[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QEWXD4AXRBMW5PZZ313CS9":3,"skill-same:01M6QEWXD4AXRBMW5PZZ313CS9":197},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":64,"commitSha":65,"skillDirectory":66,"forksCount":14,"repositoryHtmlUrl":67,"repositoryHomepageUrl":68,"ownerHtmlUrl":69,"ownerBlogUrl":70,"ownerDescription":71,"updatedAt":72,"install":73,"resources":86},"01M6QEWXD4AXRBMW5PZZ313CS9","hypothesis-generation",null,"Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"hypothesis","hypothesis generation","generation","only","candidate","bounded","claims","scientific","predictions","local","deterministic","ready","design","markdown","credentials","analysis","network","library","packages","image","2026-11-10 10:12:30",false,"---\nname: hypothesis-generation\ndescription: Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.\nlicense: MIT\ncompatibility: Python 3.11+ standard library. Bundled CLIs are deterministic and local-only; they accept bounded JSON, CSV, or Markdown and require no network, credentials, models, image services, or external packages.\nmetadata:\n  version: '2.2'\n  category: ideation-and-design\n  maintainer: Kalaris Labs\n  last-reviewed: '2026-07-23'\n  tags: hypothesis generation, research questions, preregistration, study design, scientific method\n---\n\n# Scientific Hypothesis Generation\n\nTurn an observation into a transparent set of candidate explanations and tests. A hypothesis is a proposal to be challenged, not a finding, fact, diagnosis, or recommendation.\n\n## Non-negotiable boundaries\n\nBefore using unpublished, sensitive, controlled, personal, proprietary, export-controlled, or security-relevant material:\n\n1. Confirm authorization and the applicable institutional, funder, publisher, data-use, privacy, and AI policies.\n2. Keep the material local unless an authorized human explicitly approves a named external destination and data scope.\n3. Minimize inputs. Do not place sensitive or unpublished data in web searches or external AI systems without authorization.\n4. Stop at the appropriate human, animal, biosafety, dual-use, data-governance, or regulatory gate.\n\nNever:\n\n- present a hypothesis, mechanism, causal effect, citation, or apparent pattern as established evidence;\n- claim novelty because a quick search found nothing;\n- infer causation from association, temporal order alone, predictive accuracy, or model output;\n- supply patient-specific diagnosis, treatment, dose, prognosis, or other clinical advice;\n- provide harmful experimental optimization or operational detail for pathogens, toxins, weapons, evasion, or other misuse;\n- bypass IRB\u002FREC, IACUC, IBC, biosafety, dual-use, privacy, legal, or regulatory review;\n- fabricate sources, identifiers, search coverage, data, results, approvals, or preregistration;\n- automatically score, rank, select, accept, or reject scientific hypotheses.\n\nIf a request crosses a safety gate, produce only a high-level risk\u002Foversight note and route it to the qualified local authority. Do not continue with operational detail.\n\n## Keep the objects distinct\n\n| Object | Meaning |\n|---|---|\n| **Observation** | What was measured, noticed, or reported, with provenance and uncertainty |\n| **Research question** | The answerable question that defines scope |\n| **Hypothesis** | A candidate explanatory or relational proposition |\n| **Mechanism** | The proposed process connecting conditions to an outcome |\n| **Causal estimand** | The precisely defined causal contrast to estimate |\n| **Prediction** | An observable implication derived before checking the target result |\n| **Alternative explanation** | A rival account, including bias or non-causal explanations |\n| **Null hypothesis** | A specified no-effect\u002Fno-difference model used by an analysis |\n| **Negative control** | A control expected not to operate through the proposed mechanism |\n| **Operationalization** | How a construct becomes a variable, measurement, intervention, or category |\n| **Analysis plan** | Prespecified transformations, models, contrasts, uncertainty, and decision rules |\n| **Evidence** | Observations or sources that bear on a claim; never the claim itself |\n\nDo not collapse these labels. A mechanistic story is not a prediction; a prediction is not evidence; rejection of one null does not prove a mechanism; support for one candidate does not eliminate unconsidered rivals.\n\n## Workflow\n\n### 1. Run the scope and safety gate\n\nRecord:\n\n- accountable human owner and intended use;\n- data sensitivity, authorization, retention, and permitted processing;\n- affected people, animals, ecosystems, communities, or security interests;\n- required ethics, feasibility, biosafety, dual-use, and regulatory reviews;\n- unresolved blocks and domain expertise needed.\n\nNo script approval is an ethics, safety, regulatory, or scientific approval.