Index of every page on this site: llms.txt
All skills
paulrberg avatar

/cli-coingecko

@c9e5a34
by Paul Bergpaulrberg/agent-skills106 stars
11
Run it yourself

Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or historical/OHLC data.

  • 5 files
  • 6.5 KB
  • Updated 2 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/paulrberg/agent-skills/cli-coingecko

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈38 tokens for metadata: the name and description. ≈981 when used: this file. ≈362 more on demand in 2 files.

Description uses 1.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈154 characters, or 1.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

CoinGecko CLI

This skill is coordination-exempt: skip the ai-coord gate for its declared work.

Use the installed CLI's machine-readable command catalog as the authority for supported market-data operations.

Workflow

  1. Verify cg exists. Inspect non-interactive auth/tier state:

    command -v cg
    cg status -o json
    cg commands -o json

    Do not run interactive cg auth or write config without the user's approval.

  2. On an explicitly requested CLI update, run cg update --dry-run. Then run cg update within that authorization. Ask only if the preview reveals an action beyond the requested update. If automatic detection is wrong, pass --method with homebrew, npm, go, or script. Recheck cg version and cg commands -o json. Then, when maintaining this skill, record the verified version in references/version.txt.

  3. Select the command, flags, enum values, output formats, endpoint, auth requirement, and paid_only status from cg commands -o json. Use cg <command> --help only when the catalog lacks a needed detail.

  4. Resolve CoinGecko IDs with cg search <term> -o json when the user supplied a name or ambiguous symbol. Do not silently treat symbols as unique.

  5. Preview unfamiliar or quota-sensitive requests with --dry-run. Execute parseable queries with -o json. Use --export only when the user requested a CSV artifact.

  6. For a historical-data request, these CLI failures can trigger the browser fallback:

    • cg is unavailable.
    • cg history fails due to a CLI defect.
    • Its response is demonstrably malformed.

    If one prevents completion and a visual result can satisfy the request, immediately read references/open-historical-page.md. Under those conditions, use its browser fallback.

  7. Present the requested result in the user's format. For ordinary human-readable output, use a compact table. Preserve enough precision for the asset's magnitude.

Boundaries and Defaults

  • Batch IDs in one request when the command supports it. On 429, respect the reported reset/backoff instead of retrying aggressively.
  • Detect paid-only commands before execution. If the current tier cannot serve the request, report that limitation. Under that condition, offer a supported route.
  • Do not use the browser fallback for authentication, tier, rate-limit, invalid-input, or ambiguity errors. It does not satisfy requests for JSON, CSV, or other machine-readable evidence.
  • cg does not cover every CoinGecko endpoint. For unsupported contract-address prices, global stats, NFT detail, GeckoTerminal, or logo metadata, fetch the relevant current API documentation from https://docs.coingecko.com/llms.txt. For those requests, state that the CLI route is unavailable.
  • Never expose API keys or send private wallet/account data to market-data endpoints.

Completion requires the resolved coin/command, successful JSON or requested export evidence, and explicit handling of tier, ambiguity, or rate-limit constraints. A historical-page fallback instead requires a validated URL opened in Chromium plus disclosure of the CLI failure that triggered it.

User-Facing Output

For ordinary human output, lead with ### 🪙 <coin> (<id>). Show only the requested metrics in a compact table. Add one source line with the endpoint plus timestamp, tier, or window when material.

For exports, use ### ✅ Exported <row count> rows. Link the artifact. State the query/window without reproducing the CSV.

When returning control, use ### ⚠️ Rate limited — retry after <time>. Only while actively waiting, use ### ⏳ Rate limited — retrying after <time>. For a paid endpoint, use ### ⚠️ Paid endpoint — current tier: <tier> with one supported route. Return requested JSON/CSV, exact IDs, URLs, values, commands, and diagnostics undecorated.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at c9e5a34. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 months ago
coordination
exempt
user-invocable
false

README badge

README badge for paulrberg/agent-skills/cli-coingecko