[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F32PPA2FBYEYACQMHJRK1Q":3,"skill-same:01M7F32PPA2FBYEYACQMHJRK1Q":87},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7F32PPA2FBYEYACQMHJRK1Q","systems-thinking",null,"For a problem where the obvious fix has already failed or made things worse. The cause usually lives three or four layers below the events that keep appearing; this finds that structure, matches it against the ~10 known archetypes to get the canonical intervention, and checks second-order effects before you commit. Event-level fixes are what it exists to replace. USE WHEN systems thinking, causal loop, feedback loops, archetypes, leverage points, iceberg model, fix the system, why does this keep happening, recurring problem, second-order effects, the fix made it worse, this keeps coming back. NOT FOR incident causal chains (use root-cause-analysis).","VytCepas\u002Fharbor-core","VytCepas","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121751744?v=4","01M7F2WXE5SD8DMXS16GS3B63Z","Vytautas Cepas","01M7F2WXEWJ26637KE8PFYGBRK",0,"MIT","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: systems-thinking\nversion: 1.0.5\ndescription: \"For a problem where the obvious fix has already failed or made things worse. The cause usually lives three or four layers below the events that keep appearing; this finds that structure, matches it against the ~10 known archetypes to get the canonical intervention, and checks second-order effects before you commit. Event-level fixes are what it exists to replace. USE WHEN systems thinking, causal loop, feedback loops, archetypes, leverage points, iceberg model, fix the system, why does this keep happening, recurring problem, second-order effects, the fix made it worse, this keeps coming back. NOT FOR incident causal chains (use root-cause-analysis).\"\neffort: high\ncontext: fork\ndisable-model-invocation: true\n---\n\n# SystemsThinking Skill\n\n## What It Does\n\nAnalyzes complex systems to reveal why the same problem keeps coming back and where a small change produces a large result. Five workflows: Iceberg (walk symptom down to structure), CausalLoop (map feedback loops), FindArchetype (match a known pattern and apply its fix), FindLeverage (Meadows' 12 leverage points), ConceptMap (Novak entity-relationship). Grounded in Donella Meadows, Peter Senge, Jay Forrester, Russell Ackoff, and the Santa Fe Institute tradition.\n\n## The Problem\n\nMost attempts to fix a recurring problem operate at the event layer — patch the bug, retry the request, add another check — and the problem comes back, because the real cause lives 3-4 layers below in the structure that generates the events. People also can't see second-order effects: a \"fix\" ships and creates a new problem, or makes the original worse. Without a way to see the structure, you treat symptoms forever and the obvious lever is almost never where the symptom shows up.\n\n## How It Works\n\nSystems thinking is the difference between treating symptoms (patch the bug) and fixing structure (change the feedback loop that keeps producing the bug). The skill walks from visible events down to the structure underneath, names the pattern, and finds where to push.\n\n**The deliverable:** identify the generating structure and the highest-leverage intervention, with second-order effects surfaced. A done analysis names the structure that produces the behavior (not the nearest event), the leverage point to push, and at least one round of the intervention's own feedback traced before shipping.\n\n## Core Concept\n\nA **system** is a set of elements interconnected in a way that produces a characteristic behavior over time. Change the elements, often nothing happens. Change the interconnections or the purpose, and behavior shifts dramatically.\n\nFive axioms this skill operates on:\n\n1. **Behavior is generated by structure.** If the same outcome keeps happening, the cause is structural, not a series of unrelated incidents.\n2. **Events are visible; structure is not.** Most analysis stops at events. Systems thinking walks down.\n3. **Feedback loops are the basic unit.** Every persistent pattern is one of a small number of loop archetypes.\n4. **High-leverage interventions are usually counterintuitive.** The obvious fix often makes the problem worse (policy resistance, shifting the burden, fixes that fail).\n5. **You can't optimize a part of a system — you can only improve the system.** Local optimization often degrades global performance.