\n\n### 2. Freeze the observation\n\nWrite the observation before interpretation:\n\n- measurement or source;\n- population, system, place, and time;\n- unit of observation and unit of analysis;\n- uncertainty, missingness, exclusions, and preprocessing;\n- whether the pattern was expected, exploratory, or selected after viewing results.\n\nUse “reported,” “observed,” or “associated,” not causal language, unless a causal design and estimand justify it.\n\n### 3. Frame the research question\n\nChoose a framework only when it fits:\n\n- **PICO\u002FPICOT** for intervention\u002Feffectiveness questions: population, intervention, comparator, outcome, and optionally time.\n- **PECO** for exposure questions.\n- **Population–index test–reference standard–target condition** for diagnostic accuracy.\n- **Population–prognostic factor–outcome–time** for prognosis.\n- A domain-specific construct–context–outcome frame for qualitative, descriptive, mechanistic, or theoretical work.\n\nPICO is not a universal template. Define stakeholders, context, boundaries, feasibility, and what answer would change knowledge or practice. FINER is a question-refinement mnemonic—Feasible, Interesting, Novel, Ethical, Relevant—not a scoring system. Treat “Novel” as unresolved until a documented, fit-for-purpose search and expert review support it.\n\n### 4. Establish a dated evidence boundary\n\nSearch before making literature-dependent statements. Prefer primary research, official policies, primary methods papers, current reporting guidelines, and systematic reviews used for orientation.\n\nRecord:\n\n- search date and cutoff;\n- databases\u002Findexes, queries, filters, and screening boundary;\n- included and excluded source types;\n- sources supporting, challenging, or contextualizing each claim;\n- known access, language, database, and time limitations.\n\nA search can establish what was searched, not universal absence. Say “not located within the documented search boundary,” never “no prior work exists.” Use `assets\u002Fsearch_boundary_template.json`, `assets\u002Fevidence_ledger_template.csv`, and `references\u002Fliterature_search_strategies.md`.\n\n### 5. Generate rivals before choosing tests\n\nCreate multiple candidates from genuinely different explanatory classes when plausible:\n\n- proposed mechanism;\n- measurement or processing artifact;\n- confounding or common cause;\n- selection or attrition;\n- conditioning on a collider;\n- reverse causation;\n- temporal, contextual, or boundary-condition differences;\n- stochastic variation;\n- competing mechanisms at another scale.\n\nGenerate an initial rival set independently before AI-assisted expansion to reduce anchoring and homogenization. Do not force a fixed number or false symmetry. Keep every candidate labeled `candidate`.\n\nPlatt’s strong-inference pattern motivates alternative hypotheses and crucial tests, but failed alternatives do not make the survivor true. Unknown alternatives, auxiliary assumptions, measurement error, and mixed mechanisms remain possible.\n\n### 6. Declare the claim type and estimand\n\nClassify each target as:\n\n- descriptive;\n- associational;\n- predictive;\n- causal;\n- mechanistic.\n\nFor a causal target, define before analysis:\n\n- target population or system;\n- intervention\u002Fexposure and comparator;\n- outcome and time horizon;\n- population-level summary;\n- treatment versions and intercurrent-event handling where relevant;\n- identification assumptions and target-trial\u002Fdesign analogue.\n\nDocument confounding, selection, collider, measurement, and reverse-causation risks separately. An observational causal estimate remains assumption-dependent. Use `references\u002Fcausal_inference_and_claims.md`.\n\n### 7. Derive discriminating predictions\n\nFor every candidate:\n\n1. State conditions and boundary conditions.\n2. Name the observable and measurement.\n3. State the expected pattern and uncertainty.\n4. State a result incompatible with the candidate under declared assumptions.\n5. Contrast the expected result with at least one rival.\n6. Define indeterminate outcomes and what would be learned from them.\n\nPrefer tests where rivals predict meaningfully different outcomes. Add positive, procedural, and negative controls when scientifically appropriate. A negative control must be incapable of operating through the target mechanism while sharing relevant bias pathways; it is not a decorative untreated group.\n\nUse `assets\u002Fprediction_rival_matrix_template.csv` and `assets\u002Ffalsification_controls_template.json`.\n\n### 8. Operationalize and validate measurement\n\nFor every construct record:\n\n- variable role and operational definition;\n- population\u002Fsystem, unit, timing, and conditions;\n- instrument\u002Fmethod, calibration, quality control, and masking;\n- reliability\u002Frepeatability;\n- validity evidence and applicability;\n- missingness, detection limits, transformations, cut points, and their rationales;\n- measurement invariance or cross-group comparability when relevant;\n- foreseeable measurement bias and limitations.