{"id":"80acb805-fa86-4789-a0cb-b37fb8854e9d","shortId":"CsLEVw","kind":"skill","title":"researchclaw","tagline":"Automate setup, configuration, execution, monitoring, and troubleshooting of AutoResearchClaw — the 23-stage autonomous research pipeline that generates conference-grade papers. Use when the user mentions ResearchClaw, wants to write a research paper autonomously, needs to set up","description":"# ResearchClaw Skill — Autonomous Research Pipeline\n\nThis skill wraps [AutoResearchClaw](https://github.com/aiming-lab/AutoResearchClaw), a 23-stage pipeline that takes a research topic and produces a conference-grade LaTeX paper with real citations, sandbox-executed experiments, multi-agent peer review, and citation verification.\n\n**Honesty policy:** This skill does not fabricate capabilities. Every command maps to real upstream functionality. If something fails, the skill reports the actual error and suggests concrete fixes — it never pretends the problem does not exist.\n\n## Commands\n\n| Command | Purpose |\n|---|---|\n| `/researchclaw` | Show help and available subcommands |\n| `/researchclaw:setup` | Check and install all prerequisites (Python, Docker, LaTeX, pip packages) |\n| `/researchclaw:config` | Interactive config wizard — generates a working `config.yaml` |\n| `/researchclaw:run` | Start a research pipeline run |\n| `/researchclaw:status` | Check the status of a running or completed pipeline |\n| `/researchclaw:resume` | Resume a pipeline from the last successful stage |\n| `/researchclaw:diagnose` | Auto-detect and explain common failures |\n| `/researchclaw:validate` | Validate config, dependencies, and connectivity before running |\n\n---\n\n## /researchclaw — Help\n\nWhen invoked without a subcommand, display this command list and a one-line status summary:\n\n1. Check if `researchclaw` CLI is installed: `which researchclaw`\n2. Check if `config.yaml` exists in the current directory\n3. Print the command table above\n4. Suggest the most logical next step based on what is missing\n\n---\n\n## /researchclaw:setup — Prerequisites Installation\n\n**MANDATORY: Ask the user before installing anything.** Present what is missing and get explicit approval.\n\nRun the prerequisite check script:\n\n```bash\nbash \"${CLAUDE_SKILL_DIR}/scripts/check-prereqs.sh\"\n```\n\nThe script checks each dependency and outputs a JSON report. Based on the report:\n\n1. **Python 3.11+**: Check `python3 --version`. If missing or too old, suggest `pyenv install 3.11` or system package manager.\n2. **pip / uv**: Check `pip3 --version` or `uv --version`. Suggest `uv` if not present (faster).\n3. **Docker**: Check `docker info`. If Docker daemon is not running, tell the user honestly — this skill cannot start Docker for you on most systems.\n4. **LaTeX**: Check `pdflatex --version`. If missing, suggest `sudo apt-get install texlive-full` (Linux) or `brew install --cask mactex` (macOS). **Be honest: this is a large download (2-4 GB).**\n5. **AutoResearchClaw**: Check `pip3 show researchclaw`. If not installed:\n   ```bash\n   pip3 install researchclaw\n   ```\n   Or from source:\n   ```bash\n   git clone https://github.com/aiming-lab/AutoResearchClaw.git\n   cd AutoResearchClaw\n   pip3 install -e \".[all]\"\n   ```\n\nAfter installation, re-run the check script to verify everything passes.\n\n**What this skill CANNOT do:**\n- Start the Docker daemon (requires system-level access)\n- Install LaTeX without sudo on Linux\n- Fix network/firewall issues blocking API access\n- Provide LLM API keys — the user must supply their own\n\n---\n\n## /researchclaw:config — Interactive Configuration Wizard\n\nGenerate a working `config.yaml` by asking the user a series of questions. Use `AskUserQuestion` for each batch.