{"id":"9f43958e-53be-4ce2-a942-a2e005a8949b","shortId":"YER2XT","kind":"skill","title":"sn-image-resume","tagline":"Generates a designed portfolio-resume image from resume content provided in conversation text.\nExtracts optional style instructions, converts the resume into a fixed portfolio-resume layout prompt,\nand generates the final image through sn-image-base. Use when user asks to create ","description":"# sn-image-resume\n\nResume image generation scene skill (tier 1), relying on the `sn-text-optimize` and `sn-image-generate` tools provided by `sn-image-base` (tier 0).\n\nFeatures:\n\n- Accepts resume content directly from conversational text\n- Supports optional user-provided style direction\n- Applies the fixed portfolio-resume layout rules in `prompts/resume.md`\n- Generates a tall designed resume image through `sn-image-generate`\n\n## Non-goals\n\n- Editing or polishing a plain text resume document without generating an image\n- Parsing uploaded resume files as the primary input format\n- Creating a conventional single-column ATS resume\n- Guaranteeing exact preservation of every long paragraph when the image layout requires compression\n\n## Input Specification\n\n|Parameter|Type|Default Value|Description|\n|---|---|---|---|\n|`resume_content`|string|**Required**|Resume text provided by the user in conversation, including name, profile, education, experience, skills, projects, contact details, etc.|\n|`style`|string|Optional|User-specified visual style, tone, color palette, profession aesthetic, or reference mood. May be embedded in `resume_content`.|\n|`aspect_ratio`|string|`9:16`|Output aspect ratio. Allowed values: `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `1:1`, `16:9`, `9:16`, `21:9`, `9:21`. Default is `9:16` (vertical) because the template is a tall stacked portfolio-resume page.|\n|`image_size`|string|`2k`|Image size preset, `1k` or `2k`.|\n|`output_mode`|string|`friendly`|Output mode: `friendly` or `verbose`.|\n\n## API Configuration\n\nAll API calls in this skill are executed through the `sn_agent_runner.py` of the `sn-image-base` skill, with authentication parameters using default values (CLI > environment variables > built-in defaults), so they do not need to be passed explicitly in normal use.\n\n|Call Type|Tool|Authentication Parameters|Description|\n|---|---|---|---|\n|**LLM**|`sn-text-optimize`|Default reads `SN_TEXT_API_KEY` -> `SN_CHAT_API_KEY` -> `SN_API_KEY`|Converts user resume text into a detailed image generation prompt using `prompts/resume.md` as the system prompt|\n|**Image Generation**|`sn-image-generate`|Default reads `SN_IMAGE_GEN_API_KEY` -> `SN_API_KEY`|Generates the final resume image|\n\nIf all capabilities use the same gateway, configure only:\n\n```ini\nSN_BASE_URL=\"https://your-api-endpoint.com/v1\"\nSN_API_KEY=\"your-api-key\"\n```\n\n**When encountering `MissingApiKeyError` or needing to specify a model**: pass parameters explicitly via CLI. See `$SN_IMAGE_BASE/references/api_spec.md`.\n\n**`$SN_IMAGE_BASE` path explanation**: `$SN_IMAGE_BASE` is the installation directory of the `sn-image-base` skill (`SKILL.md` exists). The agent can locate this path by skill name `sn-image-base`.