\n\n## Use \u002F Win\n\n**When to use:**\n\n- **Recurring problems** — the same kind of bug, incident, deadline slip, or conflict keeps appearing. Event-level fixes are not working.\n- **Unintended consequences** — a \"fix\" produced a new problem, or made the original worse.\n- **System design** — before committing to an architecture, product strategy, organization structure, or policy.\n- **Debugging systemic issues** — distributed-system flakiness, performance cliffs, reliability decay, tech-debt accretion.\n- **Strategy** — understanding where competition, demand, adoption, or resistance actually comes from.\n- **Policy, incentives, organization design** — any environment where human behavior is an input.\n- **Before a large intervention** — run the causal loop first; intended effects are rarely the only effects.\n\n**What you win:**\n\n- **Structural causes** instead of blame-the-nearest-event. The real lever is almost never where the symptom appeared.\n- **Archetype recognition** — most organizational and technical pathologies match one of ~10 patterns. Naming the pattern unlocks the canonical intervention.\n- **Leverage-point identification** — Meadows' 12 leverage points, ordered. Parameters are low leverage; paradigms are highest. Knowing where to push is the whole game.\n- **Unintended-consequence preview** — causal loops let you simulate second- and third-order effects before shipping the change.\n- **Durable fixes** — structural changes don't regress the way symptom patches do.\n\n**Default mental model:** At Extended+ effort on anything with recurring behavior, organizational dynamics, or cross-component coupling, systems thinking is not optional enrichment — it's how you find the fix that sticks.\n\n## Workflow Routing\n\nRoute to the appropriate workflow based on the request.\n\n| Workflow | Trigger | File |\n|----------|---------|------|\n| **Iceberg** | \"iceberg model\", \"structural cause\", \"why does this keep happening\", walk from symptom down to structure | `Workflows\u002FIceberg.md` |\n| **CausalLoop** | \"causal loop\", \"feedback loop\", \"connection circle\", \"map relationships\", build a CLD | `Workflows\u002FCausalLoop.md` |\n| **FindArchetype** | \"systems archetype\", \"recognize this pattern\", \"fixes that fail\", \"shifting the burden\", \"tragedy of the commons\" | `Workflows\u002FFindArchetype.md` |\n| **FindLeverage** | \"leverage point\", \"where to intervene\", \"highest-leverage change\", Meadows' 12 | `Workflows\u002FFindLeverage.md` |\n| **ConceptMap** | \"concept map\", \"map the entities\", \"relationship map\", Novak-style mapping | `Workflows\u002FConceptMap.md` |\n\n## Quick Reference\n\n- **5 workflows** — Iceberg, CausalLoop, FindArchetype, FindLeverage, ConceptMap\n- **Iceberg layers (top to bottom):** Events → Patterns → Structures → Mental Models\n- **Feedback loop types:** Reinforcing (R) — amplifying \u002F exponential; Balancing (B) — goal-seeking \u002F stabilizing\n- **Archetype count:** ~10 canonical patterns (Senge, Braun)\n- **Leverage points:** 12 levels, from parameters (weakest) to paradigm transcendence (strongest) — Meadows\n\n**Context files (loaded on demand):**\n- `Foundation.md` — Meadows, Senge, Forrester, Ackoff, Capra; canonical definitions\n- `Archetypes.md` — the 10 systems archetypes with structure, recognition signs, canonical intervention\n- `LeveragePoints.md` — Meadows' 12 leverage points with worked examples\n\n## Integration\n\n**Depends on:** nothing — standalone analytical skill.\n\n**Works well with:**\n- **RootCauseAnalysis** — RCA is event-layer and pattern-layer; SystemsThinking continues down to structure and mental models. Pair them for deep incident analysis.\n- **FirstPrinciples** — decompose to axioms, then use SystemsThinking to see how axioms interconnect.\n- **IterativeDepth** — rotates lenses; SystemsThinking is the structural lens.\n- **BeCreative \u002F Ideate** — generate intervention candidates after identifying the leverage point.\n- **Art** — render causal loop diagrams, iceberg diagrams, concept maps.\n\n## Examples\n\n**Example 1: Recurring incidents**\n```\nUser: \"we keep getting paged for the same class of timeout\"\n→ Iceberg workflow\n→ Events: 6 pages in 3 weeks\n→ Patterns: all during deploy windows, all touching payments service\n→ Structure: auto-scaler cold-start latency > health-check timeout during deploys\n→ Mental model: \"deploys are safe if tests pass\" — but health checks aren't in the test path\n→ Fix is structural, not another retry\n```\n\n**Example 2: Strategy**\n```\nUser: \"why does adding engineers slow us down past team size 12?