\n\n**Batch 1 — Essential settings (MUST ask):**\n\n1. **Research topic**: What do you want to research? (free text)\n2. **LLM provider**: Which LLM API? Options: `openai`, `anthropic`, `azure`, `deepseek`, `local`\n3. **API key**: Provide your API key, or the environment variable name that holds it (e.g., `OPENAI_API_KEY`)\n4. **Model**: Which model? Suggest defaults per provider:\n   - openai: `gpt-4o`\n   - anthropic: `claude-sonnet-4-20250514`\n   - deepseek: `deepseek-chat`\n\n**Batch 2 — Experiment settings (ask with smart defaults):**\n\n5. **Experiment mode**: `simulated` (no code execution, fastest), `sandbox` (local execution), or `ssh_remote` (GPU server). Default: `simulated`\n6. **Auto-approve gates**: Skip human approval at stages 5, 9, 20? Default: `true` for first run\n7. **Output directory**: Where to save artifacts. Default: `artifacts/`\n\n**Batch 3 — Optional advanced settings (offer but don't require):**\n\n8. **Paper template**: `neurips`, `icml`, `iclr`, or `generic`. Default: `neurips`\n9. **Max iterations**: For iterative pipeline mode. Default: `3`\n10. **Literature sources**: `arxiv`, `semantic_scholar`, or `both`. Default: `both`\n\nAfter collecting answers, generate `config.yaml` using the template in `assets/config-template.yaml`. Write it to the current directory and show the user the generated file.\n\n**Validation**: After generating, run:\n```bash\nresearchclaw validate --config config.yaml\n```\n\nIf validation fails, explain what went wrong and offer to fix it.\n\n---\n\n## /researchclaw:run — Execute the Pipeline\n\n**Pre-flight checks (always run before starting):**\n\n1. Run `/researchclaw:validate` logic silently\n2. If any check fails, report it and ask the user whether to proceed or fix first\n\n**Start the pipeline:**\n\n```bash\nresearchclaw run --topic \"$ARGUMENTS\" --config config.yaml --auto-approve 2>&1 | tee researchclaw-run.log\n```\n\nIf `$ARGUMENTS` is empty, read the topic from `config.yaml`.\n\n**During execution:**\n- The pipeline runs 23 stages. Each stage produces output in `artifacts/<run-id>/stage-N/`\n- Monitor progress by checking which stage directories exist\n- If the pipeline fails, capture the error output and run `/researchclaw:diagnose` logic automatically\n\n**After completion:**\n- Report which stages succeeded and which failed\n- Show the path to the generated paper (typically `artifacts/<run-id>/stage-17/paper_draft.md` or the final PDF)\n- Show total execution time\n\n---\n\n## /researchclaw:status — Pipeline Status\n\nCheck the current state of a pipeline run:\n\n```bash\nls -la artifacts/ 2>/dev/null | tail -5\n```\n\nFor the most recent run:\n\n1. Find the latest `artifacts/rc-*` directory\n2. Count completed stages: `ls -d artifacts/rc-*/stage-* 2>/dev/null | wc -l`\n3. Check for `pipeline_summary.json` — if it exists, the run is complete\n4. If no summary exists, check which stage was last modified to estimate current progress\n5. Report: `Stage X/23 complete. Current stage: [stage name]. Status: [running/failed/complete]`\n\n**Stage name mapping** (for human-readable output):\n\n| Stage | Name |\n|---|---|\n| 1 | Topic Initialization |\n| 2 | Problem Decomposition |\n| 3 | Literature Search |\n| 4 | Literature Analysis |\n| 5 | Research Direction (Gate) |\n| 6 | Hypothesis Generation |\n| 7 | Experiment Design |\n| 8 | Experiment Plan Review |\n| 9 | Experiment Approval (Gate) |\n| 10 | Code Generation |\n| 