\n\n## Architecture: Main Agent + Worker Agent\n\nThis skill uses a two-tier agent architecture:\n\n|Role|Responsibility|\n|---|---|\n|**Main Agent**|Receive user request, normalize parameters, send preflight, start Worker, collect result, and send final text/image to user|\n|**Worker Agent**|Execute prompt generation and image generation, then return structured JSON|\n\n**Responsibility Boundaries**:\n\n- Worker Agent **does not send any messages to the user directly**, only returns structured JSON\n- Main Agent is responsible for all user-visible messages\n- Worker Agent's last message **must be and only be** the JSON string defined in the Return Contract\n- Worker Agent's low-level API calls execute directly through `sn-image-base`, without spawning nested subagents\n\n## Workflow\n\n### Main Agent Workflow\n\n1. Extract `resume_content`, optional `style`, `aspect_ratio` (default `9:16`), `image_size` (default `2k`), and `output_mode` (default `friendly`) from the user request\n2. Validate that `resume_content` is non-empty and contains enough resume information to generate a meaningful page\n3. Validate `aspect_ratio` against the allowed values: `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `1:1`, `16:9`, `9:16`, `21:9`, `9:21`. If the user-provided value is not in this list, inform the user and fall back to the default `9:16`\n4. Send uniform preflight message: `\"Using sn-image-resume skill to generate a resume image, please wait...\"`\n5. Start Worker Agent, passing in complete parameters and working directory\n6. When Worker Agent returns:\n   - `status=ok`: send a short summary and the generated image\n   - `status=error`: report the real `error` field content to the user\n\n### Worker Agent Workflow\n\nWorker Agent receives `resume_content`, `style`, `aspect_ratio`, `image_size`, `output_mode`, and the working directory of this skill (`SKILL_DIR`).\n\n#### Step 0 — Initialization\n\n1. Generate `task_id` using timestamp format `YYYYMMDD_HHMMSS`\n2. Create temporary directory: `/tmp/openclaw/sn-image-resume/<task_id>/` as `TEMP_DIR`\n3. Persist normalized inputs:\n\n```bash\necho \"$RESUME_CONTENT\" > \"$TEMP_DIR/resume-content.txt\"\necho \"$STYLE\" > \"$TEMP_DIR/style.txt\"\n```\n\n#### Step 1 — Resume Prompt Generation\n\nUse `prompts/resume.md` as the system prompt and call `sn-text-optimize` to convert the user resume content into a detailed image generation prompt.\n\n```bash\nUSER_PROMPT=$(cat << EOF\nResume content:\n$RESUME_CONTENT\n\nOptional style instruction:\n${STYLE:-No explicit style instruction. Infer an appropriate professional visual style from the resume content.}\n\nTask:\nConvert the resume content into a complete text-to-image prompt for a tall portfolio-resume image.\nFollow the fixed layout, language, content mapping, typography, panel, and style translation rules in the system prompt.\nReturn only the final image generation prompt. Do not include explanations, markdown fences, or alternative options.\nEOF\n)\n\npython \"$SN_IMAGE_BASE/scripts/sn_agent_runner.py\" sn-text-optimize \\\n  --system-prompt-path \"$SKILL_DIR/prompts/resume.md\" \\\n  --user-prompt \"$USER_PROMPT\" \\\n  --output-format json\n```\n\nParse JSON stdout and extract `result` as `generation_prompt`. If the process exits non-zero, returns invalid JSON, or `result` is empty, return `status=error` with the actual error.\n\nPersist output:\n\n```bash\necho \"$GENERATION_PROMPT\" > \"$TEMP_DIR/generation-prompt.txt\"\n```\n\n#### Step 2 — Resume Image Generation\n\nGenerate the final image using `sn-image-base`'s `sn-image-generate` tool.