[ { "scope": "https://api.anthropic.com:443", "method": "POST", "path": "/v1/messages", "body": { "model": "claude-haiku-4-5", "max_tokens": 64000, "system": [ { "type": "text", "text": "Skill loading protocol:\nSkills are optional instruction packs, not execution tools. Use them to get extra guidance only when they are relevant to the user's current request.\n\nAvailable skills:\n- name: \"Summary marker\"\n description: \"Use for summarizing notes, updates, or short text while preserving a marker.\"\n id: \"summary-marker\"\n category: \"productivity\"\n\nWhen deciding whether to load a skill:\n- Match the user's request against the skill name and description.\n- If one skill clearly matches, call load_skill once with `{ \"skillId\": \"\" }`, then follow the returned instructions.\n- If a loaded skill references a supporting file, call load_skill with `{ \"skillId\": \"\", \"filePath\": \"\" }`.\n- If the relevant skill was already loaded for this request, do not call load_skill again.\n- If no skill clearly matches, do not call load_skill.\n- Do not load a skill just because it is listed here.\n\nYou are testing runtime skill loading. Use the skill catalog in your instructions to pick a matching skillId. Call load_skill with the exact matching skillId before answering when a skill applies. After loading a skill, strictly follow its returned instructions. Do not answer from memory when a relevant skill applies." } ], "messages": [ { "role": "user", "content": [ { "type": "text", "text": "The Summary marker skill applies. Load the relevant skill first, then summarize: n8n agents keep workflow context compact." } ] } ], "tools": [ { "name": "load_skill", "description": "Load a skill by skillId or name. This source does not support linked files, so do not pass filePath.", "input_schema": { "type": "object", "properties": { "skillId": { "type": "string", "minLength": 1, "description": "Skill id from the skill catalog." }, "name": { "type": "string", "minLength": 1, "description": "Skill name from the skill catalog." } }, "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#" } } ], "tool_choice": { "type": "auto" } }, "status": 200, "response": "{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_017Ydh5amLQEJMZi2SL2BFZp\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"toolu_01L1gQY84Qqkbb2Vj91eQHay\",\"name\":\"load_skill\",\"input\":{\"skillId\":\"summary-marker\"},\"caller\":{\"type\":\"direct\"}}],\"stop_reason\":\"tool_use\",\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":1079,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":57,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}", "rawHeaders": { "anthropic-ratelimit-input-tokens-limit": "10000000", "anthropic-ratelimit-input-tokens-remaining": "10000000", "anthropic-ratelimit-input-tokens-reset": "2026-07-06T08:44:58Z", "anthropic-ratelimit-output-tokens-limit": "2000000", "anthropic-ratelimit-output-tokens-remaining": "2000000", "anthropic-ratelimit-output-tokens-reset": "2026-07-06T08:44:58Z", "anthropic-ratelimit-requests-limit": "20000", "anthropic-ratelimit-requests-remaining": "19999", "anthropic-ratelimit-requests-reset": "2026-07-06T08:44:57Z", "anthropic-ratelimit-tokens-limit": "12000000", "anthropic-ratelimit-tokens-remaining": "12000000", "anthropic-ratelimit-tokens-reset": "2026-07-06T08:44:58Z", "cf-cache-status": "DYNAMIC", "cf-ray": "a16d549adc3e589a-BCN", "connection": "keep-alive", "content-security-policy": "default-src 'none'; frame-ancestors 'none'", "content-type": "application/json", "date": "Mon, 06 Jul 2026 08:44:58 GMT", "request-id": "req_011CckWYH41USJ75EenpGCQY", "server": "cloudflare", "strict-transport-security": "max-age=31536000; includeSubDomains; preload", "traceresponse": "00-97b48f09aca0aecc15e1ed8c9fe8651d-dd31bf983e86dc71-01", "vary": "Accept-Encoding", "x-robots-tag": "none" }, "responseIsBinary": false }, { "scope": "https://api.anthropic.com:443", "method": "POST", "path": "/v1/messages", "body": { "model": "claude-haiku-4-5", "max_tokens": 64000, "system": [ { "type": "text", "text": "Skill loading protocol:\nSkills are optional instruction packs, not execution tools. Use them to get extra guidance only when they are relevant to the user's current request.