11 | Code Review |\n| 12 | Experiment Execution |\n| 13 | Result Collection |\n| 14 | Result Analysis |\n| 15 | Paper Outline |\n| 16 | Section Writing |\n| 17 | Paper Draft |\n| 18 | Peer Review |\n| 19 | Revision |\n| 20 | Final Review (Gate) |\n| 21 | Citation Verification |\n| 22 | Visualization |\n| 23 | Final Export |\n\n---\n\n## /researchclaw:resume — Resume a Failed Run\n\nResume from the last successful stage:\n\n1. Find the latest run directory: `ls -td artifacts/rc-* | head -1`\n2. Find the last completed stage: check `pipeline_summary.json` or find the highest-numbered `stage-*` directory with output files\n3. Determine the next stage name from the stage mapping above\n4. Run:\n   ```bash\n   researchclaw run --config config.yaml --from-stage STAGE_NAME --output <run-dir> --auto-approve 2>&1 | tee researchclaw-resume.log\n   ```\n\n**Known issue (upstream):** The `--from-stage` flag may not work correctly in all versions. If resume fails, inform the user honestly and suggest:\n- Starting a fresh run\n- Manually copying successful stage outputs to a new run directory\n\n---\n\n## /researchclaw:diagnose — Auto-Diagnose Failures\n\nRead the most recent log and error output to identify the problem:\n\n```bash\ntail -100 researchclaw-run.log 2>/dev/null || tail -100 researchclaw-resume.log 2>/dev/null\n```\n\n**Common failure patterns and fixes:**\n\n| Error Pattern | Cause | Fix |\n|---|---|---|\n| `HTTP 401` or `AuthenticationError` | Invalid or expired API key | Check `config.yaml` → `llm.api_key` or the env var |\n| `HTTP 429` or `RateLimitError` | API rate limit hit | Wait 60 seconds and resume, or switch to a different model |\n| `Stage 10` failure | Code generation produced invalid Python | Check `artifacts/*/stage-10/experiment.py` for syntax errors |\n| `Docker` errors | Docker not running or permission denied | Run `docker info` to verify; may need `sudo usermod -aG docker $USER` |\n| `pdflatex` not found | LaTeX not installed | Install with `sudo apt-get install texlive-full` |\n| `ModuleNotFoundError` | Missing Python dependency | Run `pip3 install researchclaw[all]` |\n| `quality_score < threshold` | Quality gate too strict | Edit `config.yaml` → lower `quality.min_score` (default 2.0 is very strict) |\n| `MemoryError` or OOM | Insufficient RAM (needs 32GB+) | Use `simulated` experiment mode or reduce `max_concurrent_stages` |\n| `ConnectionError` to arxiv/semantic_scholar | Network issue | Check internet connectivity; try `curl https://api.semanticscholar.org/graph/v1/paper/search?query=test` |\n| `YAML` parse error in config | Malformed config file | Run `python3 -c \"import yaml; yaml.safe_load(open('config.yaml'))\"` to find the error |\n\nAfter diagnosis, suggest the specific fix. If the fix is automatable (e.g., installing a package), offer to do it with user approval.\n\n---\n\n## /researchclaw:validate — Pre-Run Validation\n\nRun all checks without starting the pipeline:\n\n```bash\nbash \"${CLAUDE_SKILL_DIR}/scripts/check-prereqs.sh\"\n```\n\nThen additionally:\n\n1. **Config syntax**: `python3 -c \"import yaml; yaml.safe_load(open('config.yaml'))\"`\n2. **Config completeness**: Check that `llm.api_key` or `llm.api_key_env` is set, `research.topic` is non-empty\n3. **API connectivity**: Test the LLM endpoint with a minimal request\n4. **Docker health**: `docker info` (if experiment mode is `sandbox`)\n5. **Disk space**: `df -h .` — warn if less than 10 GB free\n6. **Write permissions**: `touch artifacts/.write-test && rm artifacts/.write-test`\n\nReport results as a checklist with pass/fail for each item.