Ship
juliepy/AI-Engineer-from-scrach
Commit and push the current work properly — lint, run the release gate, write a detailed commit message, push to GitHub.
A skill your agent uses for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup…
Install Levyra Context Efficiency
$ npx skills add LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LUC4N3X/Levyra-deepsound levyra-context-efficiency --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LUC4N3X/Levyra-deepsound.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/levyra-context-efficiency .claude/skills/levyra-context-efficiency && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "levyra-context-efficiency" agent skill from https://github.com/LUC4N3X/Levyra-deepsound/tree/main/.agents/skills/levyra-context-efficiency into .claude/skills/levyra-context-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "levyra-context-efficiency", 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.
$skill-installer install https://github.com/LUC4N3X/Levyra-deepsound/tree/main/.agents/skills/levyra-context-efficiencyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LUC4N3X/Levyra-deepsound levyra-context-efficiency --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LUC4N3X/Levyra-deepsound.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/levyra-context-efficiency .agents/skills/levyra-context-efficiency && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "levyra-context-efficiency" agent skill from https://github.com/LUC4N3X/Levyra-deepsound/tree/main/.agents/skills/levyra-context-efficiency into .agents/skills/levyra-context-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "levyra-context-efficiency", 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 LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LUC4N3X/Levyra-deepsound levyra-context-efficiency --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LUC4N3X/Levyra-deepsound.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/levyra-context-efficiency .cursor/skills/levyra-context-efficiency && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "levyra-context-efficiency" agent skill from https://github.com/LUC4N3X/Levyra-deepsound/tree/main/.agents/skills/levyra-context-efficiency into .cursor/skills/levyra-context-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "levyra-context-efficiency", 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.
$ gemini skills install https://github.com/LUC4N3X/Levyra-deepsound.git --path .agents/skills/levyra-context-efficiency--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LUC4N3X/Levyra-deepsound levyra-context-efficiency --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LUC4N3X/Levyra-deepsound.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/levyra-context-efficiency .gemini/skills/levyra-context-efficiency && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "levyra-context-efficiency" agent skill from https://github.com/LUC4N3X/Levyra-deepsound/tree/main/.agents/skills/levyra-context-efficiency into .gemini/skills/levyra-context-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "levyra-context-efficiency", 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 LUC4N3X/Levyra-deepsound levyra-context-efficiencyInstalls 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 LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LUC4N3X/Levyra-deepsound.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/levyra-context-efficiency .github/skills/levyra-context-efficiency && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "levyra-context-efficiency" agent skill from https://github.com/LUC4N3X/Levyra-deepsound/tree/main/.agents/skills/levyra-context-efficiency into .github/skills/levyra-context-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "levyra-context-efficiency", 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 LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LUC4N3X/Levyra-deepsound levyra-context-efficiency --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LUC4N3X/Levyra-deepsound.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/levyra-context-efficiency .opencode/skills/levyra-context-efficiency && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "levyra-context-efficiency" agent skill from https://github.com/LUC4N3X/Levyra-deepsound/tree/main/.agents/skills/levyra-context-efficiency into .opencode/skills/levyra-context-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "levyra-context-efficiency", 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.
Facts
- Skill name
levyra-context-efficiency- GitHub stars
- 533
- Token cost
- ~1.3k tokens
- SKILL.md length
- 555 words
- Files
- 1
- Skills in repo
- 22
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
A skill your agent uses for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup…
- Works in 6 steps: identify the architecture owner and the… → search symbol/path/call site first; → read the smallest useful source/test… → …
- Genuinely high-volume Levyra work such as builds
- SKILL.md covers Purpose, Automatic routing, RTK and Keep decisive evidence raw, plus 4 more sections
- Calls adb
What it does
Levyra Context Efficiency is an agent skill from LUC4N3X/Levyra-deepsound. Use for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup, cross-domain exploration, or useful cross-session retrieval. Reduce token waste without reducing engineering rigor.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Session handoff, LLM cost and token optimization and Linting and formatting. It works with Git and GitHub. The repository describes itself as: Open-source music player for Android and Windows with no accounts or tracking. Built for quick discovery, synced lyrics, radio, and rich artwork ♫. The licence is GPL-3.0.
When your agent uses it
- Genuinely high-volume Levyra work such as builds
- Dependency output
- CodeRabbit inspection
- Cross-domain exploration
Example prompts
- “/levyra-context-efficiency”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- identify the architecture owner and the exact question the next read answers;
- search symbol/path/call site first;
- read the smallest useful source/test range;
- expand only when a concrete unanswered question remains;
- do not reread unchanged evidence already in context;
- load only the domain/companion skills that materially affect correctness.
What it can do on your machine
Read from SKILL.md and the folder at commit 35cd2be. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
adb
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Levyra Context Efficiency loads about 1.3k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 555 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.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:93
`.env`, or `local.properties` through project memory.
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.
SKILL.md
The full file from LUC4N3X/Levyra-deepsound at commit 35cd2be, republished under its GPL-3.0 licence (© LUC4N3X). 555 words, ~1,254 tokens.