\n\nDo not treat a convenient proxy as the construct itself. Validate with:\n\n```bash\npython3 scripts\u002Fcheck_operationalization.py local-operationalization.json\n```\n\n### 9. Match design and analysis to the claim\n\nSpecify:\n\n- sampling, experimental unit, allocation, randomization, masking, and controls;\n- inclusion\u002Fexclusion and stopping rules;\n- sample-size, precision, or information rationale based on declared assumptions;\n- outcomes, contrasts, estimands, models, effect measures, and uncertainty;\n- missing-data and intercurrent-event handling;\n- multiplicity across outcomes, models, subgroups, looks, and hypotheses;\n- assumptions, diagnostics, robustness, and sensitivity analyses;\n- replication or independent validation plan;\n- what is confirmatory versus exploratory.\n\nDo not use universal sample-size minima. Do not interpret a thresholded p-value as the probability a hypothesis is true or as effect importance. See `references\u002Fexperimental_design_patterns.md`.\n\nFor intervention trials, use the current SPIRIT 2025 protocol guidance and CONSORT 2025 reporting guidance where applicable. These improve completeness; they do not certify design quality, ethics, or regulatory compliance.\n\n### 10. Prevent HARKing and expose deviations\n\nBefore accessing the target outcomes, timestamp the question, candidates, predictions, outcomes, exclusions, transformations, analysis, multiplicity, missing-data plan, and stopping rule when feasible.\n\nAfterward:\n\n- label data-dependent ideas and analyses exploratory;\n- preserve and report planned analyses;\n- list deviations with date, rationale, who decided, and expected impact;\n- never rewrite an observed pattern as an a priori prediction.\n\nPreregistration is a transparent plan, not a ban on adaptation. Registered Reports add results-blind peer review and in-principle acceptance under journal policy. See `references\u002Fpreregistration_and_open_science.md`.\n\n### 11. Plan replication and updating\n\nDistinguish:\n\n- **reproducibility:** consistent computational results from the same data\u002Fcode\u002Fconditions;\n- **replicability:** consistency across studies collecting new data for the same question.\n\nPreserve provenance, versions, code, materials, and decision logs when sharing is authorized. Plan independent replication or transport tests across relevant boundaries. Update candidate status when contrary, null, or replication evidence arrives; do not hide negative results.\n\n### 12. Apply human accountability\n\nThe accountable human must verify:\n\n- every citation and source-to-claim link;\n- domain plausibility and measurement validity;\n- causal assumptions and statistical design;\n- ethics, feasibility, safety, privacy, and regulatory status;\n- all AI-assisted text, ideas, and citations;\n- whether broader expertise or community input is required.\n\nAI can confabulate citations, anchor reasoning, and homogenize candidate sets. Record permitted AI use and material influence. Keep independent human ideation and rival generation in the process.\n\n## Local tool index\n\nAll CLIs are bounded, dependency-free, local, deterministic, and non-scoring:\n\n| Task | Asset | Command |\n|---|---|---|\n| Hypothesis-record schema | `assets\u002Fhypothesis_record_template.json` | `python3 scripts\u002Fvalidate_hypothesis_schema.py record.json` |\n| Measurement checklist | `assets\u002Foperationalization_template.json` | `python3 scripts\u002Fcheck_operationalization.py checklist.json` |\n| Prediction\u002Frival matrix | `assets\u002Fprediction_rival_matrix_template.csv` | `python3 scripts\u002Fvalidate_prediction_matrix.py matrix.csv` |\n| Claim-language lint | Annotated Markdown | `python3 scripts\u002Flint_causal_claims.py draft.md` |\n| Falsification\u002Fcontrols | `assets\u002Ffalsification_controls_template.json` | `python3 scripts\u002Fcheck_falsification_controls.py controls.json` |\n| Evidence\u002Fsource audit | `assets\u002Fevidence_ledger_template.csv` + `assets\u002Fsearch_boundary_template.json` | `python3 scripts\u002Faudit_evidence_ledger.py ledger.csv boundary.json` |\n| Preregistration scaffold | `assets\u002Fpreregistration_scaffold_template.md` | `python3 scripts\u002Fgenerate_preregistration_scaffold.py record.json -o preregistration.md` |\n\nExit codes are `0` for structurally valid output, `1` for completed validation with errors, and `2` for malformed\u002Funsafe input. Reports validate declarations and internal consistency only; they do not verify scientific truth or choose a hypothesis. Full schemas are in `references\u002Ftool_reference.md`.