[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EG1H0BDAZA0CHK5BZ8GFAQ":3,"skill-same:01M7EG1H0BDAZA0CHK5BZ8GFAQ":62},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7EG1H0BDAZA0CHK5BZ8GFAQ","bio-systems-biology-strain-design",null,"Computes metabolic-engineering strain designs on genome-scale models with StrainDesign (OptKnock, RobustKnock, minimal cut sets, OptCouple) and cameo (heuristic knockout and FSEOF over\u002Funder-expression targets), finding gene\u002Freaction interventions that couple product formation to growth. Use when designing knockouts to overproduce a target chemical, choosing between OptKnock and RobustKnock, growth-coupling a product so evolution maintains it, computing minimal cut sets, finding amplification targets with FSEOF, or understanding why MILP strain design needs a strong solver and why a design is only a hypothesis.","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-systems-biology-strain-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bio-systems-biology-strain-design\ndescription: Computes metabolic-engineering strain designs on genome-scale models with StrainDesign (OptKnock, RobustKnock, minimal cut sets, OptCouple) and cameo (heuristic knockout and FSEOF over\u002Funder-expression targets), finding gene\u002Freaction interventions that couple product formation to growth. Use when designing knockouts to overproduce a target chemical, choosing between OptKnock and RobustKnock, growth-coupling a product so evolution maintains it, computing minimal cut sets, finding amplification targets with FSEOF, or understanding why MILP strain design needs a strong solver and why a design is only a hypothesis.\ntool_type: python\nprimary_tool: straindesign\nsource: \"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills\"\nsource_repository: \"GPTomics\u002FbioSkills\"\nsource_path: \"systems-biology\u002Fstrain-design\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n## Version Compatibility\n\nReference examples tested with: StrainDesign 1.15+, COBRApy 0.29+, Python 3.10+ (cameo optional)\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- Python: `pip show \u003Cpackage>` then `help(module.function)` to check signatures\n\nIf code throws ImportError, AttributeError, or TypeError, introspect the installed\npackage and adapt the example to match the actual API rather than retrying.\n\nNote: OptKnock\u002FRobustKnock\u002FMCS are MILP problems and are far harder than plain FBA; StrainDesign supports GLPK\u002FSCIP (open source) and CPLEX\u002FGurobi (academic, much faster and more robust for genome-scale). Set a `time_limit`. Reaction-based designs must be translated back to gene knockouts via GPRs.\n\n# Strain Design\n\n**\"Design knockouts to make my organism overproduce a chemical\"** -> Search for a set of gene\u002Freaction interventions that couples product formation to growth, so the engineered strain cannot grow well without secreting the target.\n- Python: `straindesign.compute_strain_designs(model, sd_modules=[SDModule(model, OPTKNOCK, ...)])`; cameo for heuristics\u002FFSEOF\n\n## The governing principle: growth-coupling makes evolution enforce the design\n\nThe core idea of computational strain design is growth-coupling. A naive \"just delete the competing pathways\" design is fragile: the cell will find an alternate flux route, or evolution in the bioreactor will erode production because making product costs the cell resources. A growth-COUPLED design instead makes product secretion obligatory for growth - the cell physically cannot reach high growth without also secreting the target, so selection maintains production instead of eroding it. This is why OptKnock is a BILEVEL optimization: the inner problem is the cell maximizing its own growth, the outer problem is the engineer maximizing product AT that inner optimum. Consequences:\n\n- OptKnock is optimistic: it assumes the cell, among its growth-optimal states, picks the one best for the engineer. The cell need not. RobustKnock fixes this by maximizing product in the WORST-case inner optimum - a more conservative, more trustworthy design.\n- A design is a HYPOTHESIS about a model, not a strain. FBA has no regulation, no enzyme kinetics, no toxicity, no genetic stability; a computationally growth-coupled design can fail in construction or in the bioreactor. Validate with the production envelope, then in the lab.