Agent skill

Entroly Lobehub Audit

by juyterman1000 in juyterman1000/entroly

Audit and remediate Entroly's MCP marketplace quality with evidence, adversarial validation, and no score gaming.

Apache-2.0Auto-check passedAgent Workflows

Install Entroly Lobehub Audit

skills CLI
$ npx skills add juyterman1000/entroly --skill entroly-lobehub-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install juyterman1000/entroly entroly-lobehub-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/juyterman1000/entroly.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/entroly-lobehub-audit .claude/skills/entroly-lobehub-audit && rm -rf skills-src

Use ~/.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/

Facts

Skill name
entroly-lobehub-audit
GitHub stars
474
Token cost
~1.2k tokens
SKILL.md length
630 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Audit and remediate Entroly's MCP marketplace quality with evidence, adversarial validation, and no score gaming.

  • Works in 11 steps: Read every score category, deduction,… → Map every deduction to the exact… → Classify every finding as one of → …
  • Tasks that involve Context engineering
  • SKILL.md covers Mission, Non-negotiable execution…, Priority and release isolation and LobeHub score registry, plus 4 more sections
  • Reaches lobehub.com

What it does

Entroly Lobehub Audit is an agent skill from juyterman1000/entroly. Audit and remediate Entroly's MCP marketplace quality with evidence, adversarial validation, and no score gaming.

Its SKILL.md is about 1.2k 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 Agent Workflows, covering Context engineering, MCP servers and LLM cost and token optimization. It works with Model Context Protocol. The repository describes itself as: Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Context engineering
  • Tasks that involve MCP servers
  • Tasks that involve LLM cost and token optimization

Example prompts

  • “/entroly-lobehub-audit”

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. Read every score category, deduction, warning, and missing requirement.
  2. Map every deduction to the exact repository file, runtime behavior, external
  3. Classify every finding as one of
  4. Improve only legitimate weaknesses. Never add empty keywords, fabricated
  5. Preserve Entroly's positioning as the auditable context, memory, and
  6. Implement production-quality fixes with tests, schemas, validation,
  7. Add CI regression gates so corrected findings cannot return.
  8. Run the official MCP, npm, PyPI, OpenClaw/ClawHub, and LobeHub-relevant
  9. Open a focused PR with a deduction-by-deduction remediation table.
  10. Merge only after all checks pass, publish the necessary patch release, and
  11. Never claim the score improved until the public page visibly confirms it.

What it can do on your machine

Read from SKILL.md and the folder at commit 25248bb. 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

    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.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • lobehub.com

    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

Entroly Lobehub Audit loads about 1.2k tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 630 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 passed

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.

SKILL.md

The full file from juyterman1000/entroly at commit 25248bb, republished under its Apache-2.0 licence (© juyterman1000). 630 words, ~1,242 tokens.

Download SKILL.mdSave it as .claude/skills/entroly-lobehub-audit/SKILL.md (or your agent's skills folder).
name
entroly-lobehub-audit
description
Audit and remediate Entroly's MCP marketplace quality with evidence, adversarial validation, and no score gaming.
status
active

Entroly LobeHub MCP Audit

Mission

Audit Entroly's complete LobeHub MCP score at:

https://lobehub.com/mcp/juyterman1000-entroly?activeTab=score

Act as a senior open-source product architect, MCP engineer, security engineer, Rust/Python/TypeScript developer, and release engineer.

Non-negotiable execution contract

  1. Read every score category, deduction, warning, and missing requirement.
  2. Map every deduction to the exact repository file, runtime behavior, external index state, or genuinely missing capability.
  3. Classify every finding as one of:
    • product or security defect;
    • packaging or discovery defect;
    • missing documentation;
    • stale external indexing;
    • criterion irrelevant to Entroly's context-control category.
  4. Improve only legitimate weaknesses. Never add empty keywords, fabricated evidence, fake benchmarks, or unnecessary features merely to game a score.
  5. Preserve Entroly's positioning as the auditable context, memory, and verification control plane for AI agents.
  6. Implement production-quality fixes with tests, schemas, validation, security controls, documentation, and reproducible evidence.
  7. Add CI regression gates so corrected findings cannot return.
  8. Run the official MCP, npm, PyPI, OpenClaw/ClawHub, and LobeHub-relevant validation paths.
  9. Open a focused PR with a deduction-by-deduction remediation table.
  10. Merge only after all checks pass, publish the necessary patch release, and verify the public LobeHub page after its index refresh.
  11. Never claim the score improved until the public page visibly confirms it.

