New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ecosystem Usage

by evloghq in evloghq/evlog

Measure agent-facing traffic to the evlog docs site (MCP transport, raw Markdown, discovery paths) with Vercel Observability, and read it without inflating it.

MITAuto-check passedDevOps & Cloud

Install Ecosystem Usage

skills CLI
$ npx skills add evloghq/evlog --skill ecosystem-usage -a claude-code

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

GitHub CLI
$ gh skill install evloghq/evlog ecosystem-usage --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/evloghq/evlog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/evi/agent/skills/ecosystem-usage .claude/skills/ecosystem-usage && 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
ecosystem-usage
GitHub stars
1.9k
Token cost
~1.2k tokens
SKILL.md length
611 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Measure agent-facing traffic to the evlog docs site (MCP transport, raw Markdown, discovery paths) with Vercel Observability, and read it without inflating it.

  • Works in 5 steps: Agent-facing total → Explicit Markdown URLs → Content-negotiated Markdown → …
  • Tasks that involve Static sites and blogs
  • SKILL.md covers Source of truth, Query recipes, Interpretation rules and Output
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ecosystem Usage is an agent skill from evloghq/evlog. Measure agent-facing traffic to the evlog docs site (MCP transport, raw Markdown, discovery paths) with Vercel Observability, and read it without inflating it.

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 DevOps & Cloud, covering Static sites and blogs and Observability. It works with Model Context Protocol and Vercel. The repository describes itself as: Digging through logs is not observability. It's hope — wide events, structured errors, TypeScript-first, every runtime. The licence is MIT.

When your agent uses it

  • Tasks that involve Static sites and blogs
  • Tasks that involve Observability

Example prompts

  • “/ecosystem-usage”

Workflow steps

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

  1. Agent-facing total
  2. Explicit Markdown URLs
  3. Content-negotiated Markdown
  4. Agent discovery and intake
  5. curl traffic, only when explicitly asked

What it can do on your machine

Read from SKILL.md and the folder at commit 59a105f. 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

    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

Ecosystem Usage loads about 1.2k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 611 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
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 evloghq/evlog at commit 59a105f, republished under its MIT licence (© evloghq). 611 words, ~1,173 tokens.

Download SKILL.mdSave it as .claude/skills/ecosystem-usage/SKILL.md (or your agent's skills folder).
name
ecosystem-usage
description
Measure agent-facing traffic to the evlog docs site (MCP transport, raw Markdown, discovery paths) with Vercel Observability, and read it without inflating it.

Use this skill when asked about MCP adoption, AI-agent traffic, raw Markdown consumption, curl usage, or which clients consume the evlog docs. Web Analytics sees browsers only; this skill measures the requests that never run a pageview script.

Source of truth

Use the read-only vercel__create_observability_query tool, called through connection_execute.

  • Metric: vercel.request.count, aggregation sum.
  • Scope: type: 'project', ownerId: the evlog team id, projectIds: the docs site project id (both pre-scoped in the connection description).
  • Always filter to environment eq 'production'.
  • Use ISO UTC timestamps for startTime and endTime.
  • Because the result is read against a comparison, always query the requested window and the immediately preceding equal-length window with the same scope and filter, ungrouped.
  • A tool-call concurrency limit is not a total-query budget: send further read-only calls until every requested metric is collected.

Query recipes

Run independent queries in parallel, ungrouped first for the exact total, then grouped for the breakdown.

  1. Agent-facing total:
    • Filter: environment eq 'production'
    • Group by client_user_agent (limit 25) and bot_category + bot_name (limit 20).
  2. Explicit Markdown URLs:
    • Filter: endswith(request_path, '.md') and environment eq 'production'
    • Group by request_path (limit 10) and client_user_agent (limit 10).
  3. Content-negotiated Markdown:
    • Filter: contains(http_accept, 'text/markdown') and environment eq 'production'
    • Group by request_path (limit 10) and client_user_agent (limit 10).
  4. Agent discovery and intake:
    • Filter: (request_path eq '/llms.txt' or request_path eq '/llms-full.txt' or request_path eq '/sitemap.md' or request_path eq '/.well-known/mcp/server-card.json') and environment eq 'production'
    • Group by request_path (limit 10), client_user_agent (limit 10), or bot_category + bot_name (limit 10).
    • Keep these separate from content reads: fetching an index does not prove the client consumed a documentation page.
  5. curl traffic, only when explicitly asked:
    • Filter: contains(client_user_agent, 'curl/') and environment eq 'production'
    • Group by request_path and client_user_agent; exclude asset paths from the interpretation.
Show full SKILL.md (324 more words)Show less

