Menu

Not in the top 1,000 by GitHub stars

agentsvc/skills

Agent skills for agentsvc.io: speech to text, web to Markdown, email verification, token safety checks, document extraction and 127 pay-per-call APIs. Works with Claude Code, Codex, Cursor.

Claude CodeEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/agentsvc/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 4ee85135d1e1

No earlier version was observed for comparison.

Compare on GitHub

skills/read-documents/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 4ee85135d1e1

No earlier version was observed for comparison.

Compare on GitHub

skills/token-safety-check/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 4ee85135d1e1

No earlier version was observed for comparison.

Compare on GitHub

skills/transcribe-audio/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 4ee85135d1e1

No earlier version was observed for comparison.

Compare on GitHub

skills/verify-email/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 4ee85135d1e1

No earlier version was observed for comparison.

Compare on GitHub

skills/web-to-markdown/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 4ee85135d1e1

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 4ee85135d1e1a07005ff3cf386f5e91b56e7691f

git clone --filter=blob:none --no-checkout https://github.com/agentsvc/skills.git .hotskills/agentsvc-skills && git -C .hotskills/agentsvc-skills checkout --detach 4ee85135d1e1a07005ff3cf386f5e91b56e7691f # Copy each selected skill directory from .hotskills/agentsvc-skills into .claude/skills/<skill-name>/
0GitHub stars
Not availablestars in 7 days
6skills in this repository
4commits in 30 days

Heat

Insufficient history

Not enough history yet to measure heat. It appears after a few days of data.

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Nov 4, 2026Nov 4, 20260

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

agentsvc

When your agent uses it

Call one of 127 pay-per-call APIs from agentsvc.io when a task needs something you cannot do yourself, such as reading a web page, a screenshot, speech to text, OCR, email verification, a token or wallet check, sanctions screening, company lookup, exchange rates, weather, news or satellite images. Use when the user asks for live or external data or a conversion you have no tool for. Search the catalog for free, then call the endpoint with a credit token, an x402 wallet or the Zero CLI. Prices from $0.002 per call, failed calls are never charged.

What it loads into context

Frontmatter

129 tokens

Always available to the agent

SKILL.md

788 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 1. Find the right service (free)
  2. 2. Look at the output (free)
  3. 3. Call it
  4. Responses
  5. Rules

Files

  • ../../.claude-plugin/marketplace.jsonasset1,235 bytes
  • SKILL.mdcore3,045 bytes
  • SKILL.mdcore3,045 bytes
  • SKILL.mdcore3,045 bytes
  • SKILL.mdcore3,045 bytes
Read SKILL.md

# agentsvc.io: pay-per-call APIs for agents

[agentsvc.io](https://agentsvc.io) runs 127 small APIs for agents behind one pattern: `POST https://agentsvc.io/api/v1/proxy/<slug>` with a JSON body. No account and no sign-up. You pay per successful call, from $0.002.

For the most common tasks there are dedicated skills: `transcribe-audio`, `web-to-markdown`, `verify-email`, `token-safety-check`, `read-documents`. Use this one for everything else.

## 1. Find the right service (free)

```sh
curl -s "https://agentsvc.io/api/v1/services?q=sanctions&limit=5"
```

Each result has `slug`, `price_usdc`, `input_schema`, `example_input` and a `try_url`. Pick the slug whose description matches the task and build the body from `input_schema`. Short keywords work best for `q` (`screenshot`, `whois`, `weather`, `vat`).
View the complete source on GitHub

Skills included

  • agentsvc
  • read-documents
  • token-safety-check
  • transcribe-audio
  • verify-email
  • web-to-markdown

Repository facts

License
MIT
Created
Oct 25, 2026
Last pushed
Oct 31, 2026
Forks
0
Open issues
0
Project activity
Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 15 notes
  • skills/agentsvc/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/agentsvc/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/agentsvc/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/read-documents/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/read-documents/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/token-safety-check/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/token-safety-check/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/transcribe-audio/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/transcribe-audio/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/transcribe-audio/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/transcribe-audio/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/verify-email/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/verify-email/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/web-to-markdown/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/web-to-markdown/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 67 signals by file

