Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths.
Answer "I installed Cortex — now what?" for the repo you are standing in. Shows where this repo is in the sequence, marks each step done from a file on disk, and names the one…
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections.
Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria.
ML reconnaissance — inventory all models, pipelines, data sources, and monitoring. Use when asked "what ML do we have", "model inventory", or "ML assessment".
Regenerate obsidian/Connections.md from current hermit state. Runs nightly via routine and after each turn that mutates sessions/proposals. Safe to invoke manually.
Register / name THIS Claude session so it can be messaged by other Claude sessions and agents. Use when the user asks to join cortex, enable messaging, "make this session…
Generate a time-bounded markdown report from the cortex MCP server covering fleet activity, errors, stale hosts, correlations, and recommended actions.
Review a change against the repo's OWN documented context — the AGENTS.md, CONTEXT.md and ADRs Cortex wrote — on two axes.
Auto-routing skill loaded by the prompt filter hook. Routes Snowflake-related operations to Cortex Code CLI. Not for direct invocation — use $cortex-run instead.
Write the context layer into a repo — root AGENTS.md, agent shims, CONTEXT.md glossary, docs/adr/ and .cortex/.
Install Snowflake CLI and Cortex Code CLI. Use when cortex is not installed, when the user asks to set up Cortex Code, or when routing fails because the CLI is missing.
Propose and write skills that fit THIS codebase — a webhook skill because the repo takes Stripe, a migration skill because it owns a Prisma schema, a first-test skill because it…
Enrich existing hermit content with frontmatter and tags. Scans sessions, proposals, and artifact paths for missing fields, clusters similar files for batch confirmation, then…
Troubleshoot cortex connection failures, missing logs, unhealthy containers, restart loops, or vague "logs aren't working" reports.
Launch the interactive unified neural graph visualization. Use when the user says 'show visualization', 'show me the graph', 'visualize memories', 'show memory map', 'open neural…
Show who is online in the cortex mesh — which Claude sessions/agents are registered and reachable right now.
Cortex XSOAR integration. Manage data, records, and automate workflows. Use when the user wants to interact with Cortex XSOAR data.
Check whether an x402 payment endpoint is reliably delivering value before spending USDC on it. Returns paid delivery rate, active incidents, latency, and a clear…
Use when operating inside the Corvus Star estate so Codex follows the CStar authority order, Hall discovery path, and launcher contract.
Traefik üzerinden COS web uçlarına erişim; show-proxied-endpoints, path kuralları ve MetalLB önkoşullarını tanımlar.
COS bileşenlerini ayrı bir Juju modele dağıtıp cross-model relation (CMR) ile uygulama modelindeki servisleri izlemek; bu tasarım kararını ne zaman tercih edeceğini bilmek…
Upload a local file to AceData Cloud CDN and get back a public URL. Use whenever you produce a local artifact (image, audio, video, doc) that another API needs as a URL, or that…
Gebruik wanneer de gebruiker (of jij als agent namens de gebruiker) iets nodig heeft dat alleen aan Ello's kant kan, zoals cijfers uit de productie-database, een blik in logs of…
Use when extending CoSec policy matching with custom ActionMatcher or ConditionMatcher implementations, condition types, matcher factories, ServiceLoader SPI registration, or…
Use when diagnosing CoSec authentication or authorization failures such as unexpected 401/403 responses, denied requests that should be allowed, policies not loading, JWT token…
Design and configure CosId sharding algorithms for database sharding and ShardingSphere. Use when the user mentions table or database sharding, ShardingSphere COSID_MOD or…
Validates container image and artifact signatures using Sigstore Cosign with keyless verification via Fulcio and Rekor transparency logs.
Use when when you have preprocessed mass spectra (peak-filtered, metadata-cleaned) in supported formats (mzML, mzXML, msp, MGF, JSON) and need to compare all or many pairs of…
Use when after generating normalized dense embeddings for both query and reference MS/MS spectra using a pre-trained model like SpecEmbedding.
Use when you are performing dimensionality reduction on a sparse single-cell count matrix (in CSR format) and need to compute pairwise cell similarities before spectral…
Use when when you have pre-computed spectral embeddings (vectors) for both query spectra and a reference library, and you need to measure retrieval performance by ranking…
สร้างรายงานดวงชะตาครบ 10 ศาสตร์ ภาษาไทย พร้อม PDF Premium 25 หน้า สำหรับบุคคลใดก็ได้ โดยรับข้อมูล ชื่อ วันเกิด เวลาเกิด สถานที่เกิด และเพศ แล้วออก PDF…
Set up cosmiconfig for hierarchical configuration loading from multiple sources and formats.
Cosmo Electronics MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Cosmo optocouplers or CosmoHandler.
Innovation intelligence, emerging trends, market analysis, and visionary thinking for staying ahead of change
Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU e — from…
Step-by-step guide for capturing key application requirements for NoSQL use-case and produce Azure Cosmos DB Data NoSQL Model design using best practices and common patte — from…
Investigate the codebase or a spec question without writing implementation code.
Explain how spec sync works (it runs inside archive) and preview what would merge.
Show how many tokens engram has saved in this session, this week, and across all indexed projects. Use when the user asks about token usage, savings, costs, or wants a digest…
Track real-time API cost accrual during LLM execution. Activate on 'cost tracking', 'token usage', 'API costs', 'budget monitoring', 'usage metrics'.
Track real-time API cost accrual during LLM execution. Activate on 'cost tracking', 'token usage', 'API costs', 'budget monitoring', 'usage metrics'.
Review the configured cost alert rules and the alerts currently fired on the Agent Monitor dashboard, then explain exactly what tripped and why.
Analyzes infrastructure costs at 1K-100K user scales by reading the actual codebase, auto-detecting cloud providers, modeling per-action costs, and projecting total monthly spend…
Analyse infrastructure and system costs, identify optimisation opportunities, and generate savings recommendations using parallel agents — from tools-only/X-Skills
Cost approach valuation for specialized infrastructure (transmission towers, telecom sites, substations) using replacement cost new less depreciation (physical, functional,…
Break down Claude Code costs using the Agent Monitor pricing engine. Shows per-model costs (input, output, cache_read, cache_write at $/Mtok rates), per-session costs, daily…
Set per-request, per-session, daily, and monthly spend limits, configure rate limiting and circuit breakers, and isolate costs per user or tenant.
Cost estimation scripts and tools for calculating GPU hours, training costs, and inference pricing across Modal, Lambda Labs, and RunPod platforms.
A model-selection cost policy for Claude Code — route bulk, mechanical work to cheaper/faster models and reserve frontier models for judgment and review.
Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost
Use when a task is large, token-heavy, repetitive, or likely to exceed usage limits.
Cloud cost estimation and optimization. Use when estimating cloud infrastructure costs, comparing cloud providers, cost optimization strategies, or TCO analysis.
Calculate construction costs using resource-based method. Estimate project costs from work items, physical resource norms, and current prices.
Explain all costs in human terms. Always compare with real-world equivalents. Recommend cheapest that works.
Consumer-side wiring for ADR-097 Phase 3 federation_spend events — per-peer rolling windows + suspension-threshold check
Real-time cost tracking and budget management for Claude Code sessions. Shows current spend, burn rate, budget status, per-tool and per-model breakdown.
See the main Budget Guardrails skill for comprehensive coverage of cost controls and governance.
Automatically triggered when a developer asks about their Claude Code token costs, spending this month or last month, which repository is costing the most, Claude API usage…