\n\nAvailable skills:\n- name: \"Summary marker\"\n description: \"Use for summarizing notes, updates, or short text while preserving a marker.\"\n id: \"summary-marker\"\n category: \"productivity\"\n\nWhen deciding whether to load a skill:\n- Match the user's request against the skill name and description.\n- If one skill clearly matches, call load_skill once with `{ \"skillId\": \"\" }`, then follow the returned instructions.\n- If a loaded skill references a supporting file, call load_skill with `{ \"skillId\": \"\", \"filePath\": \"\" }`.\n- If the relevant skill was already loaded for this request, do not call load_skill again.\n- If no skill clearly matches, do not call load_skill.\n- Do not load a skill just because it is listed here.\n\nYou are testing runtime skill loading. Use the skill catalog in your instructions to pick a matching skillId. Call load_skill with the exact matching skillId before answering when a skill applies. After loading a skill, strictly follow its returned instructions. Do not answer from memory when a relevant skill applies." } ], "messages": [ { "role": "user", "content": [ { "type": "text", "text": "The Summary marker skill applies. Load the relevant skill first, then summarize: n8n agents keep workflow context compact." } ] }, { "role": "assistant", "content": [ { "type": "tool_use", "id": "toolu_01L1gQY84Qqkbb2Vj91eQHay", "name": "load_skill", "input": { "skillId": "summary-marker" }, "caller": { "type": "direct" } } ] }, { "role": "user", "content": [ { "type": "tool_result", "tool_use_id": "toolu_01L1gQY84Qqkbb2Vj91eQHay", "content": [ { "type": "text", "text": "[Skill: \"Summary marker\"]\n[Skill category: \"productivity\"]\n[Skill hash: \"e3433b77c9e3\"]\n\nEvery final answer after loading this skill must include the exact marker SKILL_MARKER_ALPHA. For summaries, be concise and keep the marker unchanged." } ] } ] } ], "tools": [ { "name": "load_skill", "description": "Load a skill by skillId or name. This source does not support linked files, so do not pass filePath.", "input_schema": { "type": "object", "properties": { "skillId": { "type": "string", "minLength": 1, "description": "Skill id from the skill catalog." }, "name": { "type": "string", "minLength": 1, "description": "Skill name from the skill catalog." } }, "additionalProperties": false, "$schema": "http://json-schema.org/draft-07/schema#" } } ], "tool_choice": { "type": "auto" } }, "status": 200, "response": "{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_01MLCY35L5o8Yag5erP4BPCM\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"text\",\"text\":\"**Summary:**\\n\\nn8n agents maintain workflow context efficiently by keeping it compact. This allows for streamlined execution and better memory management within automation workflows, reducing overhead while preserving essential information needed for agent operations.\\n\\nSKILL_MARKER_ALPHA\"}],\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":1215,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":55,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}", "rawHeaders": { "anthropic-ratelimit-input-tokens-limit": "10000000", "anthropic-ratelimit-input-tokens-remaining": "9999000", "anthropic-ratelimit-input-tokens-reset": "2026-07-06T08:44:59Z", "anthropic-ratelimit-output-tokens-limit": "2000000", "anthropic-ratelimit-output-tokens-remaining": "2000000", "anthropic-ratelimit-output-tokens-reset": "2026-07-06T08:45:00Z", "anthropic-ratelimit-requests-limit": "20000", "anthropic-ratelimit-requests-remaining": "19999", "anthropic-ratelimit-requests-reset": "2026-07-06T08:44:58Z", "anthropic-ratelimit-tokens-limit": "12000000", "anthropic-ratelimit-tokens-remaining": "11999000", "anthropic-ratelimit-tokens-reset": "2026-07-06T08:44:59Z", "cf-cache-status": "DYNAMIC", "cf-ray": "a16d54a14884589a-BCN", "connection": "keep-alive", "content-security-policy": "default-src 'none'; frame-ancestors 'none'", "content-type": "application/json", "date": "Mon, 06 Jul 2026 08:45:00 GMT", "request-id": "req_011CckWYMTgCwuyKTBSpSK89", "server": "cloudflare", "strict-transport-security": "max-age=31536000; includeSubDomains; preload", "traceresponse": "00-2c3af9579d58ddd9db43455722b54b60-d02bea40ae7237b6-01", "vary": "Accept-Encoding", "x-robots-tag": "none" }, "responseIsBinary": false } ]