\n\n```bash\npython \"$SN_IMAGE_BASE/scripts/sn_agent_runner.py\" sn-image-generate \\\n  --prompt \"$GENERATION_PROMPT\" \\\n  --image-size \"$IMAGE_SIZE\" \\\n  --aspect-ratio \"$ASPECT_RATIO\" \\\n  --save-path \"$TEMP_DIR/resume.png\" \\\n  --output-format json\n```\n\nParse JSON stdout. If generation fails, return `status=error` with the actual error. The generated image path is `$TEMP_DIR/resume.png`.\n\n### Error Handling Rules\n\n- If required resume content is missing, ask the user to provide resume text before starting generation\n- If `sn-text-optimize` fails or returns an empty result, stop and report the real error\n- If `sn-image-generate` fails, stop and report the real error\n- Do not silently substitute a generic resume prompt when user content is incomplete or prompt generation fails\n- Do not invent factual resume details that the user did not provide; only reorganize, condense, and visually map provided information\n\n### Return Contract\n\nAfter Worker Agent completes, its last message must be and only be the following JSON string (bare JSON, no code fences, no preceding or trailing text).\n\n**Normal Flow:**\n\n```json\n{\n  \"status\": \"ok\",\n  \"need_main_agent_send\": true,\n  \"output_mode\": \"friendly|verbose\",\n  \"image\": \"$TEMP_DIR/resume.png\",\n  \"generation_prompt\": \"<included only when output_mode=verbose>\",\n  \"timing\": {\n    \"total_elapsed_seconds\": 25.12,\n    \"prompt_generation\": { \"elapsed_seconds\": 5.23, \"model\": \"sensenova-6.7-flash-lite\" },\n    \"image_generation\": { \"elapsed_seconds\": 19.89, \"model\": \"sn_image_model\" }\n  }\n}\n```\n\n**Error Flow:**\n\n```json\n{\n  \"status\": \"error\",\n  \"error\": \"<Actual error information>\"\n}\n```\n\n**Rules:**\n\n- `status=ok` must contain `need_main_agent_send: true`\n- `generation_prompt` must contain when `output_mode=verbose`; omit it in `friendly` mode\n- `timing.prompt_generation.elapsed_seconds` and `timing.prompt_generation.model` are read from `sn-text-optimize` JSON output\n- `timing.image_generation.elapsed_seconds` is read from `sn-image-generate` JSON output\n- `timing.image_generation.model` is fixed to `\"sn_image_model\"` because `sn-image-generate` does not return a model field\n\n## Output Format\n\n### friendly mode (default)\n\n**Text Summary:** one sentence describing that the resume image has been generated, no more than 50 words.\n\n**Image:** send the single generated resume image.\n\n### verbose mode\n\n```text\nResume image generated\n---\nAspect ratio: <aspect_ratio>\nImage size: <image_size>\n---\nGeneration prompt:\n<generation_prompt>\n---\nTime statistics: Total <total>s | Prompt generation <t>s | Image generation <t>s\n---\nImage:\n<image path>\n```\n\n## Call Relationship\n\n- Bottom-level dependency: `sn-image-base` → `sn-text-optimize`, `sn-image-generate`\n- System prompt: `prompts/resume.md`\n\n## References\n\n- `prompts/resume.md` - Fixed portfolio-resume layout and language/content mapping rules\n- `../sn-image-base/SKILL.md` - Base-layer image/text tool behavior\n- `../sn-image-base/references/api_spec.md` - CLI parameter details","tags":["image","resume","sensenova","skills","opensensenova","agent","agent-skills","ai-agents","ai-assistant","data-analysis","document-processing","office-automation"],"capabilities":["skill","source-opensensenova","skill-sn-image-resume","topic-agent","topic-agent-skills","topic-ai-agents","topic-ai-assistant","topic-data-analysis","topic-document-processing","topic-office-automation","topic-presentation-slides"],"categories":["SenseNova-Skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/OpenSenseNova/SenseNova-Skills/sn-image-resume","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add