\n\n---\n\n## Additional Resources\n\n- For the full pipeline stage reference, see [references/pipeline-stages.md](references/pipeline-stages.md)\n- For configuration field reference, see [references/config-reference.md](references/config-reference.md)\n- For troubleshooting recipes, see [references/troubleshooting.md](references/troubleshooting.md)\n- For Chinese documentation, see [references/README-CN.md](references/README-CN.md)\n\n---\n\n## Principles\n\n1. **Never lie.** If something is broken, say so. If a feature does not exist upstream, do not pretend it does.\n2. **Always test.** Run validation before every pipeline execution. Check results after every action.\n3. **Ask before acting.** Never install packages, modify configs, or start long-running processes without explicit user approval.\n4. **Report honestly.** Show actual error messages, not sanitized summaries. The user needs real information to debug.\n5. **Stay current.** This skill targets AutoResearchClaw v0.3.x. If the upstream version changes significantly, some commands may need updating.","tags":["researchclaw","skill","othmanadi","agent-skills","ai-agents","arxiv","autonomous-agents","autoresearch","claude-code","codex","cursor","gemini-cli"],"capabilities":["skill","source-othmanadi","skill-researchclaw","topic-agent-skills","topic-ai-agents","topic-arxiv","topic-autonomous-agents","topic-autoresearch","topic-claude-code","topic-codex","topic-cursor","topic-gemini-cli","topic-latex","topic-paper-generation","topic-research-automation"],"categories":["researchclaw-skill"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/OthmanAdi/researchclaw-skill/researchclaw","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add OthmanAdi/researchclaw-skill","source_repo":"https://github.com/OthmanAdi/researchclaw-skill","install_from":"skills.sh"}},"qualityScore":"0.456","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 13 github stars · SKILL.md body (11,208 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":"2026-05-18T19:07:05.411Z","embedding":null,"createdAt":"2026-04-23T13:04:15.195Z","updatedAt":"2026-05-18T19:07:05.411Z","lastSeenAt":"2026-05-18T19:07:05.411Z","tsv":"'-1':998 '-100':1107,1112 '-20250514':549 '-4':384 '-5':834 '/aiming-lab/autoresearchclaw),':51 '/aiming-lab/autoresearchclaw.git':407 '/dev/null':832,855,1110,1115 '/graph/v1/paper/search?query=test':1265 '/researchclaw':123,129,141,150,157,168,178,187,196,250,462,690,705,784,815,976,1087,1309 '/scripts/check-prereqs.sh':279,1327 '/stage-':853 '/stage-10/experiment.py':1171 '/stage-17/paper_draft.md':806 '/stage-n':765 '1':214,294,485,490,703,740,840,905,988,1046,1330,1440 '10':636,935,1162,1389 '11':938 '12':941 '13':944 '14':947 '15':950 '16':953 '17':956 '18':959 '19':962 '2':223,313,383,501,555,709,739,831,846,854,908,999,1045,1109,1114,1341,1461 '2.0':1233 '20':592,964 '21':968 '22':971 '23':12,53,757,973 '3':232,328,513,608,635,858,911,1018,1359,1475 '3.11':296,308 '32gb':1243 '4':238,353,532,548,869,914,1029,1370,1494 '401':1126 '429':1143 '4o':543 '5':386,562,590,884,917,1380,1511 '6':580,921,1392 '60':1151 '7':598,924 '8':617,927 '9':591,627,931 'access':439,451 'act':1478 'action':1474 'actual':106,1498 'addit':1329,1409 'advanc':610 'ag':1192 'agent':78 'alway':699,1462 'analysi':916,949 'answer':648 'anthrop':509,544 'anyth':260 'api':450,454,506,514,518,530,1132,1146,1360 'api.semanticscholar.org':1264 'api.semanticscholar.org/graph/v1/paper/search?query=test':1263 'approv':268,583,587,738,933,1044,1308,1493 'apt':363,1205 'apt-get':362,1204 'argument':733,744 'artifact':604,606,764,805,830,1170 