\n\n## References\n\n- `references\u002Fconcepts_and_workflow.md` — object model, strong inference, uncertainty, and candidate lifecycle\n- `references\u002Fhypothesis_quality_criteria.md` — non-scoring human review criteria\n- `references\u002Fliterature_search_strategies.md` — traceable, bounded evidence search\n- `references\u002Fcausal_inference_and_claims.md` — estimands and causal-bias risks\n- `references\u002Fexperimental_design_patterns.md` — design, controls, measurement, multiplicity, and replication\n- `references\u002Fpreregistration_and_open_science.md` — preregistration, Registered Reports, deviations, and open science\n- `references\u002Fethics_safety_and_ai.md` — oversight gates, dual use, data handling, and responsible AI\n- `references\u002Ftool_reference.md` — CLI schemas, limits, and examples\n- `references\u002Fsource_ledger.md` — dated authoritative source notes\n- `references\u002Fsecurity_validation.md` — baseline findings and validation record\n\nThe bundled source ledger is `assets\u002Fsource_ledger.csv`, verified through **2026-07-23**. Recheck time-sensitive policy and guidance before a later or jurisdiction-specific use.\n\n## Related skills\n\n- `pyvene-interventions`: Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework.\n- `scientific-brainstorming`: Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evalua…\n","# Scientific Hypothesis Generation\n\nTurn an observation into a transparent set of candidate explanations and tests. A hypothesis is a proposal to be challenged, not a finding, fact, diagnosis, or recommendation.\n\n## Non-negotiable boundaries\n\nBefore using unpublished, sensitive, controlled, personal, proprietary, export-controlled, or security-relevant material:\n\n1. Confirm authorization and the applicable institutional, funder, publisher, data-use, privacy, and AI policies.\n2. Keep the material local unless an authorized human explicitly approves a named external destination and data scope.\n3. Minimize inputs. Do not place sensitive or unpublished data in web searches or external AI systems without authorization.\n4. Stop at the appropriate human, animal, biosafety, dual-use, data-governance, or regulatory gate.\n\nNever:\n\n- present a hypothesis, mechanism, causal effect, citation, or apparent pattern as established evidence;\n- claim novelty because a quick search found nothing;\n- infer causation from association, temporal order alone, predictive accuracy, or model output;\n- supply patient-specific diagnosis, treatment, dose, prognosis, or other clinical advice;\n- provide harmful experimental optimization or operational detail for pathogens, toxins, weapons, evasion, or other misuse;\n- bypass IRB\u002FREC, IACUC, IBC, biosafety, dual-use, privacy, legal, or regulatory review;\n- fabricate sources, identifiers, search coverage, data, results, approvals, or preregistration;\n- automatically score, rank, select, accept, or reject scientific hypotheses.\n\nIf a request crosses a safety gate, produce only a high-level risk\u002Foversight note and route it to the qualified local authority. Do not continue with operational detail.\n\n## Keep the objects distinct\n\n| Object | Meaning |\n|---|---|\n| **Observation** | What was measured, noticed, or reported, with provenance and uncertainty |\n| **Research question** | The answerable question that defines scope |\n| **Hypothesis** | A candidate explanatory or relational proposition |\n| **Mechanism** | The proposed process connecting conditions to an outcome |\n| **Causal estimand** | The precisely defined causal contrast to estimate |\n| **Prediction** | An observable implication derived before checking the target result |\n| **Alternative explanation** | A rival account, including bias or non-causal explanations |\n| **Null hypothesis** | A specified no-effect\u002Fno-difference model used by an analysis |\n| **Negative control** | A control expected not to operate through the proposed mechanism |\n| **Operationalization** | How a construct becomes a variable, measurement, intervention, or category |\n| **Analysis plan** | Prespecified transformations, models, contrasts, uncertainty, and decision rules |\n| **Evidence** | Observations or sources that bear on a claim; never the claim itself |\n\nDo not collapse these labels. A mechanistic story is not a prediction; a prediction is not evidence; rejection of one null does not prove a mechanism; support for one candidate does not eliminate unconsidered rivals.\n\n## Workflow\n\n### 1. Run the scope and safety gate\n\nRecord:\n\n- accountable human owner and intended use;\n- data sensitivity, authorization, retention, and permitted processing;\n- affected people, animals, ecosystems, communities, or security interests;\n- required ethics, feasibility, biosafety, dual-use, and regulatory reviews;\n- unresolved blocks and domain expertise needed.\n\nNo script approval is an ethics, safety, regulatory, or scientific approval.\n\n### 2. Freeze the observation\n\nWrite the observation before interpretation:\n\n- measurement or source;\n- population, system, place, and time;\n- unit of observation and unit of analysis;\n- uncertainty, missingness, exclusions, and preprocessing;\n- whether the pattern was expected, exploratory, or selected after viewing results.