Implement reliability patterns for Adobe APIs: circuit breakers for IMS/Firefly, idempotency for PDF Services operations, graceful degradation when Adobe is down, and dead letter…
Analyze, plan, and execute Adobe SDK upgrades — including the critical JWT-to-OAuth migration, PDF Services SDK v3-to-v4, and Photoshop API endpoint changes (cutout v1 to…
Adopt a virtual Akita dog at animalhouse.ai. One-person dog. Bonds to its primary caretaker. Distrusts others. Feeding every 6 hours. Rare tier dog.
Adopt a virtual pet as an AI agent. Name it, feed it, watch it grow. 64+ species from cats and dogs to AI-native creatures. Real-time hunger, 5 evolution sta...
Drafts a Petition for Adoption for U.S. family law courts (stepparent, relative, agency, independent).
ADP Workforce Now integration. Manage Persons, Organizations, Jobs, Payrolls, Benefitses, Talents. Use when the user wants to interact with ADP Workforce Now data.
Add ADR references to code for traceability. TRIGGERS - ADR traceability, code reference, document decision in code.
Use when deeply validating an ADR's format, approval chain, linkage to standards, or deciding the correct ADR status
docs/adr/** 변경 시 AI 리뷰어가 호출하는 ADR 전용 비평 페르소나. 추론 깊이, 대안, 결과를 stress-test 한다 (내용 비평만; 문체 비평 제외).
adr-design_skill — Entwirft System-/Lösungsarchitektur und dokumentiert Entscheidungen als ADR mit Trade-offs. Trigger: Architektur/ADR.
Build or rebuild the ADR index + dependency graph by running scripts/import.mjs (handles v3-style and plugin-style ADR formats; one Bash call vs hundreds of MCP round-trips)
ADR知見の体系的参照・適用。主要ADR抜粋（ADR_010, 013, 016, 019, 020, 021）・ADR検索・参照方法・技術決定パターン集・ADR作成判断基準。Phase C以降の技術決定時に使用。
Writes and maintains ADRs (MADR, Nygard, Y-Statement) and runs decision checkpoints before/during work—trigger matrix, option briefs, proposed ADRs.
Read back adr-patterns + adr-edges namespaces, surface dangling refs / supersede cycles / status mismatches; exit 1 on cycles
Write Architectural Decision Records following MADR template. Applies Definition of Done criteria, marks gaps for later completion.
Automate Adrapid tasks via Rube MCP (Composio). Always search tools first for current schemas. — from ComeOnOliver/skillshub
Kartiert Adressatinnen und Adressaten nach § 1 LobbyRG: Bundestagsorgane, Mitglieder, Fraktionen, Gruppen, Mitarbeitende, Bundesregierung und Leitungsebenen bis Referatsleitung.
AdRoll integration. Manage data, records, and automate workflows. Use when the user wants to interact with AdRoll data.
AdShares integration. Manage data, records, and automate workflows. Use when the user wants to interact with AdShares data.
Run a cross-platform performance review for this brand. Use when the user asks for a performance review, weekly review, or wants to see how campaigns are doing across all…
Find and fix wasted ad spend across all platforms. Use when the user wants to reduce wasted spend, find inefficiencies, or optimize budget.
Meta-skill — defines when to apply other skills automatically without being asked
Keep EN/PT README.md pairs in parity across a repo (and across twin repos like ai-dev-toolkit + ai-dev-toolkit-pt-br).
Losslessly compress PNG and SVG assets in place and generate .webp siblings for every raster image. Use when the user asks to "compress assets", "optimize images", "shrink the…
Optimize context window usage — compact stale data, compress via summarization, preserve active state
Keep sessions focused and efficient — prune stale outputs, preserve active state, recommend compaction
Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking
Graceful degradation when primary approach fails. Try alternates in priority order; record which path succeeded for future routing.
Composite skill — query, capture, improve, and persist knowledge in one workflow. Chains recall (RAG query) → sync-memories (write durable note) → rag-curate (improve weak…
Default execution rhythm — inspect → act → verify → checkpoint — applied iteratively until the task is done or a clear blocker emerges.
Persist decisions, preferences, and project state across sessions using structured memory types
Orchestrate teams of agents — DAG execution, routing, state sharing, failure recovery. Use when coordinating parallel agents in task pipelines with dependencies or distributing…
Decide the highest-value safe thing to do right now in the active repo or workspace.
Composite skill — first-touch workflow for an unfamiliar repo. Chains adt-repo-intake (understand) → audit-deep (health check) → config-drift-detect (gate audit) → init (CLAUDE.md…
Optimize context usage for the session by reducing bloat, improving token efficiency, and focusing on relevant areas.
Coordinate multiple subagents/worktrees for parallel workstreams. Decomposes larger tasks into independent sub-tasks, dispatches each to a dedicated agent.
Fan out N independent investigations as parallel agents in a single tool-use block, then roll up the results.
End-to-end performance audit composite — baseline the slow metric, profile to find the real hotspot, implement the smallest targeted fix, re-benchmark to confirm improvement,…
Build a compact, validation-gated implementation plan for multi-step, risky, or ambiguous work — typically when phases need explicit checkpoints, the change touches multiple…
Diff the Anthropic `claude-plugins-official` marketplace against installed plugins and surface the delta, filtering known-unwanted entries (language LSPs you don't use, SaaS…
Audit corpus distribution by source type and repo; identify coverage gaps and underindexed topics
Manually improve corpus quality by adding missing docs and filling retrieval gaps
Detect and fix stale chunks (files that changed or were deleted since last indexing)
Ship validated changes with repeatable release evidence — version bump, changelog, tag, and optional GitHub release
Recover session state from git, plans, and open PRs, then continue from the last completed phase without repeating work
Route a task to the most fitting skill or agent. Parses user intent, checks installed-skill inventory, and picks the best match (single skill or chain).
Composite skill — understand a problem area, plan the work, execute it, and ship it in one chained workflow.
Autonomous error recovery — detect failures, diagnose root cause, apply fixes, and resume without stopping
Composite skill — start-of-day routine. Chains wake-up (compact brief) → next-priority (decide) → pr-snapshot (PR queue) → context-pack (load relevant context if work-intent).
Install and verify ADT.ai: pip install, PATH and environment variables, Oracle Instant Client and SQLcl, connections and wallets, and the adtai doctor health check and update…
Create a committed per-feature spec under `docs/specs/YYYY-MM-DD-/{spec,tasks}.md` with frontmatter (status, created, owner, pr, tags).
Sync files (skills, packages/core/patterns, agents, specs) from EN canonical repo to PT mirror, inserting "Tradução pendente" blockquote after YAML frontmatter, then open PR.
Assemble a Jira/Linear/GitHub-Issue body from recent commits, diff, and branch context
Recover a PR whose head SHA disagrees with its branch ref (webhook desync). Force-push and close+reopen rarely fix it — recreate the PR.
Building and maintaining social connections as an adult. Use when someone is lonely, has moved to a new city, wants to make friends, struggles in group settings, or needs to…
Claim and work on beads safely with proper coordination. Use when starting work, finishing work, or finding the next task.
Produces a plain-language comparison of advance directives and POLST/MOLST forms, covering legal status, clinician signatures, emergency precedence, clinical appropriateness, and…
Drafts jurisdiction-specific Advance Health Care Directive packages with agent appointment, living will instructions, HIPAA authorization bridge, organ donation preferences, and…
Claude Code mastery for power users. Build agents, MCP servers, publish plugins. Use when: user wants to create agents, build integrations, or publish plugins.
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, and hybrid search for distributed AI systems.