Agent skills for Claude Desktop

Smart partial rebase for squash-merge repositories.

Intelligent request routing for /toh command.

Implements, refactors, and fixes code changes safely while providing comprehensive validation and change summaries.

Automate Smartrecruiters tasks via Rube MCP (Composio).

Test-Driven Repair — given a failing test, spawn a bounded headless `claude -p` (Read/Edit/Bash only) that makes the test pass without…

PREFERRED BROWSER - Browser for AI agents to carry out any task on the web.

Use when diagnosing PPT Skill setup or failures involving source parsing, Playwright or Chromium rendering, HTML-to-PPTX export, Workbench…

Compact Snakemake workflow patterns. Keep rules short, complex logic in Python modules.

Generate snapcraft.yaml with confinement settings for Ubuntu Snap packages

Use when a `research-brief` workspace has a small paper set plus outline and needs a compact reader-facing briefing instead of a full…

Format content to be eligible for featured snippets and SERP features.

Targets the featured snippet and the people-also-ask slot: picks the snippet type for the query, drafts the 40 to 60 word direct answer…

Use Snips NLU for intent parsing, slot filling, dataset/resource

Diagnose and fix common Snowflake errors and SQL compilation failures.

Implement Snowflake data governance with masking policies, row access policies, tagging, and GDPR/CCPA compliance patterns.

Execute Snowflake incident response with triage, rollback, and postmortem

Execute Snowflake production readiness checklist with monitoring and

Use when packaging an ACM SoCC artifact for the ACM Artifact Review and Badging scheme (Artifacts Available, Evaluated Functional and…

Use when drafting an ACM SoCC author response (rebuttal) during a round's response window, covering the single written turn, answering…

Use when designing or auditing ACM SoCC evaluations, covering real or realistic deployments over simulation, production or representative…

Use when strengthening ACM SoCC reproducibility, covering the testbed and workload description, released code and traces, provenance…