.claude-plugin/marketplace.json

  • Network accessline 5
    "name": "agentsvc.io",     "email": "agents@agentsvc.io",     "url": "https://agentsvc.io"
  • Network accessline 6
    "email": "agents@agentsvc.io",     "url": "https://agentsvc.io"   },
  • Network accessline 7
    "url": "https://agentsvc.io"
  • Network accessline 14
    "source": "./skills",       "skills": ["./"],       "author": { "name": "agentsvc.io", "url": "https://agentsvc.io" },
  • Network accessline 15
    "skills": ["./"],       "author": { "name": "agentsvc.io", "url": "https://agentsvc.io" },       "homepage": "https://agentsvc.io",
  • Network accessline 16
    "author": { "name": "agentsvc.io", "url": "https://agentsvc.io" },
  • Network accessline 17
    "homepage": "https://agentsvc.io",
  • Network accessline 18
    "repository": "https://github.com/agentsvc/skills",

skills/agentsvc/SKILL.md

  • Network accessline 8
    [agentsvc.io](https://agentsvc.io) runs 127 small APIs for agents behind one pattern: `POST https://agentsvc.io/api/v1/proxy/<slug>` with a JSON body. No account and no sign-up. You pay per successful call, from $0.002.
  • Network accessline 15
    curl -s "https://agentsvc.io/api/v1/services?q=sanctions&limit=5"
  • Network accessline 25
    curl -s -X POST https://agentsvc.io/api/v1/try/<slug> -H "Content-Type: application/json" -d '{}'
  • Network accessline 30
    **Credit token** (simplest for scripts and coding agents). The owner buys one at https://agentsvc.io/credits ($5 to $100 in USDC on Base, +10% bonus credit) and gives it to you as an environment variable:
  • Network accessline 33
    [Credential-related source omitted]
  • Access to secretsline 33
    [Credential-related source omitted]
  • Access to secretsline 34
    [Credential-related source omitted]
  • Network accessline 38
    **x402 wallet**: without a token the endpoint answers HTTP 402 with the price. Any x402 client pays it in USDC on Base, Solana, Polygon or Arbitrum and retries; no gas needed. Setup for JavaScript and Python: https://agentsvc.io/docs#quicks
  • Network accessline 40
    **Zero CLI**: if `zero` is installed, it pays the 402 for you: `zero fetch https://agentsvc.io/api/v1/proxy/<slug> -d '<json body>'`
  • Network accessline 52
    Full catalog with schemas: https://agentsvc.io/llms-full.txt

skills/read-documents/SKILL.md

  • Network accessline 31
    curl -s -X POST https://agentsvc.io/api/v1/try/invoice-extract -H "Content-Type: application/json" -d '{}'
  • Network accessline 36
    With a credit token (bought at https://agentsvc.io/credits for $5 or more in USDC on Base, kept in `AGENTSVC_TOKEN`). Write the body to a file, base64 is large:
  • Network accessline 39
    printf '{"pdf_base64":"%s"}' "$(base64 -w0 report.pdf)" > body.json curl -s -X POST https://agentsvc.io/api/v1/proxy/pdf-extract \
  • Network accessline 40
    [Credential-related source omitted]
  • Access to secretsline 40
    [Credential-related source omitted]
  • Access to secretsline 41
    [Credential-related source omitted]
  • Network accessline 44
    Without a token the endpoint answers 402 and any x402 client pays it in USDC (Base, Solana, Polygon or Arbitrum): https://agentsvc.io/docs#quickstart. With the Zero CLI: `zero fetch https://agentsvc.io/api/v1/proxy/pdf-extract -d '<json bod
  • Network accessline 50
    Guide: https://agentsvc.io/guides/extract-text-from-documents

skills/token-safety-check/SKILL.md

  • Network accessline 25
    curl -s -X POST https://agentsvc.io/api/v1/try/token-security -H "Content-Type: application/json" -d '{}'
  • Network accessline 30
    With a credit token (bought at https://agentsvc.io/credits for $5 or more in USDC on Base, kept in `AGENTSVC_TOKEN`):
  • Network accessline 33
    [Credential-related source omitted]
  • Access to secretsline 33
    [Credential-related source omitted]
  • Access to secretsline 34
    [Credential-related source omitted]
  • Network accessline 38
    Trading agents usually already have a wallet: without a token the endpoint answers 402 and any x402 client pays it in USDC (Base, Solana, Polygon or Arbitrum), no gas needed: https://agentsvc.io/docs#quickstart. With the Zero CLI: `zero fet
  • Network accessline 52
    Guide: https://agentsvc.io/guides/check-token-before-swap · Example repo: https://github.com/agentsvc/x402-token-check-before-swap