Download SKILL.mdSave it as
.claude/skills/levyra-context-efficiency/SKILL.md (or your agent's skills folder).- name
- levyra-context-efficiency
- description
- Use for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup, cross-domain exploration, or useful cross-session retrieval. Reduce token waste without reducing engineering rigor.
Levyra context-efficiency workflow
Purpose
Spend model context on code and decisive evidence. This skill reduces repeated instructions, broad reads, noisy command output, and stale history. It never replaces domain skills, source inspection, testing, review, or exact diagnostics.
Token savings must come from context and output, never from shallower reasoning. If omitted evidence can change correctness, read or rerun it.
Automatic routing
Route this skill only when the task is likely to create substantial repository or command-output volume. Tiny edits, ordinary explanations, and already-local code changes should not load it just because the prompt says "implement", "modify", "analyze", or "inspect".
Before broad reading:
- identify the architecture owner and the exact question the next read answers;
- search symbol/path/call site first;
- read the smallest useful source/test range;
- expand only when a concrete unanswered question remains;
- do not reread unchanged evidence already in context;
- load only the domain/companion skills that materially affect correctness.
RTK
For shell-capable noisy work, prefer the repository RTK layer after checking it.
Use scripts/ensure-rtk.ps1 -Quiet on Windows or ./scripts/ensure-rtk.sh --quiet
elsewhere. Manual repair remains available through
scripts/setup-ai.ps1 -InstallRtk or scripts/setup-ai.sh --install-rtk.
If RTK is unavailable, continue raw rather than weakening validation.
Useful compact routes include:
rtk gradlew <tasks>
rtk git diff
rtk git status
rtk gh pr view <number>
rtk test <command>
rtk err <command>
rtk grep <pattern> <path>
rtk log <file>
rtk adb logcat -d -t 400
rtk summary adb shell dumpsys <service>Compact output is not proof of success. Check the command exit status and the authoritative success/failure marker. If compression hides the deciding cause, rerun the exact command raw.
Keep decisive evidence raw
Do not compress away evidence needed for:
- compiler/test/lint failures whose exact diagnostic matters;
- security, redirects, MIME, permissions, secrets, signing, checksums, or trust boundaries;
- Perfetto/thread/frame timing, SQL/query failures, concurrency, or memory root cause;
- R8/Proguard missing-class, mapping, metadata, or release-only failures;
- exact protocol, quoting, encoding, stdout/stderr, or regression reproduction.
For ADB, bound noisy textual output first. Keep tiny control queries raw. Never
wrap binary/payload commands such as adb exec-out screencap -p in a text
compression path.
Show full SKILL.md (248 more words)Show less
Cross-session context
Use claude-mem only when earlier-session context materially affects the task and
the runtime exposes it. Retrieve progressively: search -> timeline when
chronology matters -> get_observations for only relevant IDs -> verify against
the current repository. Current code, tests, CI, runtime evidence, and owner
decisions always outrank memory.
Fail open: if memory tooling is unavailable, unhealthy, or unsupported, continue ordinary engineering without it. Do not enable cloud sync or semantic injection implicitly. For ChatGPT, Repository configuration alone cannot make ChatGPT reach a local claude-mem worker.
If a shell-capable runtime genuinely needs the optional integration and it is
missing, one bounded setup attempt may use scripts/setup-ai.ps1 or
scripts/setup-ai.sh. Manual forcing remains scripts/setup-ai.ps1 -ClaudeMem
or ./scripts/setup-ai.sh --claude-mem. Failure must not block ordinary work.
Never store or retrieve secrets, tokens, cookies, keystores, private URLs,
.env, or local.properties through project memory.
Long-task checkpoints
Carry forward only the verified goal, root cause/decision, affected files or symbols, preserved behavior, current edit state, validation results, real blockers, and one next action. Drop superseded logs and disproved hypotheses. A compact handoff never replaces source-of-truth evidence.
Safety
- Do not trade correctness, review depth, or testing for a smaller context window.
- Do not enable
danger-full-access, approval bypasses, or unrestricted sandboxing. - Do not install unrelated plugins or broad system upgrades.
- Do not let RTK or memory hide security/signing/runtime evidence.
- Never infer permission to commit, push, open/merge a PR, tag, release, or deploy.
Validation
After changing this workflow or its routing, run:
python3 scripts/validate_claude_mem.py
python3 scripts/validate_agent_config.py
python3 scripts/validate_ai_efficiency.py
python3 scripts/evaluate_skill_routing.pyOn Windows use py for the same scripts when appropriate.
© LUC4N3X, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/levyra-context-efficiency of LUC4N3X/Levyra-deepsound.
