{"id":"e55f068b-4f06-4549-b59b-4e1698e6ea1d","shortId":"PKFm4v","kind":"skill","title":"deepthink","tagline":"Auto-activate when a problem resists quick answers, when initial analysis feels shallow, when debugging hits a wall, when architectural reasoning needs depth, when confidence in a conclusion is low, when analysis feels like it is going in circles, or when the first answer feels t","description":"# Deepthink\n\nStructured extended reasoning with hypothesis tracking and confidence progression. Prevents circular thinking by explicitly tracking what's been explored, what evidence exists, and what confidence level has been reached.\n\nReferences `perspectives` for multi-angle evaluation when confidence is stuck and a fresh frame is needed.\n\n<workflow>\n\n## Workflow\n\n### 1. Frame the Problem\n\nState what you're trying to understand or decide, specifically. Vague framing produces vague investigation.\n\n### 2. Form Initial Hypothesis\n\nYour best guess based on available information. One sentence. Confidence: `exploring`.\n\nDon't skip this step — even a weak hypothesis focuses investigation better than no hypothesis.\n\n### 3. Gather Evidence\n\nRead code, check docs, run tests, trace execution. Record what you find at each step. Every piece of evidence should be evaluated against the current hypothesis.\n\n> **Note:** Sequential-thinking or similar extended reasoning tools can complement complex sub-steps within this workflow — particularly during evidence gathering (step 3) or when evaluating a hypothesis with many interdependencies. Use them to decompose a stuck sub-step without abandoning the overall hypothesis tracking structure.\n\n### 4. Evaluate Against Hypothesis\n\nDoes the evidence support, contradict, or require revision?\n\n- **Supports:** confirms a specific aspect of the hypothesis\n- **Contradicts:** rules out a specific aspect, requiring revision\n- **Requires revision:** the hypothesis was wrong in some way — update it now\n\n### 5. Update Confidence\n\nBased on evidence quality and coverage, update the confidence level:\n\n| Level | Meaning | Action |\n| ----- | ------- | ------ |\n| `exploring` | Just started, no hypothesis yet | Gather initial evidence, form hypothesis |\n| `low` | Have a hypothesis but weak evidence | Seek confirming/disconfirming evidence |\n| `medium` | Evidence supports hypothesis but gaps remain | Fill specific gaps, check edge cases |\n| `high` | Strong evidence, minor uncertainties | Verify the uncertainties aren't critical |\n| `certain` | Conclusive evidence, ready to act | Synthesize findings and present |\n\n**Escalation rule:** If confidence has not increased after 3 investigation steps, stop and reassess. Either the hypothesis is too broad, you're looking in the wrong place, or you need a different tool (`flow:tracer`, `flow:perspectives`).\n\n### 6. Decide: Continue or Conclude\n\n- **Continue:** identify exactly what's missing and loop back to step 3 with a specific target\n- **Conclude:** if confidence is `high` or `certain`, synthesize findings and present\n\nInvestigation is complete when: confidence is `high`/`certain`, all evidence-against items are explained, the hypothesis is a specific actionable conclusion, and unexplored areas are evaluated or ruled out as non-critical.\n\n</workflow>\n\n<guardrails>\n\n### Guardrails\n\n- **Evidence hoarding** — Reading files without updating hypothesis. Every read should confirm, contradict, or refine your current hypothesis. If it doesn't, you're reading the wrong thing.\n- **Premature conclusion** — Presenting hypothesis as conclusion before gathering evidence. A hypothesis is not a conclusion. Don't present it as one.\n- **Permanent exploring** — Staying at `exploring` after 5+ checks without narrowing. Formulate a hypothesis and commit to testing it.\n- **Circular investigation** — Revisiting same evidence without new framing. If you're back where you started, the hypothesis needs to change, not the evidence gathering.\n\n</guardrails>\n\n<validation>\n\n### Validation Checkpoint\n\nBefore presenting the conclusion, verify:\n\n- [ ] Hypothesis was updated at least once during investigation\n- [ ] Evidence for AND against was recorded\n- [ ] Confidence level progression is justified by evidence\n- [ ] Investigation concluded with a specific, actionable finding\n\n</validation>\n\n<example>\n\n## Example\n\n**Debugging:** \"Tests pass locally but fail in CI.\"\n\n- **Hypothesis 1:** \"Flaky test — timing issue\" (confidence: `exploring`)\n- **Evidence:** CI logs show deterministic failure on same test. Rules out flakiness. → Revise.