{"id":"00daae31-66c5-47f1-bca2-0f00bd76d814","shortId":"v8cjtP","kind":"skill","title":"re","tagline":"Explicit extra-research mode. Use only when the user says `/re` or clearly asks for a research-heavy pass before coding. This skill should bias Codex toward more source-checking and justification without replacing its normal orchestration.","description":"# Re\n\nUse this as a light override, not a rigid workflow. Keep Codex's default orchestration and only add extra diligence where it matters.\n\n## Defaults\n\n- Inspect the local codebase first.\n- Do research in 3 passes when the task is genuinely research-heavy:\n  1. Plan 3-6 sub-questions.\n  2. Retrieve sources for each sub-question and follow 1-2 second-order leads when useful.\n  3. Synthesize only after resolving conflicts and gaps that could change the conclusion.\n- Use Context7 first for version-sensitive library or framework behavior.\n- Use native `web` first for current information.\n- Use Jina only when native `web` is not enough for long pages, PDFs, or parallel page reads.\n- Only cite sources retrieved in the current workflow, and label any inference that is not directly supported by those sources.\n- If sources conflict, state the conflict explicitly instead of averaging them into one answer.\n- If a search result is empty, partial, or suspiciously narrow, retry with a broader query, alternate wording, or a second source before concluding there is no answer.\n- Compare options only when there is a real tradeoff.\n- Implement once the decision is clear.\n- Run the smallest relevant verification commands before finishing.\n\n## Avoid\n\n- Do not force phases.\n- Do not produce long research reports unless the user asked for them or the task materially benefits.\n- Do not ask extra questions if local context is already enough.\n- Do not delegate work just because this skill is active.\n\n## Large Tasks\n\nFor long tasks, optional scratch notes can live in `/tmp/re-research/<slug>/`.\n\nIf useful, keep a short `decisions.md` with:\n- key findings\n- rejected options\n- remaining risks\n- pending verification\n\n## Finish\n\nKeep the final response compressed:\n- decision\n- source-backed justification\n- key sources or citations when they materially matter\n- code or config changed\n- tests run\n- remaining unknowns","tags":["dgk","gpt","dgk-dev","agent-skills","cli","codex","developer-tools","mcp","openai-codex"],"capabilities":["skill","source-dgk-dev","skill-re","topic-agent-skills","topic-cli","topic-codex","topic-developer-tools","topic-mcp","topic-openai-codex"],"categories":["dgk-gpt"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/dgk-dev/dgk-gpt/re","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add dgk-dev/dgk-gpt","source_repo":"https://github.com/dgk-dev/dgk-gpt","install_from":"skills.sh"}},"qualityScore":"0.472","qualityRationale":"deterministic score 0.47 from registry signals: · indexed on github topic:agent-skills · 45 github stars · SKILL.md body (1,919 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":"2026-05-02T00:57:07.773Z","embedding":null,"createdAt":"2026-04-18T22:17:59.812Z","updatedAt":"2026-05-02T00:57:07.773Z","lastSeenAt":"2026-05-02T00:57:07.773Z","tsv":"'-2':103 '-6':88 '/re':13 '/tmp/re-research':296 '1':85,102 '2':92 '3':75,87,110 'activ':284 'add':60 'alreadi':273 'altern':207 'answer':191,218 'ask':16,256,266 'averag':187 'avoid':242 'back':321 'behavior':133 'benefit':263 'bias':28 'broader':205 'chang':120,334 'check':34 'citat':326 'cite':159 'clear':15,233 'code':24,331 'codebas':70 