skills/transcribe-audio/SKILL.md

  • Network accessline 8
    `POST https://agentsvc.io/api/v1/proxy/audio-transcribe` turns a recording into text with timestamps. Whisper runs on agentsvc.io's own server, the audio is deleted after the call. $0.01 per call of up to 10 minutes.
  • Network accessline 26
    curl -s -X POST https://agentsvc.io/api/v1/try/audio-transcribe -H "Content-Type: application/json" -d '{}'
  • Network accessline 31
    With a credit token (bought at https://agentsvc.io/credits for $5 or more in USDC on Base, kept in `AGENTSVC_TOKEN`):
  • Network accessline 34
    [Credential-related source omitted]
  • Access to secretsline 34
    [Credential-related source omitted]
  • Access to secretsline 35
    [Credential-related source omitted]
  • Network accessline 36
    -d '{"audio_url":"https://example.com/meeting.mp3"}'
  • Network accessline 42
    printf '{"audio_base64":"%s"}' "$(base64 -w0 note.m4a)" > body.json curl -s -X POST https://agentsvc.io/api/v1/proxy/audio-transcribe \
  • Network accessline 43
    [Credential-related source omitted]
  • Access to secretsline 43
    [Credential-related source omitted]
  • Access to secretsline 44
    [Credential-related source omitted]
  • Network accessline 47
    Without a token the endpoint answers 402 and any x402 client pays it in USDC (Base, Solana, Polygon or Arbitrum): https://agentsvc.io/docs#quickstart. With the Zero CLI: `zero fetch https://agentsvc.io/api/v1/proxy/audio-transcribe -d '{"au
  • Network accessline 63
    Guide with JavaScript and Python: https://agentsvc.io/guides/transcribe-audio

skills/verify-email/SKILL.md

  • Network accessline 8
    `POST https://agentsvc.io/api/v1/proxy/email-verify` with `{"email": "jane@example.com"}` asks the mail server whether the mailbox exists. No email is sent. $0.002 per address. Results are cached for 6 hours, so a repeated address answers i
  • Network accessline 25
    curl -s -X POST https://agentsvc.io/api/v1/try/email-verify -H "Content-Type: application/json" -d '{}'
  • Network accessline 30
    With a credit token (bought at https://agentsvc.io/credits for $5 or more in USDC on Base, kept in `AGENTSVC_TOKEN`). A list, one address per line:
  • Network accessline 33
    while read email; do   curl -s -X POST https://agentsvc.io/api/v1/proxy/email-verify \
  • Network accessline 34
    [Credential-related source omitted]
  • Access to secretsline 34
    [Credential-related source omitted]
  • Access to secretsline 35
    [Credential-related source omitted]
  • Network accessline 40
    Without a token the endpoint answers 402 and any x402 client pays it in USDC (Base, Solana, Polygon or Arbitrum): https://agentsvc.io/docs#quickstart. With the Zero CLI: `zero fetch https://agentsvc.io/api/v1/proxy/email-verify -d '{"email"
  • Network accessline 46
    Guide: https://agentsvc.io/guides/verify-email

skills/web-to-markdown/SKILL.md

  • Network accessline 27
    curl -s -X POST https://agentsvc.io/api/v1/try/web-scrape -H "Content-Type: application/json" -d '{"url":"https://example.com"}'
  • Network accessline 32
    With a credit token (bought at https://agentsvc.io/credits for $5 or more in USDC on Base, kept in `AGENTSVC_TOKEN`):
  • Network accessline 35
    [Credential-related source omitted]
  • Access to secretsline 35
    [Credential-related source omitted]
  • Access to secretsline 36
    [Credential-related source omitted]
  • Network accessline 37
    -d '{"url":"https://example.com/blog/post","max_chars":20000}' | jq -r .data.markdown
  • Network accessline 39
    [Credential-related source omitted]
  • Access to secretsline 39
    [Credential-related source omitted]
  • Access to secretsline 40
    [Credential-related source omitted]
  • Network accessline 41
    -d '{"urls":["https://example.com/a","https://example.com/b"],"max_chars":8000}'
  • Network accessline 44
    Without a token the endpoint answers 402 and any x402 client pays it in USDC (Base, Solana, Polygon or Arbitrum): https://agentsvc.io/docs#quickstart. With the Zero CLI: `zero fetch https://agentsvc.io/api/v1/proxy/web-scrape -d '{"url":"…"
  • Network accessline 53
    Guide: https://agentsvc.io/guides/web-page-to-markdown

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 59 facts

and 9 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/agentsvc/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/agentsvc/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/agentsvc/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/agentsvc/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/agentsvc/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

radres/call-me

Let your AI agents call and text your actual phone (iPhone or Android) — Claude Code plugin + agent skill

35GitHub stars

coreyhaines31/marketingskills

Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

58.9kGitHub stars

SurefireStudios/tldr

Too long; didn't read — for AI coding agents. A skill that makes Claude Code, Cursor, Codex, Gemini CLI and 16 more lead with a 3-line TL;DR and fold the detail instead of burying…

12GitHub stars

wondelai/skills

Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io a…

2.6kGitHub stars

swarmclawai/andrej-karpathy-skills

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENTS.md or Agent Skills-compatible agent.

58GitHub stars

neuman/nopekit

Explore ideas, engineer real things, and find out what holds up. An AI engineering partner for grounded, evidence-driven design.

18GitHub stars