\n- **Hypothesis 2:** \"Environment difference — missing env var\" (confidence: `low`)\n- **Evidence:** Compared CI env vs local. Found `DATABASE_URL` uses different host. Test creates real DB connection. → confidence: `medium`.\n- **Hypothesis 3:** \"CI database not seeded\" (confidence: `medium`)\n- **Evidence:** CI setup script skips seed step for test DB. Local has leftover seed data. → confidence: `high`.\n- **Conclusion:** CI test DB is empty. Fix: add seed step to CI pipeline before tests.\n\n</example>\n\n## Complements\n\n- **systematic-debugging** — deepthink provides structured hypothesis evolution when debugging stalls after 3+ iterations\n- **brainstorming** — deepthink enables deeper analysis during the design phase when approaches need thorough evaluation\n- **flow-plan** — deepthink supports thorough requirement analysis for complex decomposition decisions\n\n## References Index\n\n- **[Reasoning Strategy](references/reasoning-strategy.md)** — When to use deepthink, the 6-step workflow, and anti-patterns to avoid\n- **[Confidence Tracking](references/confidence-tracking.md)** — Confidence levels table, what to track at each step, escalation rule, and completion criteria","tags":["deepthink","flow","cofin","agent-skills","ai-agents","beads","claude-code","codex","cursor","developer-tools","gemini-cli","opencode"],"capabilities":["skill","source-cofin","skill-deepthink","topic-agent-skills","topic-ai-agents","topic-beads","topic-claude-code","topic-codex","topic-cursor","topic-developer-tools","topic-gemini-cli","topic-opencode","topic-plugin","topic-slash-commands","topic-spec-driven-development"],"categories":["flow"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/cofin/flow/deepthink","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add cofin/flow","source_repo":"https://github.com/cofin/flow","install_from":"skills.sh"}},"qualityScore":"0.455","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 11 github stars · SKILL.md body (5,308 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":"2026-04-24T01:03:25.920Z","embedding":null,"createdAt":"2026-04-23T13:03:58.645Z","updatedAt":"2026-04-24T01:03:25.920Z","lastSeenAt":"2026-04-24T01:03:25.920Z","tsv":"'1':97,573 '2':116,594 '3':146,198,342,387,622,674 '4':223 '5':263,492 '6':371,712 'abandon':217 'act':329 'action':278,423,561 'activ':4 'add':653 'analysi':13,34,680,697 'angl':84 'answer':10,46 'anti':717 'anti-pattern':716 'approach':686 'architectur':22 'area':427 'aren':321 'aspect':239,248 'auto':3 'auto-activ':2 'avail':125 'avoid':720 'back':384,515 'base':123,266 'best':121 'better':142 'brainstorm':676 'broad':353 'case':312 'certain':324,398,410 'chang':523 'check':151,310,493 'checkpoint':529 'ci':571,581,604,623,630,647,657 'circl':41 'circular':60,504 'code':150 'commit':500 'compar':603 'complement':185,661 'complet':405,736 'complex':186,699 'conclud':375,392,557 'conclus':30,325,424,466,470,479,533,646 'confid':27,57,74,87,129,265,274,337,394,407,549,578,600,619,627,644,721,724 'confirm':236,448 'confirming/disconfirming':298 'connect':618 'continu':373,376 'contradict':231,243,449 'coverag':271 'creat':615 'criteria':737 'critic':323,436 'current':173,453 'data':643 'databas':609,624 'db':617,638,649 'debug':17,564,664,671 'decid':109,372 'decis':701 'decompos':210 'decomposit':700 'deeper':679 'deepthink':1,49,665,677,693,710 'depth':25 'design':683 'determinist':584 'differ':365,596,612 'doc':152 'doesn':457 'edg':311 'either':348 'empti':651 'enabl':678 'env':598,605 'environ':595 'escal':334,733 'evalu':85,170,201,224,429,689 'even':136 'everi':164,445 'evid':70,148,167,195,229,268,287,296,299,301,315,326,413,438,473,508,526,543,555,580,602,629 'evidence-against':412 'evolut':669 'exact':378 'exampl':563 'execut':156 'exist':71 'explain':417 'explicit':63 'explor':68,130,279,487,490,579 'extend':51,181 'fail':569 'failur':585 'feel':14,35,47 'file':441 'fill':307 'find':160,331,400,562 'first':45 'fix':652 'flaki':574,591 'flow':367,369,691 'flow-plan':690 'focus':140 'form':117,288 'formul':496 'found':608 'frame':93,98,112,511 'fresh':92 'gap':305,309 'gather':147,196,285,472,527 'go':39 'guardrail':437 'guess':122 'high':313,396,409,645 'hit':18 'hoard':439 'host':613 'hypothesi':54,119,139,145,174,203,220,226,242,254,283,289,293,303,350,419,444,454,468,475,498,520,535,572,593,621,668 'identifi':377 'increas':340 'index':703 'inform':126 'initi':12,118,286 'interdepend':206 'investig':115,141,343,403,505,542,556 'issu':577 'item':415 'iter':675 'justifi':553 