Back to catalog
Human reviewedDevelopment

Skill dossier

claude-api

Source declaration

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

The author's original description, preserved in English. It describes intent, not verified performance.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

developmentscripts

Research summary

Human reviewed

Skill Atlas editorial review · editorial-preview-1.0.0

claude-api is a Claude Code Skill packaged as a fixed source snapshot. This editorial preview summarizes its declared purpose, on-disk structure and reviewable risk surface; it is not a controlled task evaluation.

Review scope

Deterministic static analysis of collected SKILL.md and supporting text/code. Machine-assisted candidates and findings await human editorial review; no dynamic behavior or effect is assessed.

Observable capabilities

  • Source-declared purpose: Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it
  • Collected 96 file(s), including 4 script(s) and 91 reference(s).
  • Source-described workflow candidates are linked to exact source lines.

Limitations & scope

  • No controlled task evaluation was performed.
  • Exact token counts are unavailable and are not estimated.
  • Static findings are review prompts, not safety guarantees.

Relevant for

  • Technical readers evaluating this Skill
  • Reviewers studying how the Skill is constructed

What ships with the skill

The file inventory comes from the collected source at the recorded commit. Paths and sizes are structural observations, not a measure of quality.

files
96
Markdown files
91
scripts
4
references
91
Size
2 MB
Structural complexity
High

File inventory

PathTypeBytes
skills/claude-api/csharp/claude-api/batches.mdReference413 B
skills/claude-api/csharp/claude-api/files-api.mdReference900 B
skills/claude-api/csharp/claude-api/README.mdReference18.5 KB
skills/claude-api/csharp/claude-api/streaming.mdReference787 B
skills/claude-api/csharp/claude-api/tool-use.mdReference7.4 KB
skills/claude-api/curl/examples.mdReference9.5 KB
skills/claude-api/curl/managed-agents.mdReference10.5 KB
skills/claude-api/go/claude-api/files-api.mdReference936 B

SKILL.md frontmatter

{
  "name": "claude-api",
  "description": "Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).",
  "license": "Complete terms in LICENSE.txt"
}

A reading of the operating sequence

This workflow reconstructs the apparent sequence from source material. Unless controlled evaluation is explicitly recorded, it is provisional—not an observed trace.

  1. 01
    Input

    Confirm scope

    Read the trigger conditions and decide whether this skill matches the current task.

  2. 02
    Action

    Load instructions

    Claude Code reads the full SKILL.md when the skill is selected.

  3. 03
    Decision

    Use resources deliberately

    Read references or run scripts only when the documented workflow requires them.

  4. 04
    Output

    Deliver and verify

    Produce the requested artifact and verify it against the source-described acceptance criteria.

Potential risk surfaces

Static findings identify points to inspect before installation. They do not establish that a skill is safe, malicious, or effective.

Items warrant review

1554 lexical/coverage finding(s) require review. At least one known file was not retained and could not be scanned; this is not a no-findings or safety result.

Network accessObserved
File writesObserved
Credential useObserved
Note

File modification is described or implemented

1123 occurrences

This line contains a possible file-write or redirection operation. Check destination paths and overwrite behavior; the static review did not write any file. This rule matched 1123 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Medium

Network access is mentioned

375 occurrences

A URL or network client appears in this source line. Review destinations, data sent, and trust boundaries; static text cannot establish actual network activity. This rule matched 375 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

High

Credential or secret material is referenced

43 occurrences

This line resembles a credential literal or reads a sensitive environment value. Do not expose its contents; verify whether it is a placeholder, required secret, or accidentally committed material. This rule matched 43 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

High

Elevated privileges are referenced

2 occurrences

Privilege-elevation syntax is present. Confirm whether elevation is necessary and inspect every operation performed under it; static analysis cannot prove that elevation succeeded. This rule matched 2 location(s) in the collected text; 2 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Inspect all security findings (1554 findings)
High

Dynamic command execution is referenced

5 occurrences

A shell, dynamic evaluation, or process execution primitive appears here. Inspect arguments and input control. Presence in source does not prove a command ran. This rule matched 5 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

High

File deletion is described or implemented

3 occurrences

Deletion syntax occurs in this line, including possible documentation. Review its exact target, recursive scope, and safeguards. The analyzer did not execute it. This rule matched 3 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

High

Downloaded content may be executed

2 occurrences

This line combines retrieval and execution. Such patterns can run mutable remote code. Review pinning, integrity checks, and isolation; the analyzer performed no download or execution. This rule matched 2 location(s) in the collected text; 2 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Note

Source file was not retained for scanning

skills/claude-api/shared/model-migration.md is known from collection metadata but its content is unavailable. No line-level finding can be made for this file; absence of other matches is not a safety result. file exceeds 131072 bytes or has no declared size This rule matched 1 location(s) in the collected text; 1 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Source evidenceskills/claude-api/shared/model-migration.md (path only; content unavailable)
Editorial security note

Review source evidence and runtime permissions before installing.

Where context can be spent

Discovery, activation, and resource layers have different meanings. Exact values appear only when the official token-counting method was run with a named model.

Exact token counts unavailable

All token values, including per-file inventory, are null until the pipeline performs an official exact count with an explicit model.

No token measurement was recorded with the required official method. This dossier does not substitute character counts, file sizes, or estimates.

Controlled evaluation

No controlled evaluation

This skill has only the evidence identified above. No task success, token efficiency, latency, or quality advantage is claimed.

Not tested

Use with the source in view

Install command
/plugin marketplace add anthropics/skills /plugin install example-skills@anthropic-agent-skills
  1. Open the immutable source at https://github.com/anthropics/skills/tree/e4bb5d960d87126ff3b3a8af1a104b7db67560ba/skills/claude-api/SKILL.md.
  2. Review the license, prerequisites and all bundled resources.
  3. Install the skill into a personal or project-level Claude Code skills directory.
  4. Restart or refresh Claude Code so the skill can be discovered.
Verify installation

Open Claude Code and confirm the skill appears in the installed skills list, then run a representative prompt below.

Prerequisites

  • No controlled task evaluation was performed.
  • Exact token counts are unavailable and are not estimated.
  • Static findings are review prompts, not safety guarantees.

Example prompts

Representative task

Use the claude-api skill to help with this task. First summarize what the skill will do, then execute its documented workflow and show the source-linked evidence for each major decision.

Inspect before use

Read the claude-api skill files at https://github.com/anthropics/skills/tree/e4bb5d960d87126ff3b3a8af1a104b7db67560ba/skills/claude-api/SKILL.md. Explain its workflow, required tools, permissions and the main risks before I decide whether to install it.

A decision, with its limits attached

Strengths

  • Source is pinned to an immutable commit.
  • Instructions and resource inventory are available for inspection.

Considerations

  • Effectiveness has not been measured.
  • Review the source and runtime requirements before installation.
Research conclusion

Editorial preview: this dossier has a complete research layout; controlled evaluation is deferred until after deployment.

Traceable by construction

The dossier is a time-bound reading of a public artifact, not an endorsement. Use the source link to inspect the exact upstream material.

anthropicsskillsskills/claude-api
Source type
Official example
Commit
e4bb5d960d87126ff3b3a8af1a104b7db67560ba
Collected
20 Nov 2026
Last checked
20 Nov 2026
Upstream license
Apache-2.0
Repository stars
197,748
Content basis

Deterministic lexical parsing, YAML frontmatter validation, file inventory, source-described workflow extraction, and heuristic provisional classification of the supplied files only. Generated by machine; no LLM, execution, dynamic testing, or human editorial approval.