\n- MILP strain design is combinatorially hard. Bound the intervention set (`max_cost`), cap solutions, set a time limit, and use a strong solver (CPLEX\u002FGurobi for genome-scale). Reaction knockouts must be mapped back to gene deletions through the GPR to be realizable.\n\n## Decision: which strain-design method\n\n| Goal | Method | Trade-off |\n|------|--------|-----------|\n| Growth-coupled knockouts, optimistic | OptKnock (Burgard 2003) | bilevel; assumes the cell cooperates at its growth optimum |\n| Growth-coupled knockouts, conservative | RobustKnock (Tepper & Shlomi 2010) | guarantees product in the worst-case inner optimum; harder |\n| Guaranteed intervention sets, enumerate all minimal | Minimal Cut Sets (von Kamp & Klamt 2014) | strong guarantees; enumerates smallest intervention sets |\n| Strong growth-coupling (obligatory) | OptCouple | maximizes the growth-coupling potential directly |\n| Over\u002Funder-EXPRESSION targets, not just knockouts | FSEOF (Choi 2010) \u002F cameo | scans fluxes that rise with enforced product; amplification targets |\n| Heuristic\u002Fevolutionary search when MILP is intractable | OptGene \u002F cameo | fast approximate designs; no optimality guarantee |\n\nPrefer RobustKnock or MCS over plain OptKnock when the design must be trustworthy; OptKnock's optimism is a well-known way to overstate a design.\n\n## Growth-Coupled Knockouts with StrainDesign (OptKnock)\n\n**Goal:** Find a small set of reaction knockouts that couples secretion of a target product to growth.\n\n**Approach:** Build an OptKnock `SDModule` with the cell's growth as the inner objective and product secretion as the outer objective, plus a minimum-growth constraint so the design keeps the strain viable, then call `compute_strain_designs` with an intervention budget and solver. Translate the returned reaction knockouts back to gene deletions via the GPR.\n\n```python\nimport cobra\nimport straindesign as sd\n\nmodel = cobra.io.load_model('textbook')\nbiomass = 'Biomass_Ecoli_core'   # the model's actual biomass reaction id (verify per model)\n\noptknock = sd.SDModule(\n    model, sd.OPTKNOCK,\n    inner_objective=biomass,            # the cell maximizes growth\n    outer_objective='EX_ac_e',          # the engineer maximizes acetate secretion\n    constraints=[f'{biomass} >= 0.3'],  # keep the strain viable\n)\n\nsolutions = sd.compute_strain_designs(\n    model, sd_modules=[optknock],\n    max_cost=3,          # at most 3 interventions\n    max_solutions=3,\n    solver='glpk',       # use 'cplex'\u002F'gurobi' for genome-scale models\n    time_limit=120,\n)\n# solutions.reaction_sd is a list of intervention dicts {reaction_id: marker}; a knockout is\n# marked -1.0 (not 0). Verify this marker for the installed StrainDesign version -- a wrong marker\n# silently yields empty designs. For a knockout-only OptKnock module every entry is a knockout.\nfor design in solutions.reaction_sd:\n    print('knockouts:', [rid for rid, mark in design.items() if mark == -1.0])\n```\n\n## Verify Growth-Coupling with the Production Envelope\n\n```python\nfrom cobra.flux_analysis import production_envelope\n\n# A genuinely growth-coupled design shows a NONZERO minimum product flux across the growth range:\n# the strain cannot grow without secreting product. Apply the design's knockouts, then:\nenv = production_envelope(model, reactions=['EX_ac_e'])   # objective defaults to biomass\n# Inspect the lower bound of product at each growth level; if it can be zero at max growth, the\n# coupling is weak (the OptKnock-optimism problem) -- consider RobustKnock. See flux-balance-analysis.\n```\n\n## Over-Expression Targets (FSEOF, cameo)\n\n```python\n# Knockouts are not the only lever. FSEOF (flux scanning with enforced objective flux) finds\n# reactions whose flux RISES as product formation is enforced -- candidate amplification\u002Fover-\n# expression targets. cameo implements FSEOF and heuristic (evolutionary) design search:\n#   from cameo.strain_design import OptGene           # heuristic knockout search\n#   from cameo.strain_design.deterministic import FSEOF\n# Use FSEOF\u002Fover-expression when the bottleneck is low flux through an existing pathway rather than\n# a competing drain that a knockout would remove.