eunomia-bpf

Prepare or publish eunomia.dev content for LinkedIn posts, articles, carousels, and professional updates. Use when asked to draft, adapt, paste, publish, QA, or record LinkedIn content for blog, tutorial, project, paper, release, consulting, research, or…

Write or revise bilingual eunomia.dev blog posts from primary sources by preparing complete drafts, running one claude-opus-4-5 paragraph-by-paragraph edit with the unchanged repository prompt template, and performing bounded mechanical verification without…

Define the finished prose style for English and Chinese eunomia.dev blog posts and Research pages. Use when writing or reviewing reader comfort, natural rhythm, technical tone, research readability, and recurring sentence-level AI tells. This skill does not…

Plan contribution-first cross-platform launches for eunomia.dev content, GitHub projects, papers, tutorials, demos, and public updates. Use when asked where/when/whether to publish, whether to do all-platform posting, whether others already posted, how to…

Prepare or publish eunomia.dev Markdown articles on DEV Community through faithful long-form syndication. Use when asked to paste, import, publish, QA, or record DEV.to posts for blog, tutorial, project, paper, release, or GitHub content. Preserves the…

Monitor approved eBPF, Linux, observability, and AI-infrastructure communities through ordinary visible browser UI, turn the strongest daily technical question into one source-grounded anonymous eBPF Q&A, and append an anonymized analysis of the day's wider…

Orchestrate the scheduled or manual eunomia.dev content operation. Use when an agent needs to read the rolling publication queue, invoke eunomia-social-radar for public performance and conversations, route explicitly authorized platform actions to publisher…

Research, write, validate, and publish source-grounded Eunomia Daily Reports for technical readers. Use when an agent needs to use platform Deep Research or direct primary-source research, identify a non-trivial systems gap, propose high-quality academic and…

Verify every citation in a paper is real, accurate, and correctly used. Downloads PDFs, reads abstracts, checks claims against source text, flags AI-hallucinated references, identifies uncited claims, and maintains structured annotations in the .bib file. Use…

Start, orchestrate, or resume an autonomous research project through hierarchical EXPERIMENT, WRITE, and REVIEW gates. Use when running a project from a rough idea to a complete paper, recovering after context loss, deciding which gate or inner loop must run…

Check a systems paper's structure at macro level (sections, subsections) and micro level (paragraph roles, sentence flow). Covers section organization, intro/abstract paragraph conventions, explicit RQ-organized evaluation, design/impl separation, and…

Check terminology, invented jargon, concept consistency, information flow, and cross-paper factual consistency in LaTeX papers. Use for undefined or drifting terms, difficult paragraph flow, architecture or workflow contradictions, claim/number drift,…

Discuss possible revisions to the scientific idea and academic architecture of a research paper through three mandatory serial read-only research discussions, returning proposals to the root agent; it does not edit the paper, execute experiments, or polish…

Iteratively refine the WRITING of a systems paper through 12 serial review-fix rounds. Covers macro structure, micro structure, section conventions, explicit RQ-organized evaluation, logic flow, abstract/intro rebuild, consistency, language (3 passes),…

Iteratively review and attack a complete research paper across systems, AI/ML, or cross-domain venues. Use for an orchestrated REVIEW gate, whole-paper accept/reject simulation, source-grounded novelty and evidence attack, external…

Create, audit, and improve figures in systems papers. Covers both design diagrams (architecture, flow, component) and result plots (bar charts, line plots, heatmaps). Checks figure-text alignment, abstraction level, claim support, and visual clarity. Use when…

Inspect, triage, and actively maintain all open GitHub issues and pull requests across public, non-archived, non-fork eunomia-bpf repositories. Use for recurring Eunomia community patrols, organization-wide issue and PR sweeps, follow-up of prior maintenance…

