Loading...
Loading...
Found 18,816 Skills
Use when synthesizing multiple sources into coherent knowledge bases, performing multi-source analysis, or creating topic expertise from URLs and files. Also use when encountering content integration tasks requiring connections across disparate materials.
Bitcoin L1 wallet for agents - check balances, send BTC, manage UTXOs. Extends to Stacks L2 (STX, DeFi) and Pillar smart wallets (sBTC yield).
Interactive onboarding workflow that interviews users to understand their coding goals and generates PR-ready implementation plans. Use when starting a new development task to ensure clear requirements and structured execution.
Find broken wiki-links in the vault. Read-only analysis — scans for [[links]] and verifies target files exist. No writes, no dependencies.
Search for music resources (songs, albums, lossless music), and obtain resource links from Quark Cloud Drive, Baidu Netdisk, Alibaba Cloud Drive, and UC Cloud Drive. Trigger words: find music, search for songs, lossless music, FLAC download, music cloud drive, song download, album resources, music resources, APE download, DSD music, Hi-Res.
Analyze won and lost deals for patterns, insights, and actionable learnings. Use when user says "win/loss analysis", "why did we lose", "deal patterns", "win themes", or asks about deal outcome trends. Do NOT use for visual HTML reports — use /octave:win-loss-report instead.
Incrementally update reverse-engineering docs based on git changes since they were last generated. Reads the commit hash from .stackshift-docs-meta.json, diffs against HEAD, analyzes only the changed files, and surgically updates the affected docs. Saves time and cost compared to full regeneration.
Inline adversarial plan review — 3 sequential checks (Feasibility, Completeness, Scope & Alignment) performed by the calling LLM in its own context. No subagents spawned. Call after saving a plan. Returns GATE_PASS or GATE_FAIL with blocking issues.
Project-specific environment setup for issue workflows. Calculates test ports and provides initialization context for minions.
Open a new context session at the start of a leader agent workflow. Records agentName, storyId, and phase in wint.contextSessions, emitting a structured SESSION CREATED block for downstream workers to inherit.
Ensures tasks are genuinely resolved before marking them done. Activates at task checkpoints during plan execution — validates that fixes actually work, tests genuinely pass, and acceptance criteria are met. Prevents premature completion declarations.
Generate JSDoc/docstrings for functions