\n\nUse “reported,” “observed,” or “associated,” not causal language, unless a causal design and estimand justify it.\n\n### 3. Frame the research question\n\nChoose a framework only when it fits:\n\n- **PICO\u002FPICOT** for intervention\u002Feffectiveness questions: population, intervention, comparator, outcome, and optionally time.\n- **PECO** for exposure questions.\n- **Population–index test–reference standard–target condition** for diagnostic accuracy.\n- **Population–prognostic factor–outcome–time** for prognosis.\n- A domain-specific construct–context–outcome frame for qualitative, descriptive, mechanistic, or theoretical work.\n\nPICO is not a universal template. Define stakeholders, context, boundaries, feasibility, and what answer would change knowledge or practice. FINER is a question-refinement mnemonic—Feasible, Interesting, Novel, Ethical, Relevant—not a scoring system. Treat “Novel” as unresolved until a documented, fit-for-purpose search and expert review support it.\n\n### 4. Establish a dated evidence boundary\n\nSearch before making literature-dependent statements. Prefer primary research, official policies, primary methods papers, current reporting guidelines, and systematic reviews used for orientation.\n\nRecord:\n\n- search date and cutoff;\n- databases\u002Findexes, queries, filters, and screening boundary;\n- included and excluded source types;\n- sources supporting, challenging, or contextualizing each claim;\n- known access, language, database, and time limitations.\n\nA search can establish what was searched, not universal absence. Say “not located within the documented search boundary,” never “no prior work exists.” Use `assets\u002Fsearch_boundary_template.json`, `assets\u002Fevidence_ledger_template.csv`, and `references\u002Fliterature_search_strategies.md`.\n\n### 5. Generate rivals before choosing tests\n\nCreate multiple candidates from genuinely different explanatory classes when plausible:\n\n- proposed mechanism;\n- measurement or processing artifact;\n- confounding or common cause;\n- selection or attrition;\n- conditioning on a collider;\n- reverse causation;\n- temporal, contextual, or boundary-condition differences;\n- stochastic variation;\n- competing mechanisms at another scale.\n\nGenerate an initial rival set independently before AI-assisted expansion to reduce anchoring and homogenization. Do not force a fixed number or false symmetry. Keep every candidate labeled `candidate`.\n\nPlatt’s strong-inference pattern motivates alternative hypotheses and crucial tests, but failed alternatives do not make the survivor true. Unknown alternatives, auxiliary assumptions, measurement error, and mixed mechanisms remain possible.\n\n### 6. Declare the claim type and estimand\n\nClassify each target as:\n\n- descriptive;\n- associational;\n- predictive;\n- causal;\n- mechanistic.\n\nFor a causal target, define before analysis:\n\n- target population or system;\n- intervention\u002Fexposure and comparator;\n- outcome and time horizon;\n- population-level summary;\n- treatment versions and intercurrent-event handling where relevant;\n- identification assumptions and target-trial\u002Fdesign analogue.\n\nDocument confounding, selection, collider, measurement, and reverse-causation risks separately. An observational causal estimate remains assumption-dependent. Use `references\u002Fcausal_inference_and_claims.md`.\n\n### 7. Derive discriminating predictions\n\nFor every candidate:\n\n1. State conditions and boundary conditions.\n2. Name the observable and measurement.\n3. State the expected pattern and uncertainty.\n4. State a result incompatible with the candidate under declared assumptions.\n5. Contrast the expected result with at least one rival.\n6. Define indeterminate outcomes and what would be learned from them.\n\nPrefer tests where rivals predict meaningfully different outcomes. Add positive, procedural, and negative controls when scientifically appropriate. A negative control must be incapable of operating through the target mechanism while sharing relevant bias pathways; it is not a decorative untreated group.\n\nUse `assets\u002Fprediction_rival_matrix_template.csv` and `assets\u002Ffalsification_controls_template.json`.\n\n### 8. Operationalize and validate measurement\n\nFor every construct record:\n\n- variable role and operational definition;\n- population\u002Fsystem, unit, timing, and conditions;\n- instrument\u002Fmethod, calibration, quality control, and masking;\n- reliability\u002Frepeatability;\n- validity evidence and applicability;\n- missingness, detection limits, transformations, cut points, and their rationales;\n- measurement invariance or cross-group comparability when relevant;\n- foreseeable measurement bias and limitations.