Agent skills for Claude Desktop

Async task processing with Celery, ARQ, and Redis for Python backends.

Symptom-based background task troubleshooting - decision trees for 'task never runs', 'task terminates early', 'works in dev not prod'…

Complete background task API reference - BGTaskScheduler, BGAppRefreshTask, BGProcessingTask, BGContinuedProcessingTask (iOS 26)…

Audit a domain's backlink profile using the SemRush API.

Find referring domains that link to multiple competitors but not to your site, then enrich with authority, anchor samples, and outreach…

Automate backlink submission for directories, forums, and other non-blog resources using AI and browser automation

[REPLACED by pipeline-quarantine on 2026-06-20] Quarantine moderation — merged into pipeline-quarantine (step 2).

Refine raw ideas and backlog items into decision-complete, actionable work and decide whether they need discovery, an Epic, implementation…

Run real-host public-facade regressions or diagnose and recover SagaSmith narrative campaigns.

Build robust, production-grade backtesting systems that avoid common pitfalls and produce reliable strategy performance estimates.

Make a timestamped backup of the whole project — a full copy of the file tree plus an infos.txt with the date, project name, size, file…

Backup strategies and disaster recovery across all database engines.

Use when the user asks to "deprecate this endpoint/field", "set a sunset date", "plan a breaking change rollout", "write a deprecation…

Help with BAdI (Business Add-In) development, the ABAP enhancement framework, and the clean core level classification of enhancement…

Secure key management for AI agents. Use when handling private keys, API secrets, wallet credentials, or when building systems that need…

Baixa os autos completos em PDF de um ou mais processos do PJE 1º grau de qualquer tribunal brasileiro que use PJE/CNJ (TJCE, TJRN, TJPE…

Compare production WordPress sites against their baked static versions to find differences.

Write an Architecture Decision Record. Use when a decision is hard to reverse — technology choice, service boundary, data model, protocol…

Review a design or a running system for cost.

Get a new user or contributor productive with this agent system.

Run a task end to end through the full delivery pipeline — product discovery, architecture, build, verification, release.