astro-tailwind-cloudflare-stack
Complete full-stack development with Astro (Islands Architecture), Tailwind CSS (utility-first styling), and CloudFlare Workers/D1/KV (edge computing and hybrid database). Strategic guidance plus practical implementation patterns for building fast, globally-distributed web applications.
cloudflare-backend-architect
Deep technical guide for building backends with CloudFlare Workers, D1 (SQL), KV (NoSQL), R2 (storage), and hybrid database strategies. Covers edge computing patterns, data modeling, performance optimization, and cost management for globally-distributed serverless applications.
code-reviewer
Code review guidelines focusing on quality, maintainability, and SOLID principles. Covers readability, performance, security, testing, and professional code review practices for JavaScript and web applications.
debugging-assistant
Systematic debugging methodology, root cause analysis, performance profiling, and troubleshooting strategies for JavaScript and web applications. Covers VSCode debugging tools, console techniques, and professional debugging workflows.
threejs-graphics-optimizer
Performance optimization rules for THREE.js and graphics programming. Covers mobile-first optimization, fallback patterns, memory management, render loop efficiency, and general graphics best practices for smooth 60fps experiences across devices.
vanilla-js-architect
Clean, modular vanilla JavaScript architecture with JSDoc standards, DDD-inspired layering, and best practices for building maintainable applications without frameworks. Focuses on separation of concerns, pure functions, and professional code organization.
handoff
Use when explicitly asked to compact the current Pi session into a local handoff document that a fresh agent can use to continue the work.
manage-scheduled-tasks
Use when creating, editing, validating, manually running, or debugging Pi scheduled task Markdown files managed by the scheduled-tasks extension.
agent-engineering
Use when designing, building, debugging, or reviewing AI coding agent harnesses — single-agent shape (tools, prompts, context, hooks, model selection) or multi-phase workflows (orchestration, subagents, verifiers, ticket-to-PR pipelines). Covers model-specific guidance for Claude 4.x and GPT-5.x families, and platform-specific patterns for Claude Code, the Claude Agent SDK, and Pi. Invoke when the user asks about harness design, scaffold patterns, agent loops, subagent orchestration, verification strategy, context compaction, plan/implement/verify pipelines, or how a particular model changes harness choices.
challenge
Use when stress-testing a concrete plan, proposal, design, architecture decision, or implementation approach before implementation. Challenges material assumptions, failure modes, alternatives, and evidence gaps; use review for completed changes.
clarify
Use when requirements, scope, product behavior, edge-case policy, acceptance criteria, or design intent are fuzzy and need an interview before planning or implementation.
create-html-artifact
Use when the user asks to create or polish a standalone HTML artifact such as an HTML report, interactive explainer, visual plan, dashboard, slide deck, diagram, prototype, or throwaway HTML tool.
create-jira-ticket
Use when creating a Jira ticket to plan upcoming work. Guides ticket drafting with clear structure, self-contained context, and testable acceptance criteria, then creates the ticket via the available Jira/Atlassian broker tool.
create-skill
Use when creating a new skill or updating an existing skill
diagnose
Use when debugging bugs, failures, exceptions, flaky behavior, regressions, or performance problems where the cause is not already proven.
frontend-design
Use when the user asks to build web components, pages, or applications that need distinctive, production-grade frontend interfaces with high design quality
handoff-to-worktree
Use when explicitly asked to hand a task to a new Pi agent in a newly created Herdr-managed Git worktree.
herdr
Use when the user explicitly mentions Herdr, asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent, or asks to create, open, list, remove, or otherwise manage a Git worktree. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1.
plan
Use when turning a clarified implementation request, feature idea, bugfix, refactor, workflow change, or design discussion into an execution-ready plan that a fresh coding agent can implement autonomously, especially before running /goal.