\n\nDo not treat a convenient proxy as the construct itself. Validate with:\n\n```bash\npython3 scripts\u002Fcheck_operationalization.py local-operationalization.json\n```\n\n### 9. Match design and analysis to the claim\n\nSpecify:\n\n- sampling, experimental unit, allocation, randomization, masking, and controls;\n- inclusion\u002Fexclusion and stopping rules;\n- sample-size, precision, or information rationale based on declared assumptions;\n- outcomes, contrasts, estimands, models, effect measures, and uncertainty;\n- missing-data and intercurrent-event handling;\n- multiplicity across outcomes, models, subgroups, looks, and hypotheses;\n- assumptions, diagnostics, robustness, and sensitivity analyses;\n- replication or independent validation plan;\n- what is confirmatory versus exploratory.\n\nDo not use universal sample-size minima. Do not interpret a thresholded p-value as the probability a hypothesis is true or as effect importance. See `references\u002Fexperimental_design_patterns.md`.\n\nFor intervention trials, use the current SPIRIT 2025 protocol guidance and CONSORT 2025 reporting guidance where applicable. These improve completeness; they do not certify design quality, ethics, or regulatory compliance.\n\n### 10. Prevent HARKing and expose deviations\n\nBefore accessing the target outcomes, timestamp the question, candidates, predictions, outcomes, exclusions, transformations, analysis, multiplicity, missing-data plan, and stopping rule when feasible.\n\nAfterward:\n\n- label data-dependent ideas and analyses exploratory;\n- preserve and report planned analyses;\n- list deviations with date, rationale, who decided, and expected impact;\n- never rewrite an observed pattern as an a priori prediction.\n\nPreregistration is a transparent plan, not a ban on adaptation. Registered Reports add results-blind peer review and in-principle acceptance under journal policy. See `references\u002Fpreregistration_and_open_science.md`.\n\n### 11. Plan replication and updating\n\nDistinguish:\n\n- **reproducibility:** consistent computational results from the same data\u002Fcode\u002Fconditions;\n- **replicability:** consistency across studies collecting new data for the same question.\n\nPreserve provenance, versions, code, materials, and decision logs when sharing is authorized. Plan independent replication or transport tests across relevant boundaries. Update candidate status when contrary, null, or replication evidence arrives; do not hide negative results.\n\n### 12. Apply human accountability\n\nThe accountable human must verify:\n\n- every citation and source-to-claim link;\n- domain plausibility and measurement validity;\n- causal assumptions and statistical design;\n- ethics, feasibility, safety, privacy, and regulatory status;\n- all AI-assisted text, ideas, and citations;\n- whether broader expertise or community input is required.\n\nAI can confabulate citations, anchor reasoning, and homogenize candidate sets. Record permitted AI use and material influence. Keep independent human ideation and rival generation in the process.\n\n## Local tool index\n\nAll CLIs are bounded, dependency-free, local, deterministic, and non-scoring:\n\n| Task | Asset | Command |\n|---|---|---|\n| Hypothesis-record schema | `assets\u002Fhypothesis_record_template.json` | `python3 scripts\u002Fvalidate_hypothesis_schema.py record.json` |\n| Measurement checklist | `assets\u002Foperationalization_template.json` | `python3 scripts\u002Fcheck_operationalization.py checklist.json` |\n| Prediction\u002Frival matrix | `assets\u002Fprediction_rival_matrix_template.csv` | `python3 scripts\u002Fvalidate_prediction_matrix.py matrix.csv` |\n| Claim-language lint | Annotated Markdown | `python3 scripts\u002Flint_causal_claims.py draft.md` |\n| Falsification\u002Fcontrols | `assets\u002Ffalsification_controls_template.json` | `python3 scripts\u002Fcheck_falsification_controls.py controls.json` |\n| Evidence\u002Fsource audit | `assets\u002Fevidence_ledger_template.csv` + `assets\u002Fsearch_boundary_template.json` | `python3 scripts\u002Faudit_evidence_ledger.py ledger.csv boundary.json` |\n| Preregistration scaffold | `assets\u002Fpreregistration_scaffold_template.md` | `python3 scripts\u002Fgenerate_preregistration_scaffold.py record.json -o preregistration.md` |\n\nExit codes are `0` for structurally valid output, `1` for completed validation with errors, and `2` for malformed\u002Funsafe input. Reports validate declarations and internal consistency only; they do not verify scientific truth or choose a hypothesis. Full schemas are in `references\u002Ftool_reference.md`.\n\n## References\n\n- `references\u002Fconcepts_and_workflow.md` — object model, strong inference, uncertainty, and candidate lifecycle\n- `references\u002Fhypothesis_quality_criteria.md` — non-scoring human review criteria\n- `references\u002Fliterature_search_strategies.md` — traceable, bounded evidence search\n- `references\u002Fcausal_inference_and_claims.md` — estimands and causal-bias risks\n- `references\u002Fexperimental_design_patterns.md` — design, controls, measurement, multiplicity, and replication\n- `references\u002Fpreregistration_and_open_science.md` — preregistration, Registered Reports, deviations, and open science\n- `references\u002Fethics_safety_and_ai.md` — oversight gates, dual use, data handling, and responsible AI\n- `references\u002Ftool_reference.md` — CLI schemas, limits, and examples\n- `references\u002Fsource_ledger.md` — dated authoritative source notes\n- `references\u002Fsecurity_validation.md` — baseline findings and validation record\n\nThe bundled source ledger is `assets\u002Fsource_ledger.csv`, verified through **2026-07-23**. Recheck time-sensitive policy and guidance before a later or jurisdiction-specific use.