\n```\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| `compute_strain_designs` never finishes | MILP is hard and GLPK is slow on genome-scale | set `time_limit`, lower `max_cost`, use CPLEX\u002FGurobi |\n| Design gives zero product when built | OptKnock optimism: the cell chose a different growth-optimal state | use RobustKnock, or check the production envelope's lower bound |\n| Constraint parser rejects the biomass id | wrong reaction id string for this model | look up the actual objective reaction id (`linear_reaction_coefficients`) |\n| Design not realizable in the lab | reaction knockouts have no clean gene mapping, or hit an essential gene | translate reaction KOs to gene KOs via GPR; exclude essential genes |\n| Predicted overproduction never materializes | FBA has no regulation\u002Fkinetics\u002Ftoxicity\u002Fstability | treat the design as a hypothesis; validate the envelope, then in vivo |\n| No feasible design found | growth constraint too tight or product infeasible on the medium | relax the minimum-growth constraint; confirm the product can be made on the medium |\n\n## Related Skills\n\n- systems-biology\u002Fflux-balance-analysis - Production envelope and the FBA\u002Fmedium foundation\n- systems-biology\u002Fgene-essentiality - Avoid designing knockouts of essential genes; GPR mapping\n- systems-biology\u002Fmodel-curation - A curated model is a prerequisite for a trustworthy design\n- systems-biology\u002Fcontext-specific-models - Constrain the chassis to a condition before designing\n- metabolomics\u002Fpathway-mapping - Interpret the affected pathways of a design\n\n## References\n\n- Burgard AP, Pharkya P, Maranas CD. 2003. OptKnock: a bilevel programming framework for identifying gene knockout strategies for microbial strain optimization. *Biotechnol Bioeng* 84(6):647-657.\n- Schneider P, Bekiaris PS, von Kamp A, Klamt S. 2022. StrainDesign: a comprehensive Python package for computational design of metabolic networks. *Bioinformatics* 38(21):4981-4983.\n- Tepper N, Shlomi T. 2010. Predicting metabolic engineering knockout strategies for chemical production: accounting for competing pathways. *Bioinformatics* 26(4):536-543. (RobustKnock)\n- von Kamp A, Klamt S. 2014. Enumeration of smallest intervention strategies in genome-scale metabolic networks. *PLoS Comput Biol* 10(1):e1003378. (minimal cut sets)\n- Choi HS, Lee SY, Kim TY, Woo HM. 2010. In silico identification of gene amplification targets for improvement of lycopene production. *Appl Environ Microbiol* 76(10):3097-3105. (FSEOF)\n- Cardoso JGR, Jensen K, Lieven C, et al. 2018. Cameo: a Python library for computer-aided metabolic engineering and optimization of cell factories. *ACS Synth Biol* 7(4):1163-1166.\n","## Version Compatibility\n\nReference examples tested with: StrainDesign 1.15+, COBRApy 0.29+, Python 3.10+ (cameo optional)\n\nBefore using code patterns, verify installed versions match. If versions differ:\n- Python: `pip show \u003Cpackage>` then `help(module.function)` to check signatures\n\nIf code throws ImportError, AttributeError, or TypeError, introspect the installed\npackage and adapt the example to match the actual API rather than retrying.\n\nNote: OptKnock\u002FRobustKnock\u002FMCS are MILP problems and are far harder than plain FBA; StrainDesign supports GLPK\u002FSCIP (open source) and CPLEX\u002FGurobi (academic, much faster and more robust for genome-scale). Set a `time_limit`. Reaction-based designs must be translated back to gene knockouts via GPRs.\n\n# Strain Design\n\n**\"Design knockouts to make my organism overproduce a chemical\"** -> Search for a set of gene\u002Freaction interventions that couples product formation to growth, so the engineered strain cannot grow well without secreting the target.\n- Python: `straindesign.compute_strain_designs(model, sd_modules=[SDModule(model, OPTKNOCK, ...)])`; cameo for heuristics\u002FFSEOF\n\n## The governing principle: growth-coupling makes evolution enforce the design\n\nThe core idea of computational strain design is growth-coupling. A naive \"just delete the competing pathways\" design is fragile: the cell will find an alternate flux route, or evolution in the bioreactor will erode production because making product costs the cell resources. A growth-COUPLED design instead makes product secretion obligatory for growth - the cell physically cannot reach high growth without also secreting the target, so selection maintains production instead of eroding it. This is why OptKnock is a BILEVEL optimization: the inner problem is the cell maximizing its own growth, the outer problem is the engineer maximizing product AT that inner optimum. Consequences:\n\n- OptKnock is optimistic: it assumes the cell, among its growth-optimal states, picks the one best for the engineer. The cell need not. RobustKnock fixes this by maximizing product in the WORST-case inner optimum - a more conservative, more trustworthy design.