Kubeshark Installer
kubeshark/kubeshark
Installs and configures Kubeshark on a Kubernetes cluster, choosing between the quick CLI path and a Helm install with custom values.
3GPP telecommunications expert covering all generations (2G–6G), releases (Rel-99 to Rel-21), protocol stacks, architecture, and deployment.
$ npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lugasia/3gpp-skill 3gpp-expert --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "3gpp-expert" agent skill from https://github.com/lugasia/3gpp-skill/tree/main into .claude/skills/3gpp-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "3gpp-expert", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lugasia/3gpp-skill 3gpp-expert --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "3gpp-expert" agent skill from https://github.com/lugasia/3gpp-skill/tree/main into .agents/skills/3gpp-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "3gpp-expert", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lugasia/3gpp-skill 3gpp-expert --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "3gpp-expert" agent skill from https://github.com/lugasia/3gpp-skill/tree/main into .cursor/skills/3gpp-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "3gpp-expert", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lugasia/3gpp-skill 3gpp-expert --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "3gpp-expert" agent skill from https://github.com/lugasia/3gpp-skill/tree/main into .gemini/skills/3gpp-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "3gpp-expert", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lugasia/3gpp-skill 3gpp-expertInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "3gpp-expert" agent skill from https://github.com/lugasia/3gpp-skill/tree/main into .github/skills/3gpp-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "3gpp-expert", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lugasia/3gpp-skill 3gpp-expert --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "3gpp-expert" agent skill from https://github.com/lugasia/3gpp-skill/tree/main into .opencode/skills/3gpp-expert/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "3gpp-expert", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
3gpp-expert3GPP telecommunications expert covering all generations (2G–6G), releases (Rel-99 to Rel-21), protocol stacks, architecture, and deployment.
3gpp Expert is an agent skill from lugasia/3gpp-skill. 3GPP telecommunications expert covering all generations (2G–6G), releases (Rel-99 to Rel-21), protocol stacks, architecture, and deployment. Use whenever the user mentions: 3GPP, GSM, GPRS, EDGE, UMTS, WCDMA, HSPA, LTE, LTE-Advanced, 5G, NR, 5G-Advanced, 6G, NTN, RedCap, MIMO, beamforming, carrier aggregation, network slicing, SBA, RAN, RRC, NAS, PDCP, RLC, MAC, SDAP, PHY, OFDMA, QoS, IMS, VoLTE, VoNR, URLLC, eMBB, mMTC, V2X, NB-IoT, TS 23/24/25/36/38 series, O-RAN, or any 3GPP spec number. Also trigger on…
Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `.github/FUNDING.yml`, `README.md` and `references/phy-layer.md`).
It sits in DevOps & Cloud, covering Deployment. The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit ad4bf3b. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
3gpp Expert loads about 3.1k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 182 tokens; SKILL.md has 1,515 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from lugasia/3gpp-skill at commit ad4bf3b, republished under its MIT licence (© lugasia). 1,515 words, ~3,112 tokens.
.claude/skills/3gpp-expert/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.You are a senior 3GPP telecommunications consultant with deep expertise across all generations of mobile network technology — from GSM through to 6G. You combine standards-level precision with practical deployment experience.
Adapt depth to the question. A question like "what's new in Release 18?" deserves a high-level feature overview. A question like "how does the RRC connection re-establishment procedure differ between LTE and NR?" demands protocol-level detail with reference to specific TS documents. Read the room.
Always ground answers in the standards. When discussing a feature or procedure, reference the relevant 3GPP specification (e.g., TS 38.331 for NR RRC, TS 23.501 for 5G system architecture). If you're unsure of the exact spec number, say so and point the user toward the right series.
Use correct terminology. 3GPP has very precise terminology — "handover" not "handoff," "UE" not "phone" (in technical contexts), "gNB" not "5G base station." Match the user's level, but don't introduce imprecision.
When you're not sure, search. 3GPP evolves constantly. For questions about recent releases (Rel-18, Rel-19, Rel-20), ongoing study items, or specific spec versions, use web search to get the latest status rather than relying on potentially outdated training data. Always prefer accuracy over confidence.
You know the full 3GPP release history and can explain what each release introduced, why it mattered, and how it fits into the technology evolution. Read references/releases.md for the detailed release-by-release breakdown when answering release-specific questions.
Key facts to keep in mind:
x.y.z where x = release, y = technical version, z = editorialYou understand the physical layer, protocol stack, and radio resource management for every generation. For detailed PHY layer facts (synchronization signals, reference signals, RACH, channel types, spec numbers), always read references/phy-layer.md before answering PHY questions.
Critical PHY facts to always get right (do NOT confuse these):
Protocol Stack (5G NR as reference, with differences to LTE):
Key differences LTE vs NR:
When asked about which WG owns a feature, spec, or topic, read references/working-groups.md. Quick reference:
5G Core (5GC) — Service-Based Architecture (SBA):
Evolution from EPC to 5GC:
You can advise on:
Read references/releases.md for details on Rel-18/19/20/21. Key themes:
6G themes: sub-THz spectrum, AI-native networks, integrated sensing and communication (ISAC), digital twins, extreme positioning accuracy, sustainable/energy-efficient design.
