdd --prepare`, which runs before any implementation exists).

Fix a bug using Scout → Diagnose → Fix → Review → Finalize. Use when the user pastes an error message, stack trace, or test failure, or says "fix this bug", "something's broken", "tests are failing", "I'm getting an error". Also accepts `--from-quality <report>` or `--from-test <report>` to fix exactly the findings/failures a report lists. Modes (pick one): --fast (trivial errors — lint, type, build — skip scout and review), --hard (mandatory review, no auto-approve).

Independent senior-engineering quality auditor — architecture, ownership, domain integrity, abstraction, and maintainability. Use as `--gate` inside the ck:cook pipeline (blocks a phase on BLOCKER/HIGH/current-change MEDIUM findings) or call directly with `--audit`, `--diff`, `--changed` on any repository, directory, or file. Never writes tests and never edits production code — it returns structured findings only; ck:cook or ck:fix apply the fix.

Always use this skill before claiming any work is done, fixed, passing, or complete — even if it seems obvious. Also use when receiving code review feedback from any source (human or automated), when finishing a task or major feature, before committing or creating a PR, or when about to express satisfaction with work. Covers three practices: receiving feedback with technical rigor (no performative agreement), triggering code review via /code-review command or cook/fix pipelines, and verification gates (run the command, read the output, then make the claim). Never skip — the cost of false completion claims is higher than the cost of verifying. References: code-review-reception.md, requesting-code-review.md, verification-before-completion.md.

Fix a bug using Scout → Diagnose → Fix → Review → Finalize. Use when the user pastes an error message, stack trace, or test failure, or says "fix this bug", "something's broken", "tests are failing", "I'm getting an error". Also accepts `--from-quality <report>` or `--from-test <report>` to fix exactly the findings/failures a report lists. Modes (pick one): --fast (trivial errors — lint, type, build — skip scout and review), --hard (mandatory review, no auto-approve).

Independent senior-engineering quality auditor — architecture, ownership, domain integrity, abstraction, and maintainability. Use as `--gate` inside the ck:cook pipeline (blocks a phase on BLOCKER/HIGH/current-change MEDIUM findings) or call directly with `--audit`, `--diff`, `--changed` on any repository, directory, or file. Never writes tests and never edits production code — it returns structured findings only; ck:cook or ck:fix apply the fix.

Always use this skill before claiming any work is done, fixed, passing, or complete — even if it seems obvious. Also use when receiving code review feedback from any source (human or automated), when finishing a task or major feature, before committing or creating a PR, or when about to express satisfaction with work. Covers three practices: receiving feedback with technical rigor (no performative agreement), triggering code review via /code-review command or cook/fix pipelines, and verification gates (run the command, read the output, then make the claim). Never skip — the cost of false completion claims is higher than the cost of verifying. References: code-review-reception.md, requesting-code-review.md, verification-before-completion.md.

Build robust backend systems — APIs (REST, GraphQL, gRPC), authentication (OAuth 2.1, JWT), databases, performance optimization, security (OWASP Top 10), scalability patterns (microservices, caching, sharding), and testing. Use when designing APIs, implementing auth, optimizing queries, handling security vulnerabilities, building microservices, or developing production-ready backend systems.

Terse output mode — strips filler/articles/hedging, ~75% token reduction. Activate whenever: context is filling up, user says be brief/terse/caveman/less tokens, or CAVEMAN_TRIGGERED appears in context. Persists every response until CAVEMAN_RELEASED or user says stop/normal mode.

Explore and debate solutions before writing code. Use when the user poses a design question, asks "how should I approach X", wants to think through options before committing, or says anything like "let's brainstorm", "what's the best way to...", "I'm not sure how to tackle this", or "should I use X or Y". Always runs before /ck:plan for novel or ambiguous features. No code is written — only: explore → clarify → spec → report.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?"

Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"

Spot patterns appearing in 3+ domains to find universal principles