'artifacts/.write-test':1396,1398 'artifacts/rc-':844,852,996 'arxiv':639 'arxiv/semantic_scholar':1255 'ask':255,472,489,558,717,1476 'askuserquest':480 'assets/config-template.yaml':655 'authenticationerror':1128 'auto':181,582,737,1043,1090 'auto-approv':581,736,1042 'auto-detect':180 'auto-diagnos':1089 'autom':2 'automat':787,1297 'autonom':14,35,42 'autoresearchclaw':10,48,387,409,1517 'avail':127 'azur':510 'base':245,290 'bash':274,275,395,402,673,729,827,1031,1105,1322,1323 'batch':483,484,554,607 'block':449 'brew':371 'broken':1446 'c':1276,1334 'cannot':345,429 'capabl':91 'captur':778 'cask':373 'caus':1123 'cd':408 'chang':1523 'chat':553 'check':131,159,215,224,272,282,297,316,330,355,388,420,698,712,769,819,859,874,1005,1134,1169,1258,1317,1344,1470 'checklist':1403 'chines':1434 'citat':71,82,969 'claud':276,546,1324 'claude-sonnet':545 'cli':218 'clone':404 'code':567,936,939,1164 'collect':647,946 'command':93,120,121,205,235,1526 'common':185,1116 'complet':166,789,848,868,888,1003,1343 'concret':110 'concurr':1251 'confer':20,65 'conference-grad':19,64 'config':142,144,190,463,676,734,1034,1270,1272,1331,1342,1483 'config.yaml':149,226,470,650,677,735,751,1035,1135,1228,1282,1340 'configur':4,465,1421 'connect':193,1260,1361 'connectionerror':1253 'copi':1078 'correct':1060 'count':847 'curl':1262 'current':230,660,821,882,889,1513 'd':851 'daemon':335,434 'debug':1510 'decomposit':910 'deepseek':511,550,552 'deepseek-chat':551 'default':537,561,578,593,605,625,634,644,1232 'deni':1182 'depend':191,284,1214 'design':926 'detect':182 'determin':1019 'df':1383 'diagnos':179,785,1088,1091 'diagnosi':1288 'differ':1159 'dir':278,1326 'direct':919 'directori':231,600,661,772,845,993,1014,1086 'disk':1381 'display':203 'docker':137,329,331,334,347,433,1175,1177,1184,1193,1371,1373 'document':1435 'download':382 'draft':958 'e':412 'e.g':528,1298 'edit':1227 'empti':746,1358 'endpoint':1365 'env':1140,1351 'environ':522 'error':107,780,1099,1121,1174,1176,1268,1286,1499 'essenti':486 'estim':881 'everi':92,1467,1473 'everyth':424 'execut':5,74,568,572,692,753,813,943,1469 'exist':119,227,773,864,873,1454 'experi':75,556,563,925,928,932,942,1246,1376 'expir':1131 'explain':184,681 'explicit':267,1491 'export':975 'fabric':90 'fail':101,680,713,777,796,980,1066 'failur':186,1092,1117,1163 'faster':327 'fastest':569 'featur':1451 'field':1422 'file':668,1017,1273 'final':809,965,974 'find':841,989,1000,1008,1284 'first':596,725 'fix':111,446,688,724,1120,1124,1292,1295 'flag':1056 'flight':697 'found':1197 'free':499,1391 'fresh':1075 'from-stag':1036,1053 'full':368,1210,1413 'function':98 'gate':584,920,934,967,1224 'gb':385,1390 'generat':18,146,467,649,667,671,802,923,937,1165 'generic':624 'get':266,364,1206 'git':403 'github.com':50,406 'github.com/aiming-lab/autoresearchclaw),':49 'github.com/aiming-lab/autoresearchclaw.git':405 'gpt':542 'gpt-4o':541 'gpu':576 'grade':21,66 'h':1384 'head':997 'health':1372 'help':125,197 'highest':1011 'highest-numb':1010 'hit':1149 'hold':526 'honest':342,377,1070,1496 'honesti':84 'http':1125,1142 'human':586,900 'human-read':899 'hypothesi':922 'iclr':622 'icml':621 'identifi':1102 'import':1277,1335 'info':332,1185,1374 'inform':1067,1508 'initi':907 'instal':133,220,253,259,307,365,372,394,397,411,415,440,1200,1201,1207,1217,1299,1480 'insuffici':1240 'interact':143,464 'internet':1259 'invalid':1129,1167 'invok':199 'issu':448,1050,1257 'item':1408 'iter':629,631 'json':288 'key':455,515,519,531,1133,1137,1347,1350 'known':1049 'l':857 'la':829 'larg':381 'last':175,878,985,1002 