Use when starting work on code with non-obvious constraints or history, debugging, making architectural decisions, working with external services, when the user references something from a past session, or after completing analyses, hitting unexpected results, or resolving issues worth capturing for future sessions. --- <subagent-stop> If dispatched as a subagent to execute a specific task, skip this. </subagent-stop> Kilroy is the project's knowledge base — notes from past agent sessions, teammates, and humans. It persists across sessions, machines, and the project. It is NOT local auto-memory. **If Kilroy tools are failing or returning auth errors, re-run the install script from the project's web dashboard.** ## Project Routing Check `.kilroy/config.toml` for the project mapping. If it exists and has a `project` field, pass that value as the `project` parameter on every Kilroy tool call.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Route API calls through the Aegis credential proxy — keeps raw API keys out of the agent context
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Audit bloated agent-instruction files (CLAUDE.md, AGENTS.md, and their local/user-level variants) and rewrite them lean, or author a new one from scratch following the 200-line "recipe book" principle. Use this skill whenever the user mentions CLAUDE.md, AGENTS.md, agent instruction file, project memory file, context file, token budget, context bloat, "my CLAUDE.md is too big", trimming CLAUDE.md, auditing AGENTS.md, writing AGENTS.md for a new project, or any discussion of what belongs in the agent-instruction-file hierarchy (enterprise, project, user-level, project-local). Also trigger when such a file is shown in context and is visibly long (over 200 lines) or contains anti-patterns like embedded API docs, negative "Don't do X" rules, step-by-step tutorials, or preemptive file-preload instructions — even if the user doesn't explicitly ask for optimization, proactively offer to use it.
- 📁 agents/
- 📁 references/
- 📄 SKILL.md
Token-efficient Chrome tab inspection, interaction, and patching via local bridge extension (CLI: bbx). Reads live DOM, styles, console, network, and storage from a real Chrome tab with lower token cost than screenshots.
Use this skill when the user types /improve-context or asks to capture learnings, improve documentation, or enrich the knowledge base based on this conversation.
- 📁 references/
- 📁 scripts/
- 📄 .env.example
- 📄 config.example.yaml
- 📄 README.md
Trade on Hyperliquid — spot and perpetual futures. Supports market orders (IOC), limit orders (GTC), leverage setting, and WDK wallet. Triggers: buy ETH spot, sell BTC, long ETH, short BTC, open long, open short, close position, perp trade, check balance, Hyperliquid positions, limit order, limit buy, limit sell, open orders, cancel order, modify order, GTC.
api-change-safe skill reference
- 📄 approval_dialog.applescript
- 📄 container_claude_md.txt
- 📄 Dockerfile
This skill should be used when the user asks to run a command on the host machine, open an application on the host, send a desktop notification to the user, list previously approved host commands, or manage long-running background processes (daemons) on the host. Provides the host-tools binary at /home/ai-pod/.local/bin/host-tools.
Read and summarize the user's local work notes from `~/work/notes/` and `~/work/shared/`. Use when the user asks to "summarize notes", "sync notes", "review my notes", "what's in my work notes", or any operation that needs the contents of their personal markdown notebook. Returns the raw markdown contents of all .md files in those folders so the calling assistant can summarize, sync, or paraphrase as the user instructs.
- 📁 references/
- 📁 scripts/
- 📁 tests/
- 📄 SKILL.md
>-
- 📄 PATTERNS.md
- 📄 REFERENCE.md
- 📄 SKILL.md
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations. --- # Next.js Cache Components > **Auto-activation**: This skill activates automatically in projects with `cacheComponents: true` in next.config. ## Project Detection When starting work in a Next.js project, check if Cache Components are enabled: ```bash # Check next.config.ts or next.config.js for cacheComponents grep -r "cacheComponents" next.config.* 2>/dev/null ``` If `cacheComponents: true` is found, apply this skill's patterns proactively when: - Writing React Server Components - Implementing data fetching - Creating Server Actions with mutations - Optimizing page performance - Reviewing existing component code Cache Components enable **Partial Prerendering (PPR)** - mixing static HTML shells with dynamic streaming content for optimal performance. ## Philosophy: Code Over Configuration Cache Components represents a shift from **segment configuration** to **compositional code**: | Before (Deprecated) | After (Cache Components) | | --------------------------------------- | ----------------------------------------- | | `export const r
