Research & Data

Engineering-first OpenAI Codex guide: 14 modules, 9 installable skills, reproducible benchmarks, testing, review, orchestration, and a Living Wiki.

The discovery layer for the agentic web: connecting developers and AI agents to build together

Codex skill for guided DFRobot WIAnode configuration, validation, and SKU reporting

A Codex skill for auditing creator contracts, routing metadata, source boundaries, and declared validation evidence.

Agent skill to audit and clean a self-hosted Plex library. HTML report, duplicates vs soft copies, action stacks for Cursor/Claude.

Claude Skill: analisis & pressure-test strategi kompetitif pakai kerangka Porter (Five Forces + Five Tests) ala Magretta

Save anything. Find the right thing when work starts. AI agent skills that turn saved material into a searchable working library.

Project-driven academic research assistant Codex skill

Public repository for immune repertoire analysis Agent Skills.

Read-only Codex skill for local Windows WeChat 4.x messages, search, export, and media.

Evidence-backed Codex skill for rental research, listing verification, viewing, and contract due diligence.

A Go benchmark runner for evaluating coding agents, skills, and LLMs through repeatable trials and OpenTelemetry-native observability.

Discipline-neutral Codex skill for high-standard academic research paper workflows

Codex skill for resolving and downloading public GEO, NCBI, and ENA data with IBM Aspera ascp

One persona, one frozen memory, N models: how much of an agent's character survives a model swap? Harness + blind multi-lens judge panel + cross-vendor rank control + contamination probe. Results included: 7 models, spread 4.80 -> 2.20.

Voice -> text -> your personal knowledge base. A primitive, not a platform: 4 small Python scripts turn voice notes into linked, tagged, searchable markdown.

Claude Desktop on Windows will not reopen after an update and you reboot. A dead instance is holding the single-instance lock. This kills only the stale processes, relaunches, and snapshots the failing state so the bug can be reported with artifacts. One PowerShell file, MIT.

CharmOS / C(H+A)RM — open-source framework to manage humans AND AI agents as first-class relationships, on a personal second brain, driven by the RDR loop (Recall to Deep Research). Manifest-first, Apache-2.0.

Pre-registered A/B/C benchmark: Superpowers vs OpenSpec vs baseline, on real brownfield ops code. Methodology frozen before runs; results published either way.

Search local Agent Skill collections without loading them all.

Makes your AI agent answer like a briefing to a busy, skeptical boss. Conclusion first, no padding, no agreement it doesn't mean.

Open up your internal work without leaking it: substitute personal data with plausible fakes of the same shape (not <REDACTED>), then gate the WHOLE tree before the push. Stdlib-only, with the eleven traps it cost us.

Geography literature review research skill: distills HOW top journals structure reviews (Book-to-Skill), then runs an evidence-first multi-agent pipeline — Google Scholar API-only discovery, human-gated full-text acquisition, Zotero-verified citations, draft figures, independent audit.

Agent Skills: agent-thread-visualizer — execution maps / session timelines for Cursor, Codex, Claude Code, Workbuddy, kimi-code