'latest':843,991 'latex':67,138,354,441,1198 'less':1387 'level':438 'lie':1442 'limit':1148 'line':211 'linux':369,445 'list':206 'literatur':637,912,915 'llm':453,502,505,1364 'llm.api':1136,1346,1349 'load':1280,1338 'local':512,571 'log':1097 'logic':242,707,786 'long':1487 'long-run':1486 'lower':1229 'ls':828,850,994 'maco':375 'mactex':374 'malform':1271 'manag':312 'mandatori':254 'manual':1077 'map':94,897,1027 'max':628,1250 'may':1057,1188,1527 'memoryerror':1237 'mention':27 'messag':1500 'minim':1368 'miss':249,264,301,359,1212 'mode':564,633,1247,1377 'model':533,535,1160 'modifi':879,1482 'modulenotfounderror':1211 'monitor':6,766 'multi':77 'multi-ag':76 'must':458,488 'name':524,892,896,904,1023,1040 'need':36,1189,1242,1506,1528 'network':1256 'network/firewall':447 'neurip':620,626 'never':113,1441,1479 'new':1084 'next':243,1021 'non':1357 'non-empti':1356 'number':1012 'offer':612,686,1302 'old':304 'one':210 'one-lin':209 'oom':1239 'open':1281,1339 'openai':508,529,540 'option':507,609 'outlin':952 'output':286,599,762,781,902,1016,1041,1081,1100 'packag':140,311,1301,1481 'paper':22,34,68,618,803,951,957 'pars':1267 'pass':425 'pass/fail':1405 'path':799 'pattern':1118,1122 'pdf':810 'pdflatex':356,1195 'peer':79,960 'per':538 'permiss':1181,1394 'pip':139,314 'pip3':317,389,396,410,1216 'pipelin':16,44,55,155,167,172,632,694,728,755,776,817,825,1321,1414,1468 'pipeline_summary.json':861,1006 'plan':929 'polici':85 'pre':696,1312 'pre-flight':695 'pre-run':1311 'prerequisit':135,252,271 'present':261,326 'pretend':114,1458 'principl':1439 'print':233 'problem':116,909,1104 'proceed':722 'process':1489 'produc':62,761,1166 'progress':767,883 'provid':452,503,516,539 'purpos':122 'pyenv':306 'python':136,295,1168,1213 'python3':298,1275,1333 'qualiti':1220,1223 'quality.min':1230 'question':478 'ram':1241 'rate':1147 'ratelimiterror':1145 're':417 're-run':416 'read':747,1093 'readabl':901 'real':70,96,1507 'recent':838,1096 'recip':1429 'reduc':1249 'refer':1416,1423 'references/config-reference.md':1425,1426 'references/pipeline-stages.md':1418,1419 'references/readme-cn.md':1437,1438 'references/troubleshooting.md':1431,1432 'remot':575 'report':104,289,293,714,790,885,1399,1495 'request':1369 'requir':435,616 'research':15,33,43,59,154,491,498,918 'research.topic':1354 'researchclaw':1,28,40,217,222,391,398,674,730,1032,1218 'researchclaw-resume.log':1048,1113 'researchclaw-run.log':742,1108 'resourc':1410 'result':945,948,1400,1471 'resum':169,170,977,978,982,1065,1154 'review':80,930,940,961,966 'revis':963 'rm':1397 'run':151,156,164,195,269,338,418,597,672,691,700,704,731,756,783,826,839,866,981,992,1030,1033,1076,1085,1179,1183,1215,1274,1313,1315,1464,1488 'running/failed/complete':894 'sandbox':73,570,1379 'sandbox-execut':72 'sanit':1502 'save':603 'say':1447 'scholar':641 'score':1221,1231 'script':273,281,421 'search':913 'second':1152 'section':954 'see':1417,1424,1430,1436 'semant':640 'seri':476 'server':577 'set':38,487,557,611,1353 'setup':3,130,251 'show':124,390,663,797,811,1497 'signific':1524 'silent':708 'simul':565,579,1245 'skill':41,46,87,103,277,344,428,1325,1515 'skill-researchclaw' 'skip':585 'smart':560 'someth':100,1444 'sonnet':547 'sourc':401,638 'source-othmanadi' 'space':1382 'specif':1291 'ssh':574 'stage':13,54,177,589,758,760,771,792,849,876,886,890,891,895,903,987,1004,1013,1022,1026,1038,1039,1055,1080,1161,1252,1415 'start':152,346,431,702,726,1073,1319,1485 'state':822 'status':158,161,212,816,818,893 'stay':1512 'step':244 'strict':1226,1236 'subcommand':128,202 'succeed':793 