\"\n→ FindArchetype workflow\n→ Match: \"Limits to Growth\" archetype\n→ Reinforcing loop: more engineers → more output → more hiring\n→ Balancing loop: team size → coordination cost → per-engineer output ↓\n→ Canonical intervention: attack the balancing loop (coordination mechanism), not the reinforcing one (stop hiring)\n```\n\n**Example 3: Unintended consequences preview**\n```\nUser: \"we're about to add a rate limit to stop abuse\"\n→ CausalLoop workflow\n→ Build CLD of users, abusers, support load, legitimate traffic\n→ Surface: balancing loop (rate limit ↓ abuse), reinforcing loop (rate limit → legit users retry → total load ↑)\n→ Recommend: rate-limit per-identity with reputation scoring, not per-IP\n```\n\n## Gotchas\n\n- **Systems thinking is descriptive, not prescriptive.** It reveals structure; it does not tell you what to build. Use it with `BeCreative` or `FirstPrinciples` to generate interventions.\n- **Don't mistake a list for a system.** A system has feedback. If you can't draw at least one loop, you have a list of components, not a system.\n- **Blaming the model is the mistake.** When a loop says something uncomfortable (\"incentives are the cause\"), the reaction is often to reject the model. Sit with it.\n- **Delay is underrated.** Many systemic failures come from delays (between action and feedback). Capture delays explicitly on your diagram.\n- **Soft variables count.** \"Trust,\" \"morale,\" \"perceived safety\" are as real as latency numbers in systems work. Don't drop them because they're hard to measure.\n\n---\n\n**Attribution:** Frameworks drawn from Donella Meadows (*Thinking in Systems*, 2008; \"Places to Intervene in a System,\" 1999), Peter Senge (*The Fifth Discipline*, 1990), Jay Forrester (*Industrial Dynamics*, 1961), Russell Ackoff (*Systems Thinking for Curious Managers*), Fritjof Capra (*The Web of Life*), and the System Dynamics Society tradition.\n","# SystemsThinking Skill\n\n## What It Does\n\nAnalyzes complex systems to reveal why the same problem keeps coming back and where a small change produces a large result. Five workflows: Iceberg (walk symptom down to structure), CausalLoop (map feedback loops), FindArchetype (match a known pattern and apply its fix), FindLeverage (Meadows' 12 leverage points), ConceptMap (Novak entity-relationship). Grounded in Donella Meadows, Peter Senge, Jay Forrester, Russell Ackoff, and the Santa Fe Institute tradition.\n\n## The Problem\n\nMost attempts to fix a recurring problem operate at the event layer — patch the bug, retry the request, add another check — and the problem comes back, because the real cause lives 3-4 layers below in the structure that generates the events. People also can't see second-order effects: a \"fix\" ships and creates a new problem, or makes the original worse. Without a way to see the structure, you treat symptoms forever and the obvious lever is almost never where the symptom shows up.\n\n## How It Works\n\nSystems thinking is the difference between treating symptoms (patch the bug) and fixing structure (change the feedback loop that keeps producing the bug). The skill walks from visible events down to the structure underneath, names the pattern, and finds where to push.\n\n**The deliverable:** identify the generating structure and the highest-leverage intervention, with second-order effects surfaced. A done analysis names the structure that produces the behavior (not the nearest event), the leverage point to push, and at least one round of the intervention's own feedback traced before shipping.\n\n## Core Concept\n\nA **system** is a set of elements interconnected in a way that produces a characteristic behavior over time. Change the elements, often nothing happens. Change the interconnections or the purpose, and behavior shifts dramatically.\n\nFive axioms this skill operates on:\n\n1. **Behavior is generated by structure.** If the same outcome keeps happening, the cause is structural, not a series of unrelated incidents.\n2. **Events are visible; structure is not.** Most analysis stops at events. Systems thinking walks down.\n3. **Feedback loops are the basic unit.** Every persistent pattern is one of a small number of loop archetypes.\n4. **High-leverage interventions are usually counterintuitive.** The obvious fix often makes the problem worse (policy resistance, shifting the burden, fixes that fail).