Claude Skills by tools-only

These are the release notes for gptme version v0.3.1.

These are the release notes for gptme version v0.4.2.

These are the release notes for gptme version v0.6.0.

These are the release notes for gptme version v0.7.0.

Create TaskList component implementing navigable task list with status icons. Uses pi-tui Component interface with custom rendering (not wrapping SelectList due to different rendering requirements: status icons, blocked indicators, etc.)

Create TaskDetail component showing full task info with markdown rendering.

Search .flow/memory/ for entries relevant to the current task or request.

Manually trigger plan-sync to update downstream task specs after implementation drift

Synchronize local branch with remote repository.

(Branch question already asked in SKILL.md before reading this file) **CRITICAL**: If you are about to create: - a markdown TODO list, - a task list outside `.flow/`, - or any plan files outside `.flow/`, **STOP** and instead: - create/update tasks in `.flow/` using `flowctl`, - record details in the epic/task spec markdown.

(Branch question already asked in SKILL.md before reading this file) **CRITICAL**: If you are about to create: - a markdown TODO list, - a task list outside `.flow/`, - or any plan files outside `.flow/`, **STOP** and instead: - create/update tasks in `.flow/` using `flowctl`, - record details in the epic/task spec markdown.

You are a precise browser automation agent that interacts with websites through structured commands. Your role is to: 1. Analyze the provided webpage elements and structure 2. Plan a sequence of actions to accomplish the given task 3. Respond with valid JSON containing your action sequence and state assessment INPUT STRUCTURE: 1. Current URL: The webpage you're currently on 2. Available Tabs: List of open browser tabs 3. Interactive Elements: List in the format: id[:]<element_type>element_tex...

* `id`: action 1 name and description * `id`: action 2 name and description ... * `id`: action X name and description * `id`: action Y name and description ... ``` Note that `id` is identifier for interaction. `ids` can be decomposed into `<role_first_letter><index>[:]` where `<index>` is the index of the element in the list of elements with the same role and `<role_first_letter>` are: - `I` for input fields (textbox, select, checkbox, etc.) - `B` for buttons - `L` for links - `F` for figures...

Common issues and solutions: **Agent Initialization Failures** - Error: AI SDK provider configuration invalid - Solution: Verify API keys in environment variables, check provider-specific setup requirements **Handoff Execution Errors** - Error: Agent handoff fails or creates circular dependencies - Solution: Review handoff rules for clarity, implement handoff depth limits, add fallback agents **Routing Logic Failures** - Error: Tasks routed to incorrect agent or no agent - Solution: Refine ro...

| Error | Cause | Solution | |-------|-------|----------| | `Missing errors during migration` | Sampling mismatch | Run both tools at 100% during parallel | | `Alert parity issues` | Different alert models | Map alert rules carefully before cutover | | `Data export failed` | API rate limits | Use pagination and backoff | | `Team unfamiliar with UI` | No training | Schedule Sentry training sessions |

| Error | Cause | Solution | |-------|-------|----------| | Model not available | Subscription tier or access | Check subscription, request access | | Rate limited | Too many requests | Switch model or wait for reset | | Context too long | Model limit exceeded | Use larger context model | | Poor quality output | Wrong model for task | Switch to higher quality model |

| Error | Cause | Solution | |-------|-------|----------| | Data transmission blocked | Exclusion pattern matched | Review pattern, whitelist if safe | | Retention violation | Data not deleted on schedule | Check deletion job, manual cleanup | | Consent missing | User not opted in | Prompt for consent, block until granted | | Region mismatch | Data sent to wrong region | Update residency configuration | | Audit gap | Logging disabled | Enable audit logging, investigate gap |

| Error | Cause | Solution | |-------|-------|----------| | Slow AI responses | Network or model choice | Switch to faster model, check connection | | Lost context mid-task | Long conversation or topic switch | Start new chat, re-state context | | Completions not matching | .cursorrules outdated | Update rules with current patterns | | Performance issues | Too many open files | Close unused tabs, restart Cursor |

| Error | Cause | Solution | |-------|-------|----------| | `429 Rate Limited` | Exceeding rate limits | Implement adaptive sampling | | `Quota exhausted mid-month` | Uncontrolled volume | Set project rate limits and budget alerts | | `High memory usage` | Large event buffer | Reduce `maxBreadcrumbs` and event size | | `Events dropped silently` | Buffer overflow | Implement offline queue with persistence |

| Issue | Cause | Solution | |-------|-------|----------| | Can't reproduce | Race condition | Add timing analysis | | Intermittent failure | Timing-dependent | Increase sample size | | No useful logs | Missing instrumentation | Add debug logging | | Memory growth | Resource leak | Use heap profiling |

| Security Issue | Detection | Mitigation | |----------------|-----------|------------| | Exposed API key | Git scanning | Rotate immediately | | Excessive scopes | Audit logs | Reduce permissions | | Missing rotation | Key age check | Schedule rotation |

**Common Issues and Resolutions**: 1. **Domain Unreachable** - Error: "Failed to connect to example.com" - Resolution: Check domain spelling, network connectivity, firewall rules - Fallback: Test alternate protocols (HTTP vs HTTPS) 2. **SSL/TLS Errors** - Error: "SSL certificate verification failed" - Resolution: Note in report, test with certificate validation disabled - Impact: Indicates HSTS not properly enforced 3. **Redirect Loops** - Error: "Too many redirects" - Resolution: Report redi...

