Loading...
Loading...
Found 6,247 Skills
Agent skill for pseudocode - invoke with $agent-pseudocode
Opteo integration. Manage data, records, and automate workflows. Use when the user wants to interact with Opteo data.
R&D management expertise for R&D portfolio management, technology roadmapping, research methodology, patent strategy, lab management, academic partnerships, and regulatory pathways. Use when managing research programs, planning technology roadmaps, or building patent portfolios.
Perform a thorough quality review of a pull request or feature branch before merging. Use this skill whenever the user asks to review a PR, check if code is production-ready, assess quality, verify docs are updated, or asks "is this ready to merge?", "review this PR", "check quality", "is this production ready?", or similar. Also use when reviewing your own work before submitting.
Audit design documents for missing decisions, compatibility risks, rollout gaps, and observability omissions. Use whenever the user asks to review a design doc, architecture proposal, implementation-facing design, plan, or design-adjacent markdown file for completeness, migration strategy, rollback, data handling, or suggested additions without directly editing the document. Also trigger on short requests such as `review <file>.md` or `audit <file>.md` when the target looks like a design, plan, architecture, proposal, or decision document.
Use these skills when you need to troubleshoot performance bottlenecks, analyze query execution plans, identify resource-heavy processes, and monitor system-level PromQL metrics.
Run a session retrospective against the CLAUDE.md, skills, and hooks — identify guidance violations, stale rules, and gaps. Use when user says 'reflect on this session', 'what did we learn', 'post-mortem this work', 'what should we update in CLAUDE.md', or 'are our skills still right'. Do NOT use for code review (use /review-diff), PR prep (use /create-pr), or creating new skills from scratch (use /create-or-audit-skill).
Use when you find additional work needed during task execution that's not in the original task description, to report it to ZŌE for review
Equips engineering managers with persuasion techniques and positioning strategies for getting things done without direct authority — produces tactical methods (Nemawashi, Decoy Pricing, Reverse Psychology, LMDTFY, Engineered Serendipity), conversation techniques for disarming resistance (Label the Concern, Get to "That's Right"), a headcount argument framework, and a three-level visibility/trust model. Use when the user says "how do I convince," "persuade," "get buy-in," "stakeholder management," "influence without authority," "get approval," "calibration," "nobody takes me seriously," "how do I get headcount," or "organizational politics." Do NOT use when the issue is the user's relationship with their own manager (use managing-up).
/cs:freeze <decision> <days> — Lock a strategic decision for a cooldown period to prevent impulse reversal. Mirrors gstack's safety primitives for the business layer.
/cs:caio-review <plan> — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model selection, risk classification, cost economics, or AI hiring.
DataTrails integration. Manage data, records, and automate workflows. Use when the user wants to interact with DataTrails data.