OpenSenseNova/SenseNova-Skills","source_repo":"https://github.com/OpenSenseNova/SenseNova-Skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 1627 github stars · SKILL.md body (9,211 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:53:05.123Z","embedding":null,"createdAt":"2026-05-15T06:53:10.248Z","updatedAt":"2026-05-18T18:53:05.123Z","lastSeenAt":"2026-05-18T18:53:05.123Z","tsv":"'-6.7':1171 '/sn-image-base/references/api_spec.md':1346 '/sn-image-base/skill.md':1339 '/tmp/openclaw/sn-image-resume':767 '/v1':402 '0':81,752 '1':60,236,237,577,640,641,754,786 '16':218,238,241,249,587,642,645,671 '19.89':1179 '1k':269 '2':224,227,601,628,631,763,957 '21':242,245,646,649 '25.12':1163 '2k':265,271,591 '3':225,226,228,231,620,629,630,632,635,771 '4':229,230,232,235,633,634,636,639,672 '5':233,234,637,638,690 '5.23':1168 '50':1275 '6':701 '9':217,239,240,243,244,248,586,643,644,647,648,670 'accept':83 'actual':946,1018 'aesthet':204 'agent':450,464,466,474,479,498,512,527,537,555,575,693,704,728,731,1116,1147,1197 'allow':222,626 'altern':892 'api':281,284,341,345,348,377,380,404,408,560 'appli':97 'appropri':833 'architectur':462,475 'ask':47,1036 'aspect':214,220,583,622,736,994,996,1290 'aspect-ratio':993 'at':148 'authent':302,329 'back':666 'bare':1130 'base':43,79,299,398,430,435,445,461,568,969,1316,1341 'base-lay':1340 'base/references/api_spec.md':427 'base/scripts/sn_agent_runner.py':898,980 'bash':775,814,950,976 'behavior':1345 'bottom':1310 'bottom-level':1309 'boundari':510 'built':311 'built-in':310 'call':285,326,561,797,1307 'capabl':389 'cat':817 'chat':344 'cli':307,423,1347 'code':1133 'collect':489 'color':201 'column':147 'complet':696,848,1117 'compress':162 'condens':1106 'configur':282,394 'contact':189 'contain':611,1194,1203 'content':14,85,171,213,580,605,723,734,778,807,820,822,840,845,866,1033,1085 'contract':553,1113 'convent':144 'convers':17,88,181 'convert':23,350,803,842 'creat':49,142,764 'default':167,246,305,313,337,372,585,590,595,669,1259 'defin':549 'depend':1312 'describ':1264 'descript':169,331 'design':7,110 'detail':190,356,810,1097,1349 'dir':750,770 'dir/generation-prompt.txt':955 'dir/prompts/resume.md':908 'dir/resume-content.txt':780 'dir/resume.png':1002,1026,1156 'dir/style.txt':784 'direct':86,96,521,563 'directori':439,700,745,766 'document':128 'echo':776,781,951 'edit':121 'educ':185 'elaps':1161,1166,1177 'embed':210 'empti':609,940,1055 'encount':411 'enough':612 'environ':308 'eof':818,894 'error':717,721,943,947,1015,1019,1027,1062,1074,1184,1188,1189 'etc':191 'everi':154 'exact':151 'execut':290,499,562 'exist':448 'exit':930 'experi':186 'explan':432,888 'explicit':322,421,828 'extract':19,578,922 'factual':1095 'fail':1012,1051,1068,1091 'fall':665 'featur':82 'fenc':890,1134 'field':722,1254 'file':136 'final':37,384,493,881,963 'fix':28,99,863,1239,1330 'flash':1173 'flash-lit':1172 'flow':1141,1185 'follow':861,1127 'format':141,760,916,1005,1256 'friend':275,278,596,1152,1211,1257 'gateway':393 'gen':376 'generat':5,35,56,72,107,117,130,358,367,371,382,501,504,616,684,714,755,789,812,883,925,952,960,961,974,984,986,1011,1021,1045,1067,1090,1157,1165,1176,1200,1234,1248,1271,1281,1289,1294,1301,1304,1324 'generic':1080 'goal':120 'guarante':150 'handl':1028 'hhmmss':762 'id':757 'imag':3,11,38,42,52,55,71,78,112,116,132,159,262,266,298,357,366,370,375,386,426,429,434,444,460,503,567,588,680,687,715,738,811,852,860,882,897,959,964,968,973,979,983,989,991,1022,1066,1154,1175,1182,1233,1242,1247,1268,1277,1283,1288,1292,1303,1306,1315,1323 