| Error | Cause | Solution | |-------|-------|----------| | `Events not appearing` | DSN, sampling, or filtering issue | Use diagnostic checklist above | | `Source maps not working` | URL prefix or release mismatch | Verify upload and SDK release match | | `429 errors` | Rate limit exceeded | Implement sampling and filtering | | `Missing breadcrumbs` | Integration disabled | Enable Breadcrumbs integration |

``` [ ] Unused extensions disabled [ ] File watcher exclusions set [ ] Max open editors limited [ ] Search exclusions configured

WilmerAI ships with several example users, and those come with pre-defined endpoints that are meant to be updated with connection info from the user, so that they can be used in workflows.

**Cause:** Mutating state directly or not calling `setState()` after modifications **Solution:** Always use `setState()` with immutable updates: ```ts // ❌ this.state.count++ // ✅ this.setState({...this.state, count: this.state.count + 1}) ```

**Cause:** Tunnel not running or not connected **Solution:** ```bash cloudflared tunnel info my-tunnel # Check status ps aux | grep cloudflared # Verify running journalctl -u cloudflared -n 100 # Check logs ```

**Problem:** WebSocket connections fail silently

**Cause:** Eventual consistency means writes may not be immediately visible in other regions **Solution:** Don't read immediately after write; return confirmation without reading or use the local value you just wrote. Writes visible immediately in same location, ≤60s globally

**Problem:** Variables lost after hibernation **Cause:** DO auto-hibernates when idle; in-memory state not persisted **Solution:** Use `ctx.storage` for critical data, `ws.serializeAttachment()` for per-connection metadata

Check current worktree status, branch, and assigned task

Use when teams need facilitation, process optimization, velocity improvement, or agile ceremony management—especially for sprint planning, retrospectives, impediment removal, and scaling agile practices across multiple teams. Specifically:\\n\\n<example>\\nContext: A team is struggling with sprint planning, taking 4+ hours with unclear goals and inconsistent velocity estimates\\nuser: \"Our 8-person team wastes too much time in sprint planning. Stories are poorly sized, we never agree on the ...

Use this agent when you need to audit Active Directory security posture, evaluate privilege escalation risks, review identity delegation patterns, or assess authentication protocol hardening. Specifically:\\n\\n<example>\\nContext: Organization's security team has discovered risky privileged group configurations and needs a comprehensive review.\\nuser: \"We need to audit our Domain Admins and Enterprise Admins groups. Can you review our AD structure?\"\\nassistant: \"I'll use the ad-security...

Use this agent when you need to harden PowerShell automation, secure remoting configuration, enforce least-privilege design, or align scripts with enterprise security baselines and compliance frameworks. Specifically:\\n\\n<example>\\nContext: User needs to review a PowerShell script that connects to servers using hardcoded credentials.\\nuser: \"This script uses embedded admin passwords to connect to remote servers. Can you help secure it?\"\\nassistant: \"I'll use the powershell-security-ha...

Use this snippet to register the Figma MCP server in `~/.codex/config.toml` as a streamable HTTP server with bearer auth pulled from your env. ```toml [mcp_servers.figma] url = "https://mcp.figma.com/mcp" bearer_token_env_var = "FIGMA_OAUTH_TOKEN" http_headers = { "X-Figma-Region" = "us-east-1" } ```

``` organization-config/ .windsurf-enterprise/ privacy/ config/ privacy-settings.json # Global privacy configuration # Data transmission rules # Local processing preferences # Consent requirements

``` organization-config/ .windsurf-enterprise/ analytics/ config/ tracking-config.json # Analytics configuration # Tracked metrics # Sampling rates # Privacy filters

``` project-root/ .windsurf/ performance/ profiles/ baseline.profile.json # Baseline performance profile # Metric baselines # Execution times # Memory usage

Today we celebrate our first external contributor: **@cdnsteve**.

You are the ADK Orchestrator, a production-grade agent specializing in Agent-to-Agent (A2A) protocol management and multi-agent coordination for Vertex AI Engine deployments.

View the learnings queue without processing

Guided setup wizard for complete FairDB VPS configuration from scratch

Guided setup wizard for complete FairDB VPS configuration from scratch

Execute SOP-101 Morning Health Check Routine for all FairDB VPS instances

Emergency response procedure for SOP-201 P0 - Database Down (Critical)

UX and architecture critic that generates CRITIC.md documenting annoying design decisions, UX friction, architectural mistakes, and technical debt. Focuses on the human experience and structural issues - leaves code quality to other agents. Use for honest UX assessment, architecture review, or technical debt inventory.\n\n<example>\nContext: UX feels off\nuser: "Something about this app annoys me but I can't pinpoint it"\nassistant: "Let me run geepers_critic to identify UX friction points."\...

UX and architecture critic that generates CRITIC.md documenting annoying de...

Agent for dependency audits, security vulnerability scanning, license com...

Use this agent for dependency audits, security vulnerability scanning, license compliance, and update recommendations. Invoke for security reviews, before updates, or when checking dependency health.\n\n<example>\nContext: Security audit\nuser: "Can you audit dependencies for vulnerabilities?"\nassistant: "I'll use geepers_deps to scan all requirements files."\n</example>\n\n<example>\nContext: Update planning\nuser: "I want to update Flask to 3.0, what will break?"\nassistant: "Let me use ge...

Use this agent for gamification design - reward systems, engagement loops, progress mechanics, and fun factor enhancement. Invoke when adding game-like elements to applications, improving engagement, or designing interactive experiences.\n\n<example>\nContext: Engagement improvement\nuser: "Students aren't staying engaged with my lesson planner"\nassistant: "Let me use geepers_game to design engagement mechanics that support learning."\n</example>\n\n<example>\nContext: Interactive feature\nu...