Loading...
Loading...
Found 6,567 Skills
(NS) Ad-hoc coding worker — bug fixes, small refactors, scripts, migrations — without full SDD. Entry priority 5: use for "just implement this", "quick fix", or concrete coding without execution-handoff (also C2 under ns-code-autonomous). Do NOT use for GitLab ISSUE_URL (ns-execution-gitlab-issue), multi-day/version scope (ns-spec-driven), diagnosis-only (ns-code-investigator), or when execution-handoff.md exists. Do NOT generate requirements/tasks/handoff.
Trim a spec, ADR set, or design doc down to what a builder needs, without losing a fact. TRIGGER when: user says a spec is 'too long' or 'bloated'; user asks what to remove from it, or wants it cut to 'just what we need to build'.
AI Berkshire Skill: Buffett Value Investment Pre-Purchase Checklist. Source: skills/investment-checklist.md.
Standing backlog of work only a human can do — env vars, DNS, dashboard config, third-party signups, decisions. Other skills file into it mid-run without halting; `/manual-tasks` walks the open list, doing what it can and asking for the rest. Reads `.claude/conventions.yaml` for the Linear team and evergreen project.
Use when the operator explicitly asks to iterate on a bounded objective until it is satisfied, such as a refactor, cleanup, documentation rewrite, non-ticket change, or ticket follow-up. Trigger on goal-loop, loop until done, iterate until clean, max rounds, or similar language. Do not self-trigger for ordinary implementation. Never commits.
Run one dev-loop session as the driver - preflight, select, one spec end to end. Harness-generic - grooming drafts and takes run in fresh native subagents of whatever harness drives, takes in their own worktrees (an explicit invocation request may route takes through a runner file instead); the gate stays yours.
Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
Top-level map of the skill fleet, for "which skill does this need?" when the answer is not obvious. Invoke when a task's ownership is UNCLEAR or it spans MULTIPLE domains. It routes intent → the right router / skill / recipe and names how to invoke each. When the primary goal already names a domain, enter that domain router or member directly instead. Curates the ADOPTED surface only; the full installed roster lives in the skill manifest.
Meta-router for the workflow recipes in ~/.claude/workflows/ (personal layer) and the current repo's .claude/workflows/ (shadows personal on name collision). Invoke before any loop-shaped work — audits, consensus gates, plan→build lifecycles, findings triage. Even a 1% chance this applies means invoke it.
Enable a symmetric collaborative closed-loop of "Primary Executor + Independent Reviewer" between Codex and Claude Code via native CLI. This applies when users require the two models to work together, cross-validate, conduct independent reviews, revise until ACK, or when tasks involve product requirement convergence, complex solutions, cross-module development, migration, security, major refactoring, and high-quality delivery; regardless of whether initiated from Codex or Claude Code, the current model will take charge and fully invoke the other party to complete requirement challenge, scheme gatekeeping, implementation cold review, and final acceptance.
Multi-perspective in-depth analysis. Use multiple Sub-agents to act as consultants with different thinking frameworks, conduct independent analysis on the same material, then cross-summarize consensus and differences, and produce a structured diagnostic report. Triggered when the user says "Help me with multi-perspective analysis", "Multi-dimensional analysis", "Look at it from multiple perspectives", or "Help me diagnose it".
Explain the Ralph Loop plugin, how it works, and available skills. Use when the user asks for help with ralph loop, wants to understand the technique, or needs usage examples.