Claude Leak Confirms It: LLM Systems Are Architecture, Not Prompts (Orca)
Agent Skills Runtime is a new system that enables AI agents to execute structured workflows through deterministic, contract-driven processes rather than relying on prompts. It supports multi-step workflows as declarative DAGs with built-in safety, cognitive state tracking, and full observability, operating offline without API keys. The framework is based on ORCA, an emerging standard for structured agent execution that emphasizes explicit reasoning and reusable capabilities.
- ▪Agent Skills Runtime allows AI agents to execute composable skills through deterministic workflows instead of prompt-based reasoning.
- ▪It includes 159 pre-built capabilities with Python baselines and supports integration with multiple protocols including OpenAPI, MCP, and OpenRPC.
- ▪The system operates offline, requires no API key, and provides safety features such as trust levels, confirmation prompts, and side-effect tracking.
- ▪Workflows are defined in declarative YAML, enabling reproducibility, observability, and auditability via OpenTelemetry and Prometheus.
- ▪ORCA, the underlying architecture, externalizes agent cognition into structured state, capabilities as contracts, and execution graphs for safer, more transparent AI agent behavior.
Hacker News (Front Page) files mainly under programming. We currently carry 673 of its stories. Top-voted stories on Hacker News.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/gfernandf/agent-skills |
| Publication time | Tue, 28 Apr 2026 16:52:52 +0000 |
| Retrieval time | 2026-04-28T17:01:13.967Z |
| Last seen | 2026-04-28T17:01:13.967Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 7wkTLVCb4eyd |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Agent Skills Runtime Agents should execute whenever possible. A deterministic, binding-driven execution engine for composable AI agent skills. Agent Skills Runtime lets you define agent capabilities as abstract contracts, wire them to any backend (Python, OpenAPI, MCP, OpenRPC), and execute multi-step workflows as declarative DAGs — with built-in safety gates, cognitive state tracking, and full observability. No API keys required. 159 capabilities ship with deterministic Python baselines. Install, run your first skill in under 3 minutes. ⚡ 30-second start Works on macOS, Linux, and Windows. No API key required. # 1 — clone and install git clone https://github.com/gfernandf/agent-skills.git cd agent-skills pip install -e .
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.