'codex':29,54 'command':239 'compar':219 'compress':317 'conclud':214 'conclus':122 'config':333 'conflict':115,180,183 'context':271 'context7':124 'could':119 'current':139,164 'decis':231,318 'decisions.md':302 'default':56,66 'deleg':277 'dilig':62 'direct':173 'empti':197 'enough':149,274 'explicit':2,184 'extra':4,61,267 'extra-research':3 'final':315 'find':305 'finish':241,312 'first':71,125,137 'follow':101 'forc':245 'framework':132 'gap':117 'genuin':81 'heavi':21,84 'implement':228 'infer':169 'inform':140 'inspect':67 'instead':185 'jina':142 'justif':36,322 'keep':53,299,313 'key':304,323 'label':167 'larg':285 'lead':107 'librari':130 'light':47 'live':294 'local':69,270 'long':151,250,288 'materi':262,329 'matter':65,330 'mode':6 'narrow':201 'nativ':135,145 'normal':40 'note':292 'one':190 'option':220,290,307 'orchestr':41,57 'order':106 'overrid':48 'page':152,156 'parallel':155 'partial':198 'pass':22,76 'pdfs':153 'pend':310 'phase':246 'plan':86 'produc':249 'queri':206 'question':91,99,268 're':1,42 'read':157 'real':226 'reject':306 'relev':237 'remain':308,337 'replac':38 'report':252 'research':5,20,73,83,251 'research-heavi':19,82 'resolv':114 'respons':316 'result':195 'retri':202 'retriev':93,161 'rigid':51 'risk':309 'run':234,336 'say':12 'scratch':291 'search':194 'second':105,211 'second-ord':104 'sensit':129 'short':301 'skill':26,282 'skill-re' 'smallest':236 'sourc':33,94,160,177,179,212,320,324 'source-back':319 'source-check':32 'source-dgk-dev' 'state':181 'sub':90,98 'sub-quest':89,97 'support':174 'suspici':200 'synthes':111 'task':79,261,286,289 'test':335 'topic-agent-skills' 'topic-cli' 'topic-codex' 'topic-developer-tools' 'topic-mcp' 'topic-openai-codex' 'toward':30 'tradeoff':227 'unknown':338 'unless':253 'use':7,43,109,123,134,141,298 'user':11,255 'verif':238,311 'version':128 'version-sensit':127 'web':136,146 'without':37 'word':208 'work':278 'workflow':52,165","prices":[{"id":"99dae35c-3db5-480e-8eee-d1243cbb9538","listingId":"00daae31-66c5-47f1-bca2-0f00bd76d814","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"dgk-dev","category":"dgk-gpt","install_from":"skills.sh"},"createdAt":"2026-04-18T22:17:59.812Z"}],"sources":[{"listingId":"00daae31-66c5-47f1-bca2-0f00bd76d814","source":"github","sourceId":"dgk-dev/dgk-gpt/re","sourceUrl":"https://github.com/dgk-dev/dgk-gpt/tree/main/skills/re","isPrimary":false,"firstSeenAt":"2026-04-18T22:17:59.812Z","lastSeenAt":"2026-05-02T00:57:07.773Z"}],"details":{"listingId":"00daae31-66c5-47f1-bca2-0f00bd76d814","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"dgk-dev","slug":"re","github":{"repo":"dgk-dev/dgk-gpt","stars":45,"topics":["agent-skills","cli","codex","developer-tools","mcp","openai-codex"],"license":"mit","html_url":"https://github.com/dgk-dev/dgk-gpt","pushed_at":"2026-03-13T04:37:05Z","description":"Safe Codex CLI setup installer with skills, AGENTS.md, profiles, and MCP defaults","skill_md_sha":"47e5323605ba43d64ce07012e82554b0594bfb0b","skill_md_path":"skills/re/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/dgk-dev/dgk-gpt/tree/main/skills/re"},"layout":"multi","source":"github","category":"dgk-gpt","frontmatter":{"name":"re","description":"Explicit extra-research mode. Use only when the user says `/re` or clearly asks for a research-heavy pass before coding. This skill should bias Codex toward more source-checking and justification without replacing its normal orchestration."},"skills_sh_url":"https://skills.sh/dgk-dev/dgk-gpt/re"},"updatedAt":"2026-05-02T00:57:07.773Z"}}