Priority and release isolation

  1. Finish and publicly verify the ClawHub v1.0.54 metadata correction.
  2. Keep LobeHub remediation in a separate branch, PR, and release.
  3. Do not mix unrelated product work into marketplace remediation.

LobeHub score registry

The current public LobeHub implementation assigns 100 total points:

CriterionWeightRequired
Claimed listing4No
Non-manual deployment12No
Any deployment15Yes
Detected license8No
MCP prompts8No
README10Yes
MCP resources8No
MCP tools15Yes
Runtime validation20Yes

All required criteria must pass. With all required criteria present, 80% or higher is grade A, 60-79% is grade B, and lower is grade F.

Evidence registry

Maintain a table for each run:

CriterionPublic observationRepository evidenceClassificationActionTestExternal verification

Never infer an external success from local code alone. Mark external-only results as pending, blocked, or confirmed with a direct artifact, registry response, public page, or screenshot.

Show full SKILL.md (271 more words)Show less

Search and implementation loop

  1. Collect independent evidence from the public listing, repository, package registries, official specifications, and executable protocol probes.
  2. Keep distinct hypotheses separate until each has concrete evidence.
  3. Mark routes blocked when they depend on an unavailable external refresh or an unproved assumption; do not disguise a blocked route as progress.
  4. Implement the smallest real fix that improves users' ability to install, understand, validate, or safely use Entroly.
  5. Add adversarial tests for malformed inputs, bounded output, path safety, secret leakage, prompt injection, protocol compatibility, clean installs, and stale metadata.
  6. Re-run local validators, package dry-runs, protocol smoke tests, and the full CI matrix.
  7. Publish only after all gates are green.
  8. Re-check the exact public listing and record the observed score and flags.

Adversarial review checklist

Reject any candidate remediation that:

  • changes only wording without creating the claimed capability;
  • exposes secrets, unrestricted files, unbounded receipts, or unsafe paths;
  • adds MCP prompts or resources that are duplicates or decorative;
  • relies on a local editable install but fails from the published artifact;
  • reports validation without starting the server and listing its capabilities;
  • confuses MCP Registry, LobeHub, ClawHub, npm, and PyPI indexing states;
  • claims a marketplace score before the marketplace confirms it;
  • broadens Entroly into an unrelated framework merely to satisfy a directory.

Completion condition

The task is complete only when:

  • every legitimate deduction has a tested remediation or a documented external blocker;
  • the focused PR is green and merged;
  • required artifacts are published and installable;
  • the public LobeHub score page visibly reflects the new state; and
  • the final report distinguishes confirmed improvements from unresolved external indexing.

© juyterman1000, Apache-2.0. 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/entroly-lobehub-audit of juyterman1000/entroly.

Open the folder on GitHubat commit 25248bb

Compare with similar skills

Entroly Lobehub Audit 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.

Entroly Lobehub Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Entroly Lobehub Audit this skilljuyterman1000/entroly474—~1.2kAutomated safety check: PassApache-2.0
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence
Context Mode for Antigravity CLImksglu/context-mode26k—~850Automated safety check: PassCustom licence
Claude Code Masteryborghei/Claude-Skills891—~1.9kAutomated safety check: PassMIT
LemmalogJordyZomer/lemmalog329—~2.8kAutomated safety check: PassMIT
Cortex Mem MCPsopaco/cortex-mem313—~2.8kAutomated safety check: PassMIT

Similar skills

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.