'image-s':988 'image/text':1343 'includ':182,887 'incomplet':1087 'infer':831 'inform':614,661,1111 'ini':396 'initi':753 'input':140,163,774 'instal':438 'instruct':22,825,830 'invalid':935 'invent':1094 'json':508,525,547,917,919,936,1006,1008,1128,1131,1142,1186,1224,1235 'key':342,346,349,378,381,405,409 'languag':865 'language/content':1336 'last':539,1119 'layer':1342 'layout':32,103,160,864,1334 'level':559,1311 'list':660 'lite':1174 'llm':332 'locat':452 'long':155 'low':558 'low-level':557 'main':463,478,526,574,1146,1196 'map':867,1109,1337 'markdown':889 'may':208 'meaning':618 'messag':517,535,540,676,1120 'miss':1035 'missingapikeyerror':412 'mode':273,277,594,741,1151,1206,1212,1258,1285 'model':418,1169,1180,1183,1243,1253 'mood':207 'must':541,1121,1193,1202 'name':183,457 'need':318,414,1145,1195 'nest':571 'non':119,608,932 'non-empti':607 'non-goal':118 'non-zero':931 'normal':324,483,773,1140 'ok':707,1144,1192 'omit':1208 'one':1262 'optim':67,336,801,902,1050,1223,1320 'option':20,91,194,581,823,893 'output':219,272,276,593,740,915,949,1004,1150,1205,1225,1236,1255 'output-format':914,1003 'page':261,619 'palett':202 'panel':869 'paragraph':156 'paramet':165,303,330,420,484,697,1348 'pars':133,918,1007 'pass':321,419,694 'path':431,454,906,1000,1023 'persist':772,948 'plain':125 'pleas':688 'polish':123 'portfolio':9,30,101,259,858,1332 'portfolio-resum':8,29,100,258,857,1331 'preced':1136 'preflight':486,675 'preserv':152 'preset':268 'primari':139 'process':929 'profess':203 'profession':834 'profil':184 'project':188 'prompt':33,359,365,500,788,795,813,816,853,877,884,905,911,913,926,953,985,987,1082,1089,1158,1164,1201,1295,1300,1326 'prompts/resume.md':106,361,791,1327,1329 'provid':15,74,94,176,654,1040,1103,1110 'python':895,977 'ratio':215,221,584,623,737,995,997,1291 'read':338,373,1218,1229 'real':720,1061,1073 'receiv':480,732 'refer':206,1328 'relationship':1308 'reli':61 'reorgan':1105 'report':718,1059,1071 'request':482,600 'requir':161,173,1031 'respons':477,509,529 'result':490,923,938,1056 'resum':4,10,13,25,31,53,54,84,102,111,127,135,149,170,174,212,260,352,385,579,604,613,681,686,733,777,787,806,819,821,839,844,859,958,1032,1041,1081,1096,1267,1282,1287,1333 'return':506,523,552,705,878,934,941,1013,1053,1112,1251 'role':476 'rule':104,873,1029,1190,1338 'save':999 'save-path':998 'scene':57 'second':1162,1167,1178,1214,1227 'see':424 'send':485,492,515,673,708,1148,1198,1278 'sensenova':1170 'sentenc':1263 'short':710 'silent':1077 'singl':146,1280 'single-column':145 'size':263,267,589,739,990,992,1293 'skill':58,187,288,300,446,456,468,682,748,749,907 'skill-sn-image-resume' 'skill.md':447 'sn':2,41,51,65,70,77,115,297,334,339,343,347,369,374,379,397,403,425,428,433,443,459,566,679,799,896,900,967,972,978,982,1048,1065,1181,1221,1232,1241,1246,1314,1318,1322 'sn-image-bas':40,76,296,442,458,565,966,1313 'sn-image-gener':69,114,368,971,981,1064,1231,1245,1321 'sn-image-resum':1,50,678 'sn-text-optim':64,333,798,899,1047,1220,1317 'sn_agent_runner.py':293 'source-opensensenova' 'spawn':570 'specif':164 'specifi':197,416 'stack':257 'start':487,691,1044 'statist':1297 'status':706,716,942,1014,1143,1187,1191 'stdout':920,1009 'step':751,785,956 'stop':1057,1069 'string':172,193,216,264,274,548,1129 'structur':507,524 'style':21,95,192,199,582,735,782,824,826,829,836,871 'subag':572 