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).
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
02 / STRUCTURE
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/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"
}
03 / WORKFLOW
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.
01
Input
Confirm scope
Read the trigger conditions and decide whether this skill matches the current task.
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.
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.
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.
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.
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.
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.
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.
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.
Review source evidence and runtime permissions before installing.
05 / CONTEXT
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.
06 / EVALUATION
Controlled evaluation
No controlled evaluation
This skill has only the evidence identified above. No task success, token efficiency, latency, or quality advantage is claimed.
Open the immutable source at https://github.com/anthropics/skills/tree/e4bb5d960d87126ff3b3a8af1a104b7db67560ba/skills/claude-api/SKILL.md.
Review the license, prerequisites and all bundled resources.
Install the skill into a personal or project-level Claude Code skills directory.
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.
08 / VERDICT
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.
09 / PROVENANCE
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.
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.