\n5. **You can't optimize a part of a system — you can only improve the system.** Local optimization often degrades global performance.\n\n## Use \u002F Win\n\n**When to use:**\n\n- **Recurring problems** — the same kind of bug, incident, deadline slip, or conflict keeps appearing. Event-level fixes are not working.\n- **Unintended consequences** — a \"fix\" produced a new problem, or made the original worse.\n- **System design** — before committing to an architecture, product strategy, organization structure, or policy.\n- **Debugging systemic issues** — distributed-system flakiness, performance cliffs, reliability decay, tech-debt accretion.\n- **Strategy** — understanding where competition, demand, adoption, or resistance actually comes from.\n- **Policy, incentives, organization design** — any environment where human behavior is an input.\n- **Before a large intervention** — run the causal loop first; intended effects are rarely the only effects.\n\n**What you win:**\n\n- **Structural causes** instead of blame-the-nearest-event. The real lever is almost never where the symptom appeared.\n- **Archetype recognition** — most organizational and technical pathologies match one of ~10 patterns. Naming the pattern unlocks the canonical intervention.\n- **Leverage-point identification** — Meadows' 12 leverage points, ordered. Parameters are low leverage; paradigms are highest. Knowing where to push is the whole game.\n- **Unintended-consequence preview** — causal loops let you simulate second- and third-order effects before shipping the change.\n- **Durable fixes** — structural changes don't regress the way symptom patches do.\n\n**Default mental model:** At Extended+ effort on anything with recurring behavior, organizational dynamics, or cross-component coupling, systems thinking is not optional enrichment — it's how you find the fix that sticks.\n\n## Workflow Routing\n\nRoute to the appropriate workflow based on the request.\n\n| Workflow | Trigger | File |\n|----------|---------|------|\n| **Iceberg** | \"iceberg model\", \"structural cause\", \"why does this keep happening\", walk from symptom down to structure | `Workflows\u002FIceberg.md` |\n| **CausalLoop** | \"causal loop\", \"feedback loop\", \"connection circle\", \"map relationships\", build a CLD | `Workflows\u002FCausalLoop.md` |\n| **FindArchetype** | \"systems archetype\", \"recognize this pattern\", \"fixes that fail\", \"shifting the burden\", \"tragedy of the commons\" | `Workflows\u002FFindArchetype.md` |\n| **FindLeverage** | \"leverage point\", \"where to intervene\", \"highest-leverage change\", Meadows' 12 | `Workflows\u002FFindLeverage.md` |\n| **ConceptMap** | \"concept map\", \"map the entities\", \"relationship map\", Novak-style mapping | `Workflows\u002FConceptMap.md` |\n\n## Quick Reference\n\n- **5 workflows** — Iceberg, CausalLoop, FindArchetype, FindLeverage, ConceptMap\n- **Iceberg layers (top to bottom):** Events → Patterns → Structures → Mental Models\n- **Feedback loop types:** Reinforcing (R) — amplifying \u002F exponential; Balancing (B) — goal-seeking \u002F stabilizing\n- **Archetype count:** ~10 canonical patterns (Senge, Braun)\n- **Leverage points:** 12 levels, from parameters (weakest) to paradigm transcendence (strongest) — Meadows\n\n**Context files (loaded on demand):**\n- `Foundation.md` — Meadows, Senge, Forrester, Ackoff, Capra; canonical definitions\n- `Archetypes.md` — the 10 systems archetypes with structure, recognition signs, canonical intervention\n- `LeveragePoints.md` — Meadows' 12 leverage points with worked examples\n\n## Integration\n\n**Depends on:** nothing — standalone analytical skill.\n\n**Works well with:**\n- **RootCauseAnalysis** — RCA is event-layer and pattern-layer; SystemsThinking continues down to structure and mental models. Pair them for deep incident analysis.\n- **FirstPrinciples** — decompose to axioms, then use SystemsThinking to see how axioms interconnect.\n- **IterativeDepth** — rotates lenses; SystemsThinking is the structural lens.\n- **BeCreative \u002F Ideate** — generate intervention candidates after identifying the leverage point.\n- **Art** — render causal loop diagrams, iceberg diagrams, concept maps.\n\n## Examples\n\n**Example 1: Recurring incidents**\n```\nUser: \"we keep getting paged for the same class of timeout\"\n→ Iceberg workflow\n→ Events: 6 pages in 3 weeks\n→ Patterns: all during deploy windows, all touching payments service\n→ Structure: auto-scaler cold-start latency > health-check timeout during deploys\n→ Mental model: \"deploys are safe if tests pass\" — but health checks aren't in the test path\n→ Fix is structural, not another retry\n```\n\n**Example 2: Strategy**\n```\nUser: \"why does adding engineers slow us down past team size 12?