Interpretation rules

  • Call the result HTTP requests, never tool calls, sessions, users, or unique agents. Initialization, discovery, tool calls, retries, and notifications each count separately.
  • Use the ungrouped summary as the authoritative total. Do not add grouped rows or timeseries buckets to reconstruct it.
  • Empty or generic user agents (node, undici, Go-http-client, python-httpx) identify a client stack, not an agent product. Never rename a generic or empty user agent into a specific product.
  • Report at most five recognized product rows with exact counts, then at most three generic stack rows, then the empty-user-agent row when present. Never sum version variants.
  • A .md path or a curl user agent alone does not prove AI usage: humans use "View as Markdown", scripts use curl. Treat explicit Accept: text/markdown, known AI bot categories, and MCP transport paths as the stronger signals.
  • Top-N grouped rows are partial: describe them as top returned rows, never as all traffic.
  • If a response says truncated: true or reports truncation.omittedArrayItems, only the returned timeseries was shortened; report the summary total and do not call it a data gap. Only label a real data gap when the API explicitly reports one after truncation is ruled out.
  • If a query times out, shorten the window or drop a high-cardinality grouping; the ungrouped total stays authoritative.
  • Browser traffic stays with vercel__count_pageviews and vercel__aggregate_pageviews; label it as browser pageviews and never present it as total readership when agent-facing traffic is in scope.

Output

  • Include the exact requested time window and every requested metric with its HTTP request count.
  • When a number is shown against a comparison, take the change from the queried preceding window; if that query was not performed or failed, write "change unavailable: <reason>" instead of implying a delta.
  • If a required query failed, show that metric as unavailable beside the successful totals, with the concrete error in one line.
  • End with one short caveat that HTTP request volume is not logical tool-call volume.

© evloghq, MIT. 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 apps/evi/agent/skills/ecosystem-usage of evloghq/evlog.

Open the folder on GitHubat commit 59a105f

Compare with similar skills

Ecosystem Usage 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.

Ecosystem Usage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ecosystem Usage this skillevloghq/evlog1.9k—~1.2kAutomated safety check: PassMIT
Codflow Setupbighadj22/codflow343—~7.8kAutomated safety check: NotesApache-2.0
Olore Axiom Latestolorehq/olore103—~495Automated safety check: PassMIT
UModel Root Cause Analysisalibaba/UnifiedModel412—~1.9kAutomated safety check: PassCustom licence
AWS Agentic AIzxkane/aws-skills3671 repos~2.5kAutomated safety check: PassMIT
Observability Triageevery-app/open-seo23k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Codflow Setup

    bighadj22/codflow

    Setup runbook for CodFlow — an AI agent following it authenticates with Cloudflare, creates the required resources (D1, R2, KV) in the developer's account, binds their real IDs into both…

    343 GitHub stars~7.8k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes

  • Olore Axiom Latest

    olorehq/olore

    Local Axiom documentation reference (latest). An agent skill from olorehq/olore.

    103 GitHub stars~495 tokensUpdated today
    DevOps & CloudAuto-check passed

  • UModel Root Cause Analysis

    alibaba/UnifiedModel

    Investigates a service incident to its root cause by querying a UModel object graph alongside metrics, logs, topology and recent deployments.

    412 GitHub stars~1.9k tokensUpdated 13 days ago
    DevOps & CloudAuto-check passed

  • AWS Agentic AI

    zxkane/aws-skills

    AWS Bedrock AgentCore comprehensive expert for deploying and managing AI agents at scale.