\n\n## Related skills\n\n- `pyvene-interventions`: Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework.\n- `scientific-brainstorming`: Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evalua…\n",{"name":5,"license":15,"metadata":57,"description":7,"compatibility":63},{"tags":58,"version":59,"category":60,"maintainer":61,"last-reviewed":62},"hypothesis generation, research questions, preregistration, study design, scientific method","2.2","ideation-and-design","Kalaris Labs","2026-07-23","Python 3.11+ standard library. Bundled CLIs are deterministic and local-only; they accept bounded JSON, CSV, or Markdown and require no network, credentials, models, image services, or external packages.","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkal-hypothesis-generation","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill hypothesis-generation",{"tool":79,"command":80},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill hypothesis-generation",{"tool":82,"command":83},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill hypothesis-generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002FSKILL.md",true,[87,93,97,101,105,109,113,117,121,127,131,135,139,143,147,151,155,159,163,169,173,177,181,185,189,193],{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"assets\u002Fevidence_ledger_template.csv","ASSET","资产文件",581,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fassets\u002Fevidence_ledger_template.csv",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"assets\u002Ffalsification_controls_template.json",5880,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fassets\u002Ffalsification_controls_template.json",{"path":98,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":99,"sourceHtmlUrl":100},"assets\u002Fhypothesis_record_template.json",13768,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fassets\u002Fhypothesis_record_template.json",{"path":102,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":103,"sourceHtmlUrl":104},"assets\u002Foperationalization_template.json",2208,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fassets\u002Foperationalization_template.json",{"path":106,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":107,"sourceHtmlUrl":108},"assets\u002Fprediction_rival_matrix_template.csv",1638,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fassets\u002Fprediction_rival_matrix_template.csv",{"path":110,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":111,"sourceHtmlUrl":112},"assets\u002Fpreregistration_scaffold_template.md",5005,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fassets\u002Fpreregistration_scaffold_template.md",{"path":114,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":115,"sourceHtmlUrl":116},"assets\u002Fsearch_boundary_template.json",1114,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fassets\u002Fsearch_boundary_template.json",{"path":118,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":119,"sourceHtmlUrl":120},"assets\u002Fsource_ledger.csv",12750,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fassets\u002Fsource_ledger.csv",{"path":122,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":125,"sourceHtmlUrl":126},"references\u002Fcausal_inference_and_claims.md","REFERENCE","参考文档",7777,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fcausal_inference_and_claims.md",{"path":128,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":129,"sourceHtmlUrl":130},"references\u002Fconcepts_and_workflow.md",7341,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fconcepts_and_workflow.md",{"path":132,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":133,"sourceHtmlUrl":134},"references\u002Fethics_safety_and_ai.md",9891,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fethics_safety_and_ai.md",{"path":136,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":137,"sourceHtmlUrl":138},"references\u002Fexperimental_design_patterns.md",9765,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fexperimental_design_patterns.md",{"path":140,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":141,"sourceHtmlUrl":142},"references\u002Fhypothesis_quality_criteria.md",8035,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fhypothesis_quality_criteria.md",{"path":144,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":145,"sourceHtmlUrl":146},"references\u002Fliterature_search_strategies.md",8046,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