'success':176,986,1079 'sudo':361,443,1190,1203 'suggest':109,239,305,322,360,536,1072,1289 'summari':213,872,1503 'suppli':459 'switch':1156 'syntax':1173,1332 'system':310,352,437 'system-level':436 'tabl':236 'tail':833,1106,1111 'take':57 'target':1516 'td':995 'tee':741,1047 'tell':339 'templat':619,653 'test':1362,1463 'texliv':367,1209 'texlive-ful':366,1208 'text':500 'threshold':1222 'time':814 'topic':60,492,732,749,906 'topic-agent-skills' 'topic-ai-agents' 'topic-arxiv' 'topic-autonomous-agents' 'topic-autoresearch' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-gemini-cli' 'topic-latex' 'topic-paper-generation' 'topic-research-automation' 'total':812 'touch':1395 'tri':1261 'troubleshoot':8,1428 'true':594 'typic':804 'updat':1529 'upstream':97,1051,1455,1521 'use':23,479,651,1244 'user':26,257,341,457,474,665,719,1069,1194,1307,1492,1505 'usermod':1191 'uv':315,320,323 'v0.3.x':1518 'valid':188,189,669,675,679,706,1310,1314,1465 'var':1141 'variabl':523 'verif':83,970 'verifi':423,1187 'version':299,318,321,357,1063,1522 'visual':972 'wait':1150 'want':29,496 'warn':1385 'wc':856 'went':683 'whether':720 'without':200,442,1318,1490 'wizard':145,466 'work':148,469,1059 'wrap':47 'write':31,656,955,1393 'wrong':684 'x/23':887 'yaml':1266,1278,1336 'yaml.safe':1279,1337","prices":[{"id":"f1738983-488b-4d98-8674-febc38f712ad","listingId":"80acb805-fa86-4789-a0cb-b37fb8854e9d","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"OthmanAdi","category":"researchclaw-skill","install_from":"skills.sh"},"createdAt":"2026-04-23T13:04:15.195Z"}],"sources":[{"listingId":"80acb805-fa86-4789-a0cb-b37fb8854e9d","source":"github","sourceId":"OthmanAdi/researchclaw-skill/researchclaw","sourceUrl":"https://github.com/OthmanAdi/researchclaw-skill/tree/main/skills/researchclaw","isPrimary":false,"firstSeenAt":"2026-04-23T13:04:15.195Z","lastSeenAt":"2026-05-18T19:07:05.411Z"}],"details":{"listingId":"80acb805-fa86-4789-a0cb-b37fb8854e9d","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"OthmanAdi","slug":"researchclaw","github":{"repo":"OthmanAdi/researchclaw-skill","stars":13,"topics":["agent-skills","ai-agents","arxiv","autonomous-agents","autoresearch","claude-code","codex","cursor","gemini-cli","latex","paper-generation","research-automation","researchclaw"],"license":"mit","html_url":"https://github.com/OthmanAdi/researchclaw-skill","pushed_at":"2026-04-07T17:07:59Z","description":"Turn your coding agent into a one-command autonomous research paper generator. Wraps AutoResearchClaw's 23-stage pipeline with setup automation, interactive config, error diagnosis, and self-healing hooks.","skill_md_sha":"e794557e41aee24459f029f6132e0728d55e28e6","skill_md_path":"skills/researchclaw/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/OthmanAdi/researchclaw-skill/tree/main/skills/researchclaw"},"layout":"multi","source":"github","category":"researchclaw-skill","frontmatter":{"name":"researchclaw","license":"MIT","description":"Automate setup, configuration, execution, monitoring, and troubleshooting of AutoResearchClaw — the 23-stage autonomous research pipeline that generates conference-grade papers. Use when the user mentions ResearchClaw, wants to write a research paper autonomously, needs to set up or debug the pipeline, or says research paper, autonomous research, or paper generation.","compatibility":"Requires Python 3.11+, Docker, and a LaTeX distribution. Works with Claude Code and compatible coding agents."},"skills_sh_url":"https://skills.sh/OthmanAdi/researchclaw-skill/researchclaw"},"updatedAt":"2026-05-18T19:07:05.411Z"}}