Pure-markdown output rules for plans, reports, reviews, and any structured agent output.
Dev-Toolbelt/dev-team-agents
SkillsMP has collected 154 skills from Dev-Toolbelt/dev-team-agents. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 154
- GitHub stars
- 4
- GitHub forks
- 0
Skills in this repository
Showing 40 of 154 collected skills.
Code comments — none by default; type annotations and AAA markers.
Git worktree per task — <worktree_path>/<context>/<title>, in .worktrees.
Delegation mechanics — execution gate, autonomous sprint protocol, agent roster, spawn rules.
Remote environment credentials (staging, production) — access and read-only enforcement.
Setup health check — categories, commands, auto-fix actions.
Periodic status-table check-ins while background sub-agents work, gated by credentials.json.
Test pyramid — unit, integration, E2E patterns and pitfall guidance.
Testing strategy — what, when, how; coverage planning.
Code reviewer shared rules — context, SonarQube, commit style.
Conventional Commits — types, scopes, breaking changes, layered.
Run only tests covering the touched code; full suite only on explicit user request.
User preferences — language and settings from preferences.json.
Spec layer between overview.md and sprints — testable criteria, auto contract gate.
Ingestion API — inbound data boundary design, validation, backpressure, idempotency, DLQ.
LLM/RAG in product — retrieval, chunking, prompt versioning, eval, cost, failure modes.
Resilience — circuit breaker, retry, bulkhead, health checks.
Supabase Realtime/WebSocket — broadcast, presence, Postgres changes.
Server-Sent Events — text/event-stream format, EventSource, reconnection, keep-alive, CORS.
Cross-OS install/verify knowledge base for the closed tool set /devteam:install supports.
Emit the agent's tier, model, and effort as a table before any other action.
Graphify — autonomous setup: graphify.json, Stop hook, CLAUDE.md.
Detect and migrate a project from dev-team-agents v1 to v2 (multi-provider, symlinks).
Dev Team Agents notifications — format, types, conditions, rotation.
Setup-assistant scan — commands, discovery table, skill/MCP checks.
Registry of mandatory reuse/standardization rules and the review/lint gates that enforce them.
Plan-before-execute — structured plan, approval, replanning.
Token optimization — efficient reads, bash ops, model selection.
Foundational rule — context, coexistence, Plan Mode, language, credentials.
Conditional agent spawn — path patterns and text triggers.
Security review — OWASP Top 10, LGPD/GDPR, API, infrastructure.
Detect and prevent duplicate/redundant API calls in SPA/SSG frontends — tool-agnostic.
Pre-delivery checklist for frontend tasks — run it before declaring any task complete.
Load when the user asks to push — watch GitHub Actions and auto-fix failures until green.
WordPress core, plugin/theme development, and security hardening reference.
Technical/on-page SEO, Core Web Vitals, structured data, GEO/LLM SEO, and quality-gate signals.
Architecture Decision Records — MADR format.
Design system audit — visual patterns, consistency; Design/Consultive.
Automatic per-feature lessons-learned promotion at session close, scoped mirror of /learn.
Backlog — epics, sprints, tasks, DoD, dependencies, estimates.