'substitut':1078 'summari':711,1261 'support':90 'system':364,794,876,904,1325 'system-prompt-path':903 'tall':109,256,856 'task':756,841 'temp':769,779,783,954,1001,1025,1155 'templat':253 'temporari':765 'text':18,66,89,126,175,335,340,353,800,850,901,1042,1049,1139,1222,1260,1286,1319 'text-to-imag':849 'text/image':494 'tier':59,80,473 'time':1159,1296 'timestamp':759 'timing.image_generation.elapsed':1226 'timing.image_generation.model':1237 'timing.prompt_generation.elapsed':1213 'timing.prompt_generation.model':1216 'tone':200 'tool':73,328,975,1344 'topic-agent' 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-assistant' 'topic-data-analysis' 'topic-document-processing' 'topic-office-automation' 'topic-presentation-slides' 'total':1160,1298 'trail':1138 'translat':872 'true':1149,1199 'two':472 'two-tier':471 'type':166,327 'typographi':868 'uniform':674 'upload':134 'url':399 'use':44,304,325,360,390,469,677,758,790,965 'user':46,93,179,196,351,481,496,520,533,599,653,663,726,805,815,910,912,1038,1084,1100 'user-prompt':909 'user-provid':92,652 'user-specifi':195 'user-vis':532 'valid':602,621 'valu':168,223,306,627,655 'variabl':309 'verbos':280,1153,1207,1284 'vertic':250 'via':422 'visibl':534 'visual':198,835,1108 'wait':689 'without':129,569 'word':1276 'work':699,744 'worker':465,488,497,511,536,554,692,703,727,730,1115 'workflow':573,576,729 'your-api-endpoint.com':401 'your-api-endpoint.com/v1':400 'your-api-key':406 'yyyymmdd':761 'zero':933","prices":[{"id":"a191864d-dee6-48ca-a1f8-aa4ebd60cb28","listingId":"9f43958e-53be-4ce2-a942-a2e005a8949b","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"OpenSenseNova","category":"SenseNova-Skills","install_from":"skills.sh"},"createdAt":"2026-05-15T06:53:10.248Z"}],"sources":[{"listingId":"9f43958e-53be-4ce2-a942-a2e005a8949b","source":"github","sourceId":"OpenSenseNova/SenseNova-Skills/sn-image-resume","sourceUrl":"https://github.com/OpenSenseNova/SenseNova-Skills/tree/main/skills/sn-image-resume","isPrimary":false,"firstSeenAt":"2026-05-15T06:53:10.248Z","lastSeenAt":"2026-05-18T18:53:05.123Z"}],"details":{"listingId":"9f43958e-53be-4ce2-a942-a2e005a8949b","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"OpenSenseNova","slug":"sn-image-resume","github":{"repo":"OpenSenseNova/SenseNova-Skills","stars":1627,"topics":["agent","agent-skills","ai-agents","ai-assistant","data-analysis","document-processing","office-automation","presentation-slides"],"license":"mit","html_url":"https://github.com/OpenSenseNova/SenseNova-Skills","pushed_at":"2026-05-15T04:43:37Z","description":"Modular SenseNova skills for building AI-powered office assistants and productivity workflows","skill_md_sha":"432c73490911c5189e8f4f17deeb380fee13235c","skill_md_path":"skills/sn-image-resume/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/OpenSenseNova/SenseNova-Skills/tree/main/skills/sn-image-resume"},"layout":"multi","source":"github","category":"SenseNova-Skills","frontmatter":{"name":"sn-image-resume","description":"Generates a designed portfolio-resume image from resume content provided in conversation text.\nExtracts optional style instructions, converts the resume into a fixed portfolio-resume layout prompt,\nand generates the final image through sn-image-base. Use when user asks to create \"resume image\",\n\"portfolio resume\", \"简历图\", \"简历海报\", or \"个人简历视觉设计\"."},"skills_sh_url":"https://skills.sh/OpenSenseNova/SenseNova-Skills/sn-image-resume"},"updatedAt":"2026-05-18T18:53:05.123Z"}}