আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Run a SonarCloud cleanup sprint. Fetches fresh issues via public API, generates a detailed report with code snippets, creates a cleanup branch, and tracks fixes with the TodoWrite tool. Use when starting a code quality cleanup sprint or when you need a current snapshot of SonarCloud issues.
Rapid assessment and initial response processes for production incidents
Manages quality gates and checkpoints to ensure work meets standards before proceeding to next phases. Use when you need to verify work quality, set quality standards, or decide if work is ready to proceed. Defines quality criteria, checks work against criteria, and makes go/no-go decisions.
Plan and structure moderated or unmoderated user research sessions that target the given persona and objectives.
Milestone-anchored development methodology. Use when planning milestones, starting sessions, creating implementation guides, or reviewing process. Triggers: milestone planning, session workflow, implementation guide, session summary, milestone review, maintenance session, PROJECT.md, session closeout, development session, planning phase, post session review. File patterns: _context/milestones/*.md, _context/sessions/*.md, PROJECT.md
Generate comprehensive coverage report with requirement traceability mapping. Shows coverage per REQ-*, gaps, trends, and recommendations. Use for status dashboards, quality reviews, or compliance audits.
BA Domain Skill: IIBA BABOK v3 orchestrator. 6 Knowledge Areas (Planning, Elicitation, Analysis, Traceability, Evaluation, Management), requirements engineering, stakeholder analysis, process modeling, use cases, user stories. 30 tasks, competencies, techniques.
Transform ideas into validated, dependency-mapped Linear stories. Activates when user wants to develop a new feature idea, create Linear stories from a concept, brainstorm and plan implementation, or mentions "new feature", "I want to build", "break into stories", "create issues for". Commands: /ideate, /ideate:brainstorm, /ideate:pressure-test, /ideate:plan, /ideate:stories, /ideate:upload, /ideate:setup.
Use for systematic debugging and root cause analysis with both Codex and Gemini. Triggers on "council debug", "council root cause", "have council investigate this bug", "council find the issue".
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.
Automatically extract technical requirements from design references when user mentions Figma, uploads images, or says "implement this design". Analyzes colors, typography, spacing, layout, and maps to WordPress blocks or Drupal paragraph fields. Provides detailed specifications for developers including exact values, responsive behavior, and accessibility requirements.
Specification-Driven Development workflow for planning features using GitHub Spec Kit. Use when starting new features, creating specifications, running /speckit commands, or when the user mentions spec, specification, planning, or SDD workflow.
Conducts an audit of a Pull Request, merges it into main, and synchronizes the local environment. Use this skill when a PR is ready for final review and integration.
Create ATOMIC implementation plan for a single backend task. Each step has TDD, exact code, and verification command. IMPORTANT: This skill creates MICRO-LEVEL atomic steps, NOT macro architecture plans. For architecture planning or feature scoping, use EnterPlanMode instead. Use this skill when: - Running /backend.plan command - User explicitly asks for "atomic steps", "step-by-step plan with verification" - Have a specific task from docs/reference/backend/tasks/ and need implementation steps - Need granular TDD steps: Types → DB → Test (failing) → Implementation → Test (passing) → API DO NOT use for: - Architecture planning (use EnterPlanMode) - General development planning - Feature scoping or estimation Output: Present plan to user (not saved to file), each step includes Files, Action, and Verify command.
Transform a product briefing into comprehensive, research-backed product management artifacts. This skill conducts domain-expert research BEFORE user questioning to enable smarter questions and pre-populated artifacts with validated content. Uses Context7 for technology documentation, WebSearch for market/architecture/security research, and WebFetch for deep-dive analysis. Generates 4 research-enriched files: - product.md (product vision with market research citations) - roadmap.md (12-month roadmap with architecture research) - architecture.md (technical design with extensive Context7 references) - adr.md (architectural decisions with research-justified rationale) Triggers: "create product vision", "define new product", "product planning", "bootstrap product", "product documentation", "start new product", "product briefing"
Generate structured handoff for session transitions or task boundaries. Use before clearing session, after completing a task group, or when context degradation is suspected.
Expert in making multi-agent systems resilient. Specializes in detecting loops, hallucinations, and failures, and implementing self-healing workflows. Use when designing error handling for agent systems, implementing retry strategies, or building resilient AI workflows.
CRITICAL: When the user asks to implement/build/add a feature or mentions feature development, invoke this skill FIRST (BEFORE invoking feature-dev or any other feature development workflow). This establishes test-driven development requirements and ensures tests are written early and explicitly planned as separate steps. Do NOT wait until feature-dev is already running - invoke this BEFORE starting any feature development workflow.
Skill for identifying the gap between a user's request and the project's current reality (code, existing ADRs, and documentation). Used for (1) uncovering discrepancies between intent and implementation, (2) gathering factual evidence from the codebase and SSOT, and (3) establishing a grounded starting point for new architectural decisions.