\"\n→ FindArchetype workflow\n→ Match: \"Limits to Growth\" archetype\n→ Reinforcing loop: more engineers → more output → more hiring\n→ Balancing loop: team size → coordination cost → per-engineer output ↓\n→ Canonical intervention: attack the balancing loop (coordination mechanism), not the reinforcing one (stop hiring)\n```\n\n**Example 3: Unintended consequences preview**\n```\nUser: \"we're about to add a rate limit to stop abuse\"\n→ CausalLoop workflow\n→ Build CLD of users, abusers, support load, legitimate traffic\n→ Surface: balancing loop (rate limit ↓ abuse), reinforcing loop (rate limit → legit users retry → total load ↑)\n→ Recommend: rate-limit per-identity with reputation scoring, not per-IP\n```\n\n## Gotchas\n\n- **Systems thinking is descriptive, not prescriptive.** It reveals structure; it does not tell you what to build. Use it with `BeCreative` or `FirstPrinciples` to generate interventions.\n- **Don't mistake a list for a system.** A system has feedback. If you can't draw at least one loop, you have a list of components, not a system.\n- **Blaming the model is the mistake.** When a loop says something uncomfortable (\"incentives are the cause\"), the reaction is often to reject the model. Sit with it.\n- **Delay is underrated.** Many systemic failures come from delays (between action and feedback). Capture delays explicitly on your diagram.\n- **Soft variables count.** \"Trust,\" \"morale,\" \"perceived safety\" are as real as latency numbers in systems work. Don't drop them because they're hard to measure.\n\n---\n\n**Attribution:** Frameworks drawn from Donella Meadows (*Thinking in Systems*, 2008; \"Places to Intervene in a System,\" 1999), Peter Senge (*The Fifth Discipline*, 1990), Jay Forrester (*Industrial Dynamics*, 1961), Russell Ackoff (*Systems Thinking for Curious Managers*), Fritjof Capra (*The Web of Life*), and the System Dynamics Society tradition.\n",{"name":5,"effort":25,"context":26,"version":27,"description":7,"disable-model-invocation":28},"high","fork","1.0.5",true,"main","c20d05953dd442f4617cfff4fced9c8ef12789a7","tests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core","https:\u002F\u002Fgithub.com\u002FVytCepas","Agentic AI Systems Researcher & Engineer","2026-11-15 08:28:56",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":28},[38,41,44],{"tool":39,"command":40},"npx","npx skills add VytCepas\u002Fharbor-core --skill systems-thinking",{"tool":42,"command":43},"bunx","bunx skills add VytCepas\u002Fharbor-core --skill systems-thinking",{"tool":45,"command":46},"pnpm","pnpm dlx skills add VytCepas\u002Fharbor-core --skill systems-thinking","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FSKILL.md",[49,55,59,63,67,71,75,79,83],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"Archetypes.md","REFERENCE","参考文档",15634,"https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FArchetypes.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"Foundation.md",12831,"https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FFoundation.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"LeveragePoints.md",11975,"https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FLeveragePoints.md",{"path":64,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":16},"LICENSE","许可证",1071,{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"Workflows\u002FCausalLoop.md",8824,"https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FWorkflows\u002FCausalLoop.md",{"path":72,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":73,"sourceHtmlUrl":74},"Workflows\u002FConceptMap.md",8031,"https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FWorkflows\u002FConceptMap.md",{"path":76,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":77,"sourceHtmlUrl":78},"Workflows\u002FFindArchetype.md",12676,"https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FWorkflows\u002FFindArchetype.md",{"path":80,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":81,"sourceHtmlUrl":82},"Workflows\u002FFindLeverage.md",13595,"https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FWorkflows\u002FFindLeverage.md",{"path":84,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":85,"sourceHtmlUrl":86},"Workflows\u002FIceberg.md",8573,"https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fsystems-thinking\u002FWorkflows\u002FIceberg.md",[88,96,104,112,119,126],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":20},"01M7F32H3H4GJ5GTJA0AFC5YTV","red-team","Adversarial