Afegits recentment
Els últims skills afegits al catàleg. Descobreix les novetats!
notte
Bitterbot-AI
Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI. Turns any browser flow into a deterministic Bitterbot-callable endpoint, ideal for crystallized skills + dream-engine cron schedules.
notion
Bitterbot-AI
Notion API for creating and managing pages, databases, and blocks.
nano-pdf
Bitterbot-AI
Edit PDFs with natural-language instructions using the nano-pdf CLI.
nano-banana-pro
Bitterbot-AI
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).
moltbook
Bitterbot-AI
Participate in Moltbook — the social network for AI agents. Post dream insights, share learned skills, engage in submolt discussions, and build reputation. Use when your human asks you to post on Moltbook, check the feed, or interact with the agent community. Also used during heartbeats for periodic social engagement.
model-usage
Bitterbot-AI
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
memory-architecture
Bitterbot-AI
Use when the user asks how your memory, dreams, hormones or knowledge crystals work, or when you need to interpret memory_status output. Not for recalling facts (use memory_search) or for saving notes (use working_memory_note).
mcporter
Bitterbot-AI
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
imsg
Bitterbot-AI
iMessage/SMS CLI for listing chats, history, watch, and sending.
himalaya
Bitterbot-AI
"CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language)."
video-engine
krishanraja
"Use this skill whenever the current user message, after trimming leading and trailing whitespace, equals 'Video engine' case-insensitively, so the skill can validate the launch guard. Discovery is not activation: after loading, activate only if that exact message is also the first user-authored message in a new chat. Terminal punctuation, additional words or lines, quoted mentions, later-turn uses, and $video-engine must not activate the engine. On a failed guard, stop before accessing the authority repository. Never activate for ordinary video requests."
verification-loop
krishanraja
"Correction ownership first: after fixing a failed test, invoke verification-loop to rerun the original and adjacent checks; generic regression closure belongs here, not to ux-testing-agent unless the request names UX or a rendered user flow. Exclusion gate: NEVER invoke for an unexecuted future plan when no recommendation, artifact, action, or observable outcome exists, even if asked to call it verified; strategy-brief owns that phase. Otherwise this is Krish's completion gate: invoke to verify, QA, prove, inspect, or certify an existing artifact, change, dataset, workflow, deployment, cloud state, browser flow, research conclusion, or recommendation, including attempts to skip contradictory evidence. Use after every correction and before claiming completion, readiness, parity, or delivery. Select observable independent checks, correct only within authority, rerun failed checks, separate facts from inference, never expose matched secrets, and never treat self-critique as independent proof."
ux-testing-agent
krishanraja
"Evidence-first UX diagnosis and acceptance testing for a rendered app or its repository-plus-runtime. Use when Krish asks to test, QA, audit, inspect, review, smoke-test, reproduce, accessibility-test, responsive-test, or validate a release, flow, fix, deployed app, or GitHub repository from a real user's perspective. Do not invoke for the generic instruction to rerun a failed automated test and adjacent checks after a code fix; verification-loop owns that regression closure unless UX or a rendered user flow is named. Start read-only, resolve current repository and deployment identity live, test high-value tasks and failure states, and return reproducible evidence. Do not own product strategy, visual redesign, copy voice, code implementation, deployment, security review, real payments, external sends, credentials, or production data. A repository without a matching runnable artifact supports source observations only, not a usability verdict. Last reviewed 2026-10-06."
ux-foundations
krishanraja
"Current-source lookup for generic UX, accessibility, interaction-pattern, usability-heuristic, and experiment-design fundamentals. Use when asked what WCAG or platform guidance actually requires, which heuristic applies, whether a UI rule is normative or advisory, how web/iOS/Android guidance differs, or what a sound pre-launch A/B test contract contains. Verify current primary sources, preserve units and exceptions, and label the authority of every rule. Do not use to design Krish's artifacts (krish-design), exercise a live product (ux-testing-agent), implement or deploy a fix (krish-build), certify legal compliance, or operate/analyse an experiment. Last reviewed 2026-08-05."
tools-access
krishanraja
"Secure runtime access, identity, scope, and target-verification contract for authenticated services used across Krish's operating system. Use when a task needs GitHub, Vercel, Supabase, n8n, Apify, Stripe, MCPMarket, or another authenticated service; when choosing OAuth, connector, CLI, or managed-secret access; when login, scope, tenant, session, connector, or credential state fails; or when a credential may be exposed, stale, or over-privileged. This skill contains no credential values and never turns authentication into mutation authority. It proves access and hands the verified context to the narrow task owner; it does not become the deployer, researcher, tester, publisher, or operator merely because it controls authentication. Last reviewed 2026-09-12."
golden-chain-sweep
OmniNode-ai
Validate end-to-end Kafka-to-DB-projection data flow for all golden chains
Generate ONEX Node
OmniNode-ai
"SCAFFOLD-ONLY. Contract inference (AST, no LLM) plus template scaffolding for ONEX nodes. The LLM business-logic fill stage does NOT exist; generated nodes need their handler bodies written by hand."
Friction Triage
OmniNode-ai
Read friction registry, escalate surfaces crossing threshold to Linear tickets
Feature Dashboard
OmniNode-ai
Audit skill connectivity across 8 layers and surface gaps as actionable, machine-readable output. Supports audit (read-only) and ticketize (create Linear tickets for gaps) modes.
Executing Plans
OmniNode-ai
Use when partner provides a complete implementation plan to execute — reviews the plan critically, verifies live PR state against plan assumptions, creates Linear tickets via plan-to-tickets, then routes to epic-team (≥3 tickets) or ticket-pipeline (1-2 tickets)
Epic Team Orchestration
OmniNode-ai
Orchestrate a Claude Code agent team to autonomously work a Linear epic across multiple repos
env_sync_alert
OmniNode-ai
Alert on env-sync.log and critical log failures — emits friction YAML and Linear ticket
Env Parity Checker
OmniNode-ai
Local Docker vs onex-dev k8s environment parity checker -- dispatches to node_env_parity_compute for execution
/onex:duplication_sweep — one command, one typed result
OmniNode-ai
'Detect duplicate definitions across repos: Drizzle table definitions, Kafka topic registrations,