\n- A design is a HYPOTHESIS about a model, not a strain. FBA has no regulation, no enzyme kinetics, no toxicity, no genetic stability; a computationally growth-coupled design can fail in construction or in the bioreactor. Validate with the production envelope, then in the lab.\n- MILP strain design is combinatorially hard. Bound the intervention set (`max_cost`), cap solutions, set a time limit, and use a strong solver (CPLEX\u002FGurobi for genome-scale). Reaction knockouts must be mapped back to gene deletions through the GPR to be realizable.\n\n## Decision: which strain-design method\n\n| Goal | Method | Trade-off |\n|------|--------|-----------|\n| Growth-coupled knockouts, optimistic | OptKnock (Burgard 2003) | bilevel; assumes the cell cooperates at its growth optimum |\n| Growth-coupled knockouts, conservative | RobustKnock (Tepper & Shlomi 2010) | guarantees product in the worst-case inner optimum; harder |\n| Guaranteed intervention sets, enumerate all minimal | Minimal Cut Sets (von Kamp & Klamt 2014) | strong guarantees; enumerates smallest intervention sets |\n| Strong growth-coupling (obligatory) | OptCouple | maximizes the growth-coupling potential directly |\n| Over\u002Funder-EXPRESSION targets, not just knockouts | FSEOF (Choi 2010) \u002F cameo | scans fluxes that rise with enforced product; amplification targets |\n| Heuristic\u002Fevolutionary search when MILP is intractable | OptGene \u002F cameo | fast approximate designs; no optimality guarantee |\n\nPrefer RobustKnock or MCS over plain OptKnock when the design must be trustworthy; OptKnock's optimism is a well-known way to overstate a design.\n\n## Growth-Coupled Knockouts with StrainDesign (OptKnock)\n\n**Goal:** Find a small set of reaction knockouts that couples secretion of a target product to growth.\n\n**Approach:** Build an OptKnock `SDModule` with the cell's growth as the inner objective and product secretion as the outer objective, plus a minimum-growth constraint so the design keeps the strain viable, then call `compute_strain_designs` with an intervention budget and solver. Translate the returned reaction knockouts back to gene deletions via the GPR.\n\n```python\nimport cobra\nimport straindesign as sd\n\nmodel = cobra.io.load_model('textbook')\nbiomass = 'Biomass_Ecoli_core'   # the model's actual biomass reaction id (verify per model)\n\noptknock = sd.SDModule(\n    model, sd.OPTKNOCK,\n    inner_objective=biomass,            # the cell maximizes growth\n    outer_objective='EX_ac_e',          # the engineer maximizes acetate secretion\n    constraints=[f'{biomass} >= 0.3'],  # keep the strain viable\n)\n\nsolutions = sd.compute_strain_designs(\n    model, sd_modules=[optknock],\n    max_cost=3,          # at most 3 interventions\n    max_solutions=3,\n    solver='glpk',       # use 'cplex'\u002F'gurobi' for genome-scale models\n    time_limit=120,\n)\n# solutions.reaction_sd is a list of intervention dicts {reaction_id: marker}; a knockout is\n# marked -1.0 (not 0). Verify this marker for the installed StrainDesign version -- a wrong marker\n# silently yields empty designs. For a knockout-only OptKnock module every entry is a knockout.\nfor design in solutions.reaction_sd:\n    print('knockouts:', [rid for rid, mark in design.items() if mark == -1.0])\n```\n\n## Verify Growth-Coupling with the Production Envelope\n\n```python\nfrom cobra.flux_analysis import production_envelope\n\n# A genuinely growth-coupled design shows a NONZERO minimum product flux across the growth range:\n# the strain cannot grow without secreting product. Apply the design's knockouts, then:\nenv = production_envelope(model, reactions=['EX_ac_e'])   # objective defaults to biomass\n# Inspect the lower bound of product at each growth level; if it can be zero at max growth, the\n# coupling is weak (the OptKnock-optimism problem) -- consider RobustKnock. See flux-balance-analysis.\n```\n\n## Over-Expression Targets (FSEOF, cameo)\n\n```python\n# Knockouts are not the only lever. FSEOF (flux scanning with enforced objective flux) finds\n# reactions whose flux RISES as product formation is enforced -- candidate amplification\u002Fover-\n# expression targets. cameo implements FSEOF and heuristic (evolutionary) design search:\n#   from cameo.strain_design import OptGene           # heuristic knockout search\n#   from cameo.strain_design.deterministic import FSEOF\n# Use FSEOF\u002Fover-expression when the bottleneck is low flux through an existing pathway rather than\n# a competing drain that a knockout would remove.