Use when Codex needs to run, compare, authenticate, troubleshoot, or document local command-line AI coding agents: OpenAI Codex CLI, Anthropic Claude Code, Moonshot Kimi Code, xAI Grok Build, or their agent aliases. Trigger for requests about local agent CLI…

Use GitHub CLI (`gh`) for local GitHub workflows such as installing or locating gh on Windows, checking authentication, creating or updating pull requests, inspecting PR reviews/comments/checks, monitoring CI, and falling back from GitHub connector failures…

Maintainer-quality workflow for open-source code, documentation, examples, feature requests, bug fixes, regressions, compatibility fixes, or issue-backed patches. Use when changing an OSS repository and the task needs scope control, validation, docs/changelog…

Triage open-source GitHub issues, maintainer inbox items, and the user's own outbound PRs to external repositories. Use when classifying issues, drafting maintainer replies, deciding labels/priority/milestones, requesting reproduction details, finding…

Audit or prepare an open-source release. Use when checking whether a repo is ready to tag, publish, cut a GitHub release, update changelog/release notes, bump versions, publish packages, document breaking changes, or verify release smoke tests and provenance.…

Bootstrap a lean new project, repository, research prototype, tutorial, demo, paper artifact, OSS library, CLI/tooling repo, or small web/app project. Use when creating a fresh project directory, choosing initial structure, initializing git/GitHub, writing…

Validate AgentSight changes before PR completion. Use when Codex changes AgentSight capture, parsing, top/TUI, web UI, reporting, agent-native session handling, CI scripts, or release-sensitive behavior and must run automated tests plus real CLI/TUI/UI/agent…

Generate semantic flamegraphs from local AI agent sessions using agentpprof with iterative tag rule development.

Analyze Codex, Claude, AgentSight, or other agent trajectories to find repeated failure modes and turn them into evidence-gated skill improvements. Use when the user asks why agents keep making the same mistakes, whether a skill should change, how to learn…

Analyze agent transcripts and traces to recommend collaboration improvements and generate decision-oriented HTML reports.

Analyze AgentSight system evidence to recommend operational improvements for agent runs.

Style checklist for English and Chinese bpf-developer-tutorial README files. Use while drafting or reviewing a tutorial so it reads like the established series, preserves technical detail, and presents complete kernel source clearly.

Audit bpf-developer-tutorial coverage, research current Linux BPF work and real open-source eBPF projects, maintain the repository tutorial candidate registry, and rank the next lesson by reader value, operational usefulness, eBPF leverage, reproducibility,…

Design, write, or rewrite one practical bilingual bpf-developer-tutorial lesson with pinned Claude Opus 4.5, then verify the public workflow and prose against the implementation. Use when creating README.md and README.zh.md, checking whether a tutorial tool…

Build and smoke-test bpf-developer-tutorial lessons without loading BPF programs into the host kernel. Use when creating, changing, reviewing, or debugging an eBPF tutorial and the runtime test should reuse the already-built x86 kernel under bpf-benchmark…

Review and fix academic writing in a LaTeX paper section. Checks sentence-level antipatterns, terminology consistency, and systems-paper conventions.

Review a LaTeX paper for argument-level logic, cross-section consistency, and house style. Complements /paper-review (sentence-level style) with whole-paper reasoning checks.

Run or audit KVM/QEMU/virtme-ng benchmark workflows for systems research. Use when executing VM-backed benchmarks, interpreting KVM numbers for a paper, debugging local KVM benchmark setup, checking benchmark Makefile targets, or validating result provenance…

End-to-end workflow for diagnosing and repairing eBPF verifier rejections in C, Rust/Aya, libbpf, libbpf-rs, BCC, bpftool, and CI logs from raw verbose verifier logs, BPFix diagnostics, or source/test failures. Use when Codex is asked to fix, explain, or…

Research and prepare source-grounded content briefs for agentsight.us. Use when proposing or drafting AgentSight guides, integrations, comparisons, release pages, use cases, or SEO landing pages; when checking whether a proposed page duplicates existing site…