    367 GitHub starsUsed in 1 repo~2.5k tokens
    DevOps & CloudAuto-check passed

  • Observability Triage

    every-app/open-seo

    Triage OpenSEO production errors in Cloudflare Workers Observability — verified query recipes, counting gotchas, and a known-noise filter list applied automatically.

    23k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Agentmeasure

    roy-tong/AgentMeasure

    Check whether agent telemetry preserves measurement semantics.

    218 GitHub stars~753 tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed

More from evloghq/evlog

All 22 skills in this repo

  • evlog Adapter Creator

    evloghq/evlog

    Walks through adding a new built-in evlog drain adapter for an observability platform: source, build config, exports, tests, docs and PR scope.

    1.9k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • evlog Enricher Creator

    evloghq/evlog

    Guides adding a new built-in enricher to the evlog package, covering the source, tests, docs, README, a related skill and a changeset.

    1.9k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Evlog Log Analyzer

    evloghq/evlog

    Reads the structured wide-event logs that evlog writes to .evlog/logs/ so the agent can debug errors, find slow requests and explain what the app did.

    1.9k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • evlog Framework Integration

    evloghq/evlog

    Walks a contributor through adding a new HTTP framework integration to the evlog logging package: middleware source, build entry, exports, tests, example app and docs.

    1.9k GitHub stars~5k tokensUpdated today
    Auto-check: notes

  • evlog Map Rule Creator

    evloghq/evlog

    Walks through adding a new rule or framework adapter to `evlog map` in @evlog/cli, from the rule source and registry to types, tests, docs and the published skill.

    1.9k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • evlog Content Writing

    evloghq/evlog

    Rules for writing and reviewing evlog docs, blog posts, READMEs, skills and AGENTS.md files, with separate review and rewrite roles, a house voice and a catalog of AI-sounding tells.

    1.9k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Ecosystem Usage

What does Ecosystem Usage do?

Measure agent-facing traffic to the evlog docs site (MCP transport, raw Markdown, discovery paths) with Vercel Observability, and read it without inflating it. Ecosystem Usage is an agent skill from evloghq/evlog. Measure agent-facing traffic to the evlog docs site (MCP transport, raw Markdown, discovery paths) with Vercel Observability, and read it without inflating it.

When should I use Ecosystem Usage?

Ecosystem Usage fits situations like: tasks that involve Static sites and blogs; tasks that involve Observability.

How do I install Ecosystem Usage in Claude Code?

Run `npx skills add evloghq/evlog --skill ecosystem-usage -a claude-code`. Or copy the skill folder (apps/evi/agent/skills/ecosystem-usage in evloghq/evlog) into .claude/skills/ecosystem-usage in your project. Claude Code loads it when a task matches its description.

How do I install Ecosystem Usage in Codex?

Run `npx skills add evloghq/evlog --skill ecosystem-usage -a codex`. Or copy the skill folder (apps/evi/agent/skills/ecosystem-usage in evloghq/evlog) into .agents/skills/ecosystem-usage in your project. Codex loads it when a task matches its description.

Can I use Ecosystem Usage 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 evloghq/evlog --skill ecosystem-usage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ecosystem-usage, .gemini/skills/ecosystem-usage, .github/skills/ecosystem-usage and .opencode/skills/ecosystem-usage in your project.

What does Ecosystem Usage need to run?

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

Does Ecosystem Usage 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 Ecosystem Usage 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 Ecosystem Usage use?

Ecosystem Usage is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ecosystem Usage use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Ecosystem Usage?

Skills that share tags, products or a category with Ecosystem Usage: Codflow Setup (bighadj22/codflow, 343 stars), Olore Axiom Latest (olorehq/olore, 103 stars), UModel Root Cause Analysis (alibaba/UnifiedModel, 412 stars) and AWS Agentic AI (zxkane/aws-skills, 367 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ecosystem Usage?

evloghq (a GitHub organization) maintains it in evloghq/evlog, which has 1,885 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 6, 2026.

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