'least':539 'leftov':641 'level':75,275,276,550,725 'like':36 'local':567,607,639 'log':582 'look':356 'loop':383 'low':32,290,601 'mani':205 'mean':277 'medium':300,620,628 'minor':316 'miss':381,597 'multi':83 'multi-angl':82 'narrow':495 'need':24,95,363,521,687 'new':510 'non':435 'non-crit':434 'note':175 'one':127,485 'overal':219 'particular':193 'pass':566 'pattern':718 'perman':486 'perspect':80,370 'phase':684 'piec':165 'pipelin':658 'place':360 'plan':692 'prematur':465 'present':333,402,467,482,531 'prevent':59 'problem':7,100 'produc':113 'progress':58,551 'provid':666 'qualiti':269 'quick':9 're':104,355,460,514 'reach':78 'read':149,440,446,461 'readi':327 'real':616 'reason':23,52,182,704 'reassess':347 'record':157,548 'refer':79,702 'references/confidence-tracking.md':723 'references/reasoning-strategy.md':706 'refin':451 'remain':306 'requir':233,249,251,696 'resist':8 'revis':234,250,252,592 'revisit':506 'rule':244,335,431,589,734 'run':153 'script':632 'seed':626,634,642,654 'seek':297 'sentenc':128 'sequenti':177 'sequential-think':176 'setup':631 'shallow':15 'show':583 'similar':180 'skill' 'skill-deepthink' 'skip':133,633 'source-cofin' 'specif':110,238,247,308,390,422,560 'stall':672 'start':281,518 'state':101 'stay':488 'step':135,163,189,197,215,344,386,635,655,713,732 'stop':345 'strategi':705 'strong':314 'structur':50,222,667 'stuck':89,212 'sub':188,214 'sub-step':187,213 'support':230,235,302,694 'synthes':330,399 'systemat':663 'systematic-debug':662 'tabl':726 'target':391 'test':154,502,565,575,588,614,637,648,660 'thing':464 'think':61,178 'thorough':688,695 'time':576 'tool':183,366 'topic-agent-skills' 'topic-ai-agents' 'topic-beads' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-developer-tools' 'topic-gemini-cli' 'topic-opencode' 'topic-plugin' 'topic-slash-commands' 'topic-spec-driven-development' 'trace':155 'tracer':368 'track':55,64,221,722,729 'tri':105 'uncertainti':317,320 'understand':107 'unexplor':426 'updat':260,264,272,443,537 'url':610 'use':207,611,709 'vagu':111,114 'valid':528 'var':599 'verifi':318,534 'vs':606 'wall':20 'way':259 'weak':138,295 'within':190 'without':216,442,494,509 'workflow':96,192,714 'wrong':256,359,463 'yet':284","prices":[{"id":"92e3029d-6be0-4941-ae61-f4b1023a4daf","listingId":"e55f068b-4f06-4549-b59b-4e1698e6ea1d","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"cofin","category":"flow","install_from":"skills.sh"},"createdAt":"2026-04-23T13:03:58.645Z"}],"sources":[{"listingId":"e55f068b-4f06-4549-b59b-4e1698e6ea1d","source":"github","sourceId":"cofin/flow/deepthink","sourceUrl":"https://github.com/cofin/flow/tree/main/skills/deepthink","isPrimary":false,"firstSeenAt":"2026-04-23T13:03:58.645Z","lastSeenAt":"2026-04-24T01:03:25.920Z"}],"details":{"listingId":"e55f068b-4f06-4549-b59b-4e1698e6ea1d","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"cofin","slug":"deepthink","github":{"repo":"cofin/flow","stars":11,"topics":["agent-skills","ai-agents","beads","claude-code","codex","context-driven-development","cursor","developer-tools","gemini-cli","opencode","plugin","slash-commands","spec-driven-development","subagents","tdd","workflow"],"license":"apache-2.0","html_url":"https://github.com/cofin/flow","pushed_at":"2026-04-19T23:22:27Z","description":"Context-Driven Development toolkit for AI agents — spec-first planning, TDD workflow, and Beads integration.","skill_md_sha":"9499e28b671ac2cb694bf2ddb41f0333a52b1cc8","skill_md_path":"skills/deepthink/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/cofin/flow/tree/main/skills/deepthink"},"layout":"multi","source":"github","category":"flow","frontmatter":{"name":"deepthink","description":"Auto-activate when a problem resists quick answers, when initial analysis feels shallow, when debugging hits a wall, when architectural reasoning needs depth, when confidence in a conclusion is low, when analysis feels like it is going in circles, or when the first answer feels too easy for a hard problem. Produces a confidence-tracked investigation with explicit hypothesis evolution, evidence log, and a specific actionable conclusion. Use when: complex reasoning needed, hypothesis testing required, going in circles on a problem, need to track what has been explored vs what remains, analysis feels shallow, confidence is low, or when debugging hits a wall. Not for clear questions with obvious answers, simple lookups, or problems that yield to direct investigation."},"skills_sh_url":"https://skills.sh/cofin/flow/deepthink"},"updatedAt":"2026-04-24T01:03:25.920Z"}}