fliterature_search_strategies.md",{"path":148,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":149,"sourceHtmlUrl":150},"references\u002Fpreregistration_and_open_science.md",6721,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fpreregistration_and_open_science.md",{"path":152,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":153,"sourceHtmlUrl":154},"references\u002Fsecurity_validation.md",3650,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fsecurity_validation.md",{"path":156,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":157,"sourceHtmlUrl":158},"references\u002Fsource_ledger.md",7410,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Fsource_ledger.md",{"path":160,"resourceType":123,"resourceTypeDesc":124,"sizeBytes":161,"sourceHtmlUrl":162},"references\u002Ftool_reference.md",8070,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Freferences\u002Ftool_reference.md",{"path":164,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":167,"sourceHtmlUrl":168},"scripts\u002F_common.py","SCRIPT","脚本",14234,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fscripts\u002F_common.py",{"path":170,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":171,"sourceHtmlUrl":172},"scripts\u002Faudit_evidence_ledger.py",12069,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fscripts\u002Faudit_evidence_ledger.py",{"path":174,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":175,"sourceHtmlUrl":176},"scripts\u002Fcheck_falsification_controls.py",16477,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fscripts\u002Fcheck_falsification_controls.py",{"path":178,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":179,"sourceHtmlUrl":180},"scripts\u002Fcheck_operationalization.py",8086,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fscripts\u002Fcheck_operationalization.py",{"path":182,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":183,"sourceHtmlUrl":184},"scripts\u002Fgenerate_preregistration_scaffold.py",14349,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fscripts\u002Fgenerate_preregistration_scaffold.py",{"path":186,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":187,"sourceHtmlUrl":188},"scripts\u002Flint_causal_claims.py",6809,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fscripts\u002Flint_causal_claims.py",{"path":190,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":191,"sourceHtmlUrl":192},"scripts\u002Fvalidate_hypothesis_schema.py",38955,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fscripts\u002Fvalidate_hypothesis_schema.py",{"path":194,"resourceType":165,"resourceTypeDesc":166,"sizeBytes":195,"sourceHtmlUrl":196},"scripts\u002Fvalidate_prediction_matrix.py",9815,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-hypothesis-generation\u002Fscripts\u002Fvalidate_prediction_matrix.py",[198,228,253,280,305,328],{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":207,"publishedAt":52},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[204],{"categoryNo":205,"categoryName":206,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":232,"categories":233,"keywords":234,"publishedAt":52},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[235,236,237,238,212,239,240,241,242,243,244,245,246,247,248,249,250,251,252,224],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","use","platform","grow","posting","competitive",{"skillNo":254,"name":255,"nameZh":6,"description":256,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":257,"categories":258,"keywords":262,"publishedAt":52},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[259],{"categoryNo":260,"categoryName":261,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[263,246,264,265,266,267,268,269,248,270,271,64,272,273,274,275,276,277,278,279],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":281,"name":282,"nameZh":6,"description":283,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":284,"categories":285,"keywords":286,"publishedAt":52},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[287,288,289,290,291,292,293,294,295,248,296,219,297,298,299,300,301,302,303,304],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":306,"name":307,"nameZh":6,"description":308,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":309,"categories":310,"keywords":312,"publishedAt":52},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[311],{"categoryNo":260,"categoryName":261,"taxonomyType":21,"taxonomyTypeDesc":22},[313,314,315,44,316,265,292,317,318,319,320,321,246,322,218,323,324,325,326,327],"workflow","workflow builder","builder","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":329,"name":330,"nameZh":6,"description":331,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":332,"categories":333,"keywords":334,"publishedAt":52},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[335,336,337,338,339,340,341,342,343,320,344,345,346,347,348,349,220,350,351,304],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]