sparc-methodology
Safe 76Structure Software Delivery with SPARC
Complex software work often lacks a consistent path from requirements to completion. This skill applies SPARC phases, specialized modes, and coordinated development workflows.
Unified search
Start with the task. Skillstore will show complete packs first, then individual skills when they are a better match.
Showing results for "agent"
Use these when you need one narrow capability instead of a whole pack.
Structure Software Delivery with SPARC
Complex software work often lacks a consistent path from requirements to completion. This skill applies SPARC phases, specialized modes, and coordinated development workflows.
Debug Chrome Web Apps with DevTools
Chrome web problems often require evidence from several browser surfaces, which makes diagnosis slow and inconsistent. This skill provides a focused workflow for reproducing issues, collecting bounded evidence, and verifying fixes with agent-browser and Chrome DevTools.
Design Reliable Agent Memory Systems
Agents lose useful context across interactions and may retrieve stale or irrelevant memories. This skill provides architectures, storage patterns, retrieval controls, decay methods, and evaluation guidance.
Build Reliable Autonomous Agents
Autonomous workflows often fail because errors, costs, and context grow across steps. This skill provides patterns for bounded planning, execution, reflection, recovery, and human approval.
Validate Agent Skill Files
Skill files can drift from the Agent Skills specification and trigger unreliably. This skill validates structure, frontmatter, descriptions, and evaluation examples.
Manage RouterOS v7 With AI Agents
RouterOS differs from standard Linux, so generic shell advice often fails. This skill gives Claude, Codex, and Claude Code RouterOS-specific CLI, REST API, and automation guidance.
Build AI SDK Features with Current Docs
AI SDK APIs change quickly, which can make generated code outdated. This skill guides Claude, Codex, and Claude Code to current docs and migration patterns.
Build Governed AI Skills
Teams need repeatable agent skills that are documented, tested, and packaged. This skill guides creation, evaluation, governance, and release evidence across Claude, Codex, and Claude Code.
Compact AI Coding Sessions
Long coding chats lose decisions, blockers, and file state. This skill creates concise handoff summaries for Claude, Codex, and Claude Code.
Scan and Consolidate Project Guidance
Project guidance is often scattered across assistant and IDE files. This skill finds those files, summarizes shared rules, and offers one consolidated AGENTS.md.
Create Agent Skills Faster
Writing Agent Skills requires clear structure and valid metadata. This skill guides authors through folders, frontmatter, references, and validation.
Track Project Error Lessons
Teams lose time when agents repeat the same project mistakes. This skill records concise error lessons in a shared project file.