Open the folder on GitHubat commit 35cd2be
Compare with similar skills
Levyra Context Efficiency 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 |
|---|---|---|---|---|---|---|
| Levyra Context Efficiency this skillLUC4N3X/Levyra-deepsound | 533 | — | ~1.3k | Automated safety check: Notes | GPL-3.0 | |
| Shipjuliepy/AI-Engineer-from-scrach | 436 | — | ~307 | Automated safety check: Notes | None | |
| Invoking GitHuboaustegard/claude-skills | 150 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Development Workflowkid-sid/claude-spellbook | 190 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Session Handoff Writercodewhale-hq/Codewhale | 41k | — | ~1.2k | Automated safety check: Pass | MIT | |
| GitHubswarmclawai/swarmclaw | 688 | — | ~820 | Automated safety check: Pass | MIT |
Similar skills
Invoking GitHub
oaustegard/claude-skills
Enables GitHub repository operations (read/write/commit/PR) for Claude.ai chat environments.
Development Workflow
kid-sid/claude-spellbook
A skill your agent uses when choosing a branching strategy, writing a commit message, opening or reviewing a pull request, setting up commit linting, or tagging a versioned release.
Session Handoff Writer
codewhale-hq/Codewhale
Writes a compact handoff note from real git and CI state so the next session or a teammate can pick up the work without rebuilding the context.
GitHub
swarmclawai/swarmclaw
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.
LobeHub Alint Rule Set Maintenance
lobehub/lobehub
Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.
More from LUC4N3X/Levyra-deepsound
All 22 skills in this repoLevyra Android Intent Security
LUC4N3X/Levyra-deepsound
Automatically use for Levyra Android Intent, deep-link, PendingIntent, exported component, receiver, service, provider, URI-grant, FileProvider, caller-verification, or onNewIntent security work.
Levyra R8 Proguard
LUC4N3X/Levyra-deepsound
Automatically use for Levyra R8, Proguard, minification, resource shrinking, keep rules, consumer rules, release-only crashes, reflection/serialization/JNI shrinking issues, APK size, mapping files…
Levyra Android Performance
LUC4N3X/Levyra-deepsound
Automatically use for Android runtime performance investigations involving Perfetto/System Trace, jank, latency, startup, CPU scheduling, blocking, memory, I/O, IPC, graphics, power, or measured…
Levyra CI Workflows
LUC4N3X/Levyra-deepsound
Automatically use for Levyra GitHub Actions, CI, F-Droid, Gradle/AGP/Kotlin/KSP compatibility, build performance, configuration/build cache, artifacts, release automation, workflow security, or…
Levyra Design Taste
LUC4N3X/Levyra-deepsound
Automatically use together with the matching Levyra UI skill for any visual redesign, UI polish, visual hierarchy, spacing, typography, color, shape, motion, screenshot/reference recreation, or…
Levyra PR Review
LUC4N3X/Levyra-deepsound
Review a Levyra branch, commit, patch, or pull request for correctness, regressions, concurrency, lifecycle, security, data safety, UI behavior, CI, release risk, missing tests, and merge-readiness…
Related
Questions about Levyra Context Efficiency
What does Levyra Context Efficiency do?
A skill your agent uses for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup…. Levyra Context Efficiency is an agent skill from LUC4N3X/Levyra-deepsound. Use for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup, cross-domain exploration, or useful cross-session retrieval.
When should I use Levyra Context Efficiency?
Levyra Context Efficiency fits situations like: genuinely high-volume Levyra work such as builds; dependency output; codeRabbit inspection; cross-domain exploration.
How do I install Levyra Context Efficiency in Claude Code?
Run `npx skills add LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a claude-code`. Or copy the skill folder (.agents/skills/levyra-context-efficiency in LUC4N3X/Levyra-deepsound) into .claude/skills/levyra-context-efficiency in your project. Claude Code loads it when a task matches its description.
How do I install Levyra Context Efficiency in Codex?
Run `npx skills add LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a codex`. Or copy the skill folder (.agents/skills/levyra-context-efficiency in LUC4N3X/Levyra-deepsound) into .agents/skills/levyra-context-efficiency in your project. Codex loads it when a task matches its description.
Can I use Levyra Context Efficiency in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LUC4N3X/Levyra-deepsound --skill levyra-context-efficiency -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/levyra-context-efficiency, .gemini/skills/levyra-context-efficiency, .github/skills/levyra-context-efficiency and .opencode/skills/levyra-context-efficiency in your project.
What does Levyra Context Efficiency need to run?
Going by SKILL.md and its folder, Levyra Context Efficiency needs the command-line tools its instructions call (adb). Our summary lists: Python 3.
Does Levyra Context Efficiency access the network?
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.
Is Levyra Context Efficiency safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Levyra Context Efficiency use?
Levyra Context Efficiency is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Levyra Context Efficiency use?
About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Levyra Context Efficiency?
Skills that share tags, products or a category with Levyra Context Efficiency: Ship (juliepy/AI-Engineer-from-scrach, 436 stars), Invoking GitHub (oaustegard/claude-skills, 150 stars), Development Workflow (kid-sid/claude-spellbook, 190 stars) and Session Handoff Writer (codewhale-hq/Codewhale, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Levyra Context Efficiency?
LUC4N3X (a GitHub user) maintains it in LUC4N3X/Levyra-deepsound, which has 533 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 9, 2026.
Source: LUC4N3X/Levyra-deepsound on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.