\n```\n\n## Common Errors\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| `compute_strain_designs` never finishes | MILP is hard and GLPK is slow on genome-scale | set `time_limit`, lower `max_cost`, use CPLEX\u002FGurobi |\n| Design gives zero product when built | OptKnock optimism: the cell chose a different growth-optimal state | use RobustKnock, or check the production envelope's lower bound |\n| Constraint parser rejects the biomass id | wrong reaction id string for this model | look up the actual objective reaction id (`linear_reaction_coefficients`) |\n| Design not realizable in the lab | reaction knockouts have no clean gene mapping, or hit an essential gene | translate reaction KOs to gene KOs via GPR; exclude essential genes |\n| Predicted overproduction never materializes | FBA has no regulation\u002Fkinetics\u002Ftoxicity\u002Fstability | treat the design as a hypothesis; validate the envelope, then in vivo |\n| No feasible design found | growth constraint too tight or product infeasible on the medium | relax the minimum-growth constraint; confirm the product can be made on the medium |\n\n## Related Skills\n\n- systems-biology\u002Fflux-balance-analysis - Production envelope and the FBA\u002Fmedium foundation\n- systems-biology\u002Fgene-essentiality - Avoid designing knockouts of essential genes; GPR mapping\n- systems-biology\u002Fmodel-curation - A curated model is a prerequisite for a trustworthy design\n- systems-biology\u002Fcontext-specific-models - Constrain the chassis to a condition before designing\n- metabolomics\u002Fpathway-mapping - Interpret the affected pathways of a design\n\n## References\n\n- Burgard AP, Pharkya P, Maranas CD. 2003. OptKnock: a bilevel programming framework for identifying gene knockout strategies for microbial strain optimization. *Biotechnol Bioeng* 84(6):647-657.\n- Schneider P, Bekiaris PS, von Kamp A, Klamt S. 2022. StrainDesign: a comprehensive Python package for computational design of metabolic networks. *Bioinformatics* 38(21):4981-4983.\n- Tepper N, Shlomi T. 2010. Predicting metabolic engineering knockout strategies for chemical production: accounting for competing pathways. *Bioinformatics* 26(4):536-543. (RobustKnock)\n- von Kamp A, Klamt S. 2014. Enumeration of smallest intervention strategies in genome-scale metabolic networks. *PLoS Comput Biol* 10(1):e1003378. (minimal cut sets)\n- Choi HS, Lee SY, Kim TY, Woo HM. 2010. In silico identification of gene amplification targets for improvement of lycopene production. *Appl Environ Microbiol* 76(10):3097-3105. (FSEOF)\n- Cardoso JGR, Jensen K, Lieven C, et al. 2018. Cameo: a Python library for computer-aided metabolic engineering and optimization of cell factories. *ACS Synth Biol* 7(4):1163-1166.\n",{"name":5,"source":24,"license":15,"tool_type":25,"description":7,"imported_at":26,"source_path":27,"primary_tool":28,"source_repository":29},"https:\u002F\u002Fgithub.com\u002FGPTomics\u002FbioSkills","python","2026-09-20","systems-biology\u002Fstrain-design\u002FSKILL.md","straindesign","GPTomics\u002FbioSkills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fbiology\u002Fbio-systems-biology-strain-design","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-systems-biology-strain-design",{"tool":42,"command":43},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-systems-biology-strain-design",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill bio-systems-biology-strain-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-systems-biology-strain-design\u002FSKILL.md",true,[50,56],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"examples\u002Fstrain_design.py","SCRIPT","脚本",3166,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-systems-biology-strain-design\u002Fexamples\u002Fstrain_design.py",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"usage-guide.md","REFERENCE","参考文档",5429,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fbiology\u002Fbio-systems-biology-strain-design\u002Fusage-guide.md",[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":70},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":70},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":70},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":70},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":70},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]