Loading...
Loading...
Found 10,136 Skills
Reference guide for Agentica multi-agent infrastructure APIs
Background Agent Pings
Extract experience from the current conversation and automatically generate reusable Claude Code Skills. Use when user wants to extract a skill, summarize into a skill, solidify experience, generate a skill, create a skill from context, save as a skill, or turn experience into a skill.
Updates model references across all skill files when new Claude models are released. Use when Anthropic releases new Claude models to keep skills current.
Use when substantive documents (reviews, analyses, synthesis documents) need adversarial review to strengthen arguments, identify weak points, and challenge assumptions before editorial polish (mandatory for Writer → Devil's Advocate pairing protocol)
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
GitLab repository operations. ALWAYS use this skill when user wants to: (1) clone repositories, (2) fork projects, (3) view repo info, (4) create new projects, (5) archive/delete repos, (6) manage repo settings.
Create conventional commit messages by analyzing staged changes. Generates semantic commit messages following the Conventional Commits specification. Use when user says "commit", "save changes", or "create commit".
Audit specification quality and generate compliance report.
Automated fix skill that reads review reports and applies fixes to ADR documents - handles broken links, element IDs, missing files, and iterative improvement
Automate Gmail tasks via Rube MCP (Composio): send/reply, search, labels, drafts, attachments. Always search tools first for current schemas.
Automate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels. Always search tools first for current schemas.