    26k GitHub stars~850 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Claude Code Mastery

    borghei/Claude-Skills

    A skill your agent uses when the user asks to "optimize CLAUDE.md", "create a new skill", "write a custom agent", "configure hooks", "manage context window", "set up MCP servers", "scaffold a skill…

    891 GitHub stars~1.9k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Lemmalog

    JordyZomer/lemmalog

    Externalize working memory and logical state into the lemmalog Datalog engine (MCP).

    329 GitHub stars~2.8k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Cortex Mem MCP

    sopaco/cortex-mem

    Persistent memory enhancement for AI agents. An agent skill from sopaco/cortex-mem.

    313 GitHub stars~2.8k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • MCP Code Search Tool Selection

    Context-Engine-AI/Context-Engine

    Rules for choosing Qdrant-Indexer semantic search over grep or file reads when exploring code, debugging or asking where and why questions.

    402 GitHub stars~1.3k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

More from juyterman1000/entroly

  • Entroly Context Control

    juyterman1000/entroly

    Surgically select, compress, and recover codebase context using Entroly's MCP tools.

    474 GitHub stars~501 tokensUpdated today
    Auto-check passed
  • Entroly Evidence Operations

    juyterman1000/entroly

    Use Entroly for content-blind agent-history audits, explicit baseline/optimized trials, recoverable command or browser evidence, response contracts, and token-efficiency claim verification.

    474 GitHub stars~528 tokensUpdated today
    Auto-check passed

Categories

Questions about Entroly Lobehub Audit

What does Entroly Lobehub Audit do?

Audit and remediate Entroly's MCP marketplace quality with evidence, adversarial validation, and no score gaming. Entroly Lobehub Audit is an agent skill from juyterman1000/entroly. Audit and remediate Entroly's MCP marketplace quality with evidence, adversarial validation, and no score gaming.

When should I use Entroly Lobehub Audit?

Entroly Lobehub Audit fits situations like: tasks that involve Context engineering; tasks that involve MCP servers; tasks that involve LLM cost and token optimization.

How do I install Entroly Lobehub Audit in Claude Code?

Run `npx skills add juyterman1000/entroly --skill entroly-lobehub-audit -a claude-code`. Or copy the skill folder (.agents/skills/entroly-lobehub-audit in juyterman1000/entroly) into .claude/skills/entroly-lobehub-audit in your project. Claude Code loads it when a task matches its description.

How do I install Entroly Lobehub Audit in Codex?

Run `npx skills add juyterman1000/entroly --skill entroly-lobehub-audit -a codex`. Or copy the skill folder (.agents/skills/entroly-lobehub-audit in juyterman1000/entroly) into .agents/skills/entroly-lobehub-audit in your project. Codex loads it when a task matches its description.

Can I use Entroly Lobehub Audit 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 juyterman1000/entroly --skill entroly-lobehub-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/entroly-lobehub-audit, .gemini/skills/entroly-lobehub-audit, .github/skills/entroly-lobehub-audit and .opencode/skills/entroly-lobehub-audit in your project.

What does Entroly Lobehub Audit need to run?

SKILL.md names no scripts, command-line tools or credentials: Entroly Lobehub Audit is instructions for the agent only.

Does Entroly Lobehub Audit access the network?

SKILL.md names 1 domain. In commands or code: lobehub.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Entroly Lobehub Audit safe to install?

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.

What licence does Entroly Lobehub Audit use?

Entroly Lobehub Audit is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Entroly Lobehub Audit use?

About 1.2k 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 Entroly Lobehub Audit?

Skills that share tags, products or a category with Entroly Lobehub Audit: Context Mode Output Sandbox (mksglu/context-mode, 26k stars), Context Mode for Antigravity CLI (mksglu/context-mode, 26k stars), Claude Code Mastery (borghei/Claude-Skills, 891 stars) and Lemmalog (JordyZomer/lemmalog, 329 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Entroly Lobehub Audit?

juyterman1000 (a GitHub user) maintains it in juyterman1000/entroly, which has 474 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 11, 2026.

Source: juyterman1000/entroly on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.