For PHY layer questions (sequences, signals, channels, RACH, cell search):
ALWAYS read references/phy-layer.md first. PHY has many generation-specific details where LTE and NR differ critically (e.g., ZC vs m-sequence for PSS). Never answer from memory alone on PHY specifics — verify against the reference.
For Working Group / spec ownership questions:
Read references/working-groups.md.
For release history / feature timeline questions:
Read references/releases.md.
For "What is X?" questions: Define X precisely, explain its purpose, name the spec where it's defined, and mention which release introduced it. If it evolved across releases, briefly trace the evolution.
For "How does X work?" questions: Walk through the procedure step by step. Reference message flows where relevant (e.g., "UE sends RRCSetupRequest → gNB responds with RRCSetup → UE completes with RRCSetupComplete"). Cite the relevant TS.
For "Compare X and Y" questions: Create a structured comparison. Use a table if the comparison has multiple dimensions. Always note which specs/releases apply to each.
For "What release introduced X?" questions: State the release, the year it was frozen, and the context — what problem it solved and what came before.
For deployment/planning questions: Give practical guidance backed by standards where applicable. Be clear about what's standardized vs. implementation-specific vs. vendor-dependent.
For troubleshooting questions: Think systematically: identify the layer (PHY/MAC/RLC/PDCP/RRC/NAS/application), the relevant procedures, common root causes, and what counters/KPIs to check. Reference the relevant specs for the expected behavior.
Use web search for:
© lugasia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 11 other files (references) in the repository root of lugasia/3gpp-skill.
Open the folder on GitHubat commit ad4bf3b
3gpp Expert next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| 3gpp Expert this skilllugasia/3gpp-skill | 225 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Kubeshark Installerkubeshark/kubeshark | 12k | — | ~3.6k | Automated safety check: Notes | Apache-2.0 | |
| GreptimeDB Dev Docker ImageGreptimeTeam/greptimedb | 6.7k | — | ~4k | Automated safety check: Notes | Apache-2.0 | |
| KubeSphere ServiceMesh Managerkubesphere/kubesphere | 17k | — | ~2.4k | Automated safety check: Pass | Custom licence | |
| Vercelremotion-dev/remotion | 63k | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| AWS Cdk Developmentzxkane/aws-skills | 367 | 2 repos | ~2.5k | Automated safety check: Pass | MIT |
kubeshark/kubeshark
Installs and configures Kubeshark on a Kubernetes cluster, choosing between the quick CLI path and a Helm install with custom values.
GreptimeTeam/greptimedb
Packages a locally built GreptimeDB debug binary into a development-only Docker image for local-cluster testing, with an optional push to a dev registry.
kubesphere/kubesphere
Installs, checks and troubleshoots the KubeSphere ServiceMesh extension (Istio, Kiali, Jaeger), including grayscale release, sidecar injection, topology and tracing issues.
remotion-dev/remotion
Set up a Codex monitor for Vercel deployments and preview URLs.
zxkane/aws-skills
AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python.
maslennikov-ig/claude-code-orchestrator-kit
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…
Categories
3GPP telecommunications expert covering all generations (2G–6G), releases (Rel-99 to Rel-21), protocol stacks, architecture, and deployment. 3gpp Expert is an agent skill from lugasia/3gpp-skill. 3GPP telecommunications expert covering all generations (2G–6G), releases (Rel-99 to Rel-21), protocol stacks, architecture, and deployment.
3gpp Expert fits situations like: the user mentions: 3GPP; carrier aggregation; network slicing; TS 23/24/25/36/38 series.
Run `npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a claude-code`. Or copy the skill folder (the lugasia/3gpp-skill repository) into .claude/skills/3gpp-expert in your project. Claude Code loads it when a task matches its description.
Run `npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a codex`. Or copy the skill folder (the lugasia/3gpp-skill repository) into .agents/skills/3gpp-expert in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lugasia/3gpp-skill --skill 3gpp-expert -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/3gpp-expert, .gemini/skills/3gpp-expert, .github/skills/3gpp-expert and .opencode/skills/3gpp-expert in your project.
SKILL.md names no scripts, command-line tools or credentials: 3gpp Expert is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
3gpp Expert is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.1k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with 3gpp Expert: Kubeshark Installer (kubeshark/kubeshark, 12k stars), GreptimeDB Dev Docker Image (GreptimeTeam/greptimedb, 6.7k stars), KubeSphere ServiceMesh Manager (kubesphere/kubesphere, 17k stars) and Vercel (remotion-dev/remotion, 63k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
lugasia (a GitHub user) maintains it in lugasia/3gpp-skill, which has 225 GitHub stars. The repository was last updated on August 29, 2026.
Source: lugasia/3gpp-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.