playwright
Reference skill for browser automation: web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
review
Use when reviewing code changes, a working tree, branch, commit range, pull request, patch, or implementation against acceptance criteria. Prepares evidence, runs deterministic checks, invokes the saved review workflow, and presents its findings.
test-driven-development
Use when implementing a feature or bugfix that involves writing meaningful application logic
svelte5-development
Comprehensive Svelte 5 and SvelteKit development guidance. Use this skill when building Svelte components, working with runes, or developing SvelteKit applications. Covers reactive patterns, component architecture, routing, and data loading.
expert-registry
>-
knowledge-curator
>-
knowledge-sync
>-
skill-manager
>-
agent-manager
>-
aida
This skill routes /aida commands to appropriate handlers - configuration,
claude-md-manager
>-
hook-manager
>-
memento
>-
permissions
>-
plugin-manager
>-
bitbucket-server
This skill enables interaction with BitBucket Server REST API for Pull Request management. Use when the user wants to create, review, comment on, merge, list pull requests, read comments, or manage tasks on BitBucket Server.
debrief
Capture session learnings and update project docs. Use when ending a session, after completing a feature, or when asked to "debrief", "capture learnings", "update project knowledge", or "what did we learn".
deep-interview
Start a structured interview to gather requirements for complex features. Use when tackling multi-layer features, validating PRDs, or defining scope for implementation.
mine-history
Extract and synthesize learnings from past Claude Code session transcripts into project documentation. Use when asked to "mine history", "extract learnings from past sessions", "what patterns keep recurring", or "improve docs from history".
trim-pr
Trim a PR before merging - remove complexity that accumulated during development. Use when preparing to merge, cleaning up code, trimming unnecessary complexity, or asked to simplify a PR.
update-pr
Creates comprehensive PR descriptions by systematically reviewing ALL changes - features, bug fixes, tests, docs, and infrastructure. Use when user asks to "update the PR", "prepare PR for review", "write PR description", or "document branch changes". Requires gh CLI.
analyze-deps
Analyze dependency updates and generate a changelog report with breaking changes, new features, and actionable recommendations. Use after updating packages, before planned upgrades (preflight), or to research what changed between specific versions. Triggers on "analyze deps", "analyze dependencies", "dependency update report", "breaking changes in update", "what changed in dependency update".
ask-expert
Creates expert consultation documents with code extraction, git diffs, and size tracking (125KB limit). Use when user asks to "create an expert consultation document", "prepare code for expert review", "gather architecture context", or needs comprehensive technical documentation for external analysis. Requires Node.js 18+.
pr-audit-angles
Multi-angle parallel audit of a large PR or branch before merge. Dispatches one capable subagent per angle (matched to the changed surface), each anchored to the repo's own conventions and producing a uniform Blockers / Important / New-concepts-verdict / Verified-clean report; the orchestrator verifies every candidate against current code and synthesizes one merge-readiness verdict. Use when a PR spans multiple subsystems, when you worry it introduces new concepts where patterns already exist, or when asked to "audit before merge", "review from every angle", "is this safe to merge".
pr-fix-angles
Parallel disjoint-lane fix campaign — the execution companion to pr-audit-angles. Takes a set of verified findings and fixes ALL of them across multiple subagents that edit IN PARALLEL without merge conflicts, by partitioning the findings into lanes of exclusive file ownership. A lane whose findings share a file runs as sequential stages; independent lanes run concurrently. Each agent returns a structured completed/deferred/tests report; the orchestrator owns the single final lint→build→test gate and never commits without you. Use after an audit ("fix all the findings", "patch everything blocker→minor", "make it merge-ready"), or for any many-file coordinated remediation. Triggers on "fix all findings", "fix campaign", "remediate the PR".
sf-vlocity-build-deploy
>
sf-ai-agentforce-testing
>
sf-ai-agentforce
>
sf-connected-apps
>
sf-ai-agentforce-observability
>
sf-ai-agentforce-persona
>
Page 1311 of 1666 · 83262 results