analysis deploying parallel expert agents to stress-test ideas, strategies, and plans — decomposes into atomic claims, attacks them, then steelmans and counter-argues, producing severity-ranked findings with remediation. USE WHEN red team, attack idea, counterarguments, critique, stress test, devil's advocate, find weaknesses, break this, poke holes, strongest objection. NOT FOR collaborative debate to find best path (use council).","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fred-team\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Fred-team\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":20},"01M7F32AD6SWE4PVR9WGWRJQYS","first-principles","Physics-based reasoning framework (Musk methodology) that deconstructs a problem to irreducible fundamental truths, classifies every element as hard constraint, soft constraint, or assumption, then reconstructs the optimal solution from fundamentals alone. USE WHEN first principles, fundamental truths, challenge assumptions, real constraint, rebuild from scratch, start over, physics first, question everything, reasoning by analogy. NOT FOR structural feedback loops (use systems-thinking).","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Ffirst-principles\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fthinking\u002Fpack-tree\u002Fskills\u002Ffirst-principles\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":108,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":20},"01M7F3249SWK3EXBPTEWERD0X4","company-help","Explains this laptop's safety settings in plain words: why a step was stopped, asked about or is waiting for an admin, where work files belong, and how to get a website allowed. USE WHEN a step is refused or blocked, a permission question appears, a site or download fails, or someone asks what Harbor is or where to save files. NOT FOR changing a setting: nobody here can.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Ftests\u002Fmember\u002Fpack\u002Ffixtures\u002Fhub-packs\u002Fcompany-start\u002Fpack-tree\u002Fskills\u002Fcompany-help\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":108,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":20},"01M7F31YZEGZ16W0FCH5Z9WM71","test-strength","Prove a load-bearing test can actually fail, and that it fails for the right reason. Break the thing it guards, watch it go red, restore — then check it stays green on a valid-but-unusual input, because red on a mutant proves discrimination, not correctness. USE WHEN a suite is written or changed, a guard is trusted, a gate reports zero, or a green result is about to be cited as evidence. NOT FOR reviewing a diff for defects (audit-review-fanout), or running a suite to see it pass (`bin\u002Ftest-suite-run.sh`).","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Fskills\u002Ftest-strength\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":108,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":20},"01M7F31S8VXRVM2NZYPK8QDPHG","status-suggest-scan","Runs the repeated-work scan and says in plain words what a person keeps doing by hand. USE WHEN a person asks what they repeat or what Harbor could take over. NOT FOR building what it finds.","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Fskills\u002Fstatus-suggest-scan\u002FSKILL.md",[],[],{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":108,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":20},"01M7F31J6SNPPV9XKA54CMM7P6","skill-catalog","The index of every skill, `harbor` verb, agent-facing bin tool and credentialed CLI on this box, each with the path or exact command; most are hidden from your listing and this is the only route to them. USE WHEN you are about to wait on CI or a PR, run a suite, push, merge or do any scripted chore by hand, or do reasoning work by hand: design an eval or a pass^k study, run a red-team pass, chase a root cause, reason from first principles, get independent perspectives, write or optimise a prompt, extract a paper, generate options. ALSO WHEN what skills do I have, list skills, find a tool, is there a harbor command for this, how do I wait on CI, skill-book (its old name). NOT FOR invoking a skill already in your listing.","https:\u002F\u002Fgithub.com\u002FVytCepas\u002Fharbor-core\u002Fblob\u002Fmain\u002Fskills\u002Fskill-catalog\u002FSKILL.md",[],[]]