[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MK989WWN2TRGCAQG5KCC16":3,"skill-same:01M6MK989WWN2TRGCAQG5KCC16":73},{"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":23,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":66},"01M6MK989WWN2TRGCAQG5KCC16","skill-decision-support",null,"Present options with trade-offs for informed decision-making — use when choosing between approaches","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-decision-support\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"support","decision","decision support","skill decision support","use","options","trade","decision-making","present","with","true","for","trade-offs","when","2026-11-10 10:12:30",false,"---\nname: skill-decision-support\ndescription: \"Present options with trade-offs for informed decision-making — use when choosing between approaches\"\ndisable-model-invocation: true\n---\n\n> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Decision Support & Options Presentation\n\n## Overview\n\nStructured approach to presenting options and alternatives with clear trade-offs, enabling informed decision-making.\n\n**Core principle:** Understand context → Generate options → Analyze trade-offs → Present clearly → Support choice.\n\n\n## When to Use\n\n**Use this skill when user:**\n- Asks for options or alternatives\n- Says \"fix or provide options\"\n- Needs help deciding between approaches\n- Wants to see different ways to solve a problem\n- Is uncertain about best path forward\n\n**Do NOT use for:**\n- General research (\"what is X?\") → use flow-probe\n- Implementation work → use flow-tangle\n- Simple yes\u002Fno questions\n- Already-decided approaches\n\n\n## The Process\n\n### Phase 1: Context Understanding\n\n#### Step 1: Understand the Decision Point\n\n```markdown\n**Decision Context:**\n\nWhat needs to be decided: [the core question]\nWhy it matters: [impact of this decision]\nConstraints: [time, resources, compatibility, etc.]\nCurrent state: [what exists now]\n```\n\n#### Step 2: Gather Requirements\n\nUse AskUserQuestion if needed to understand:\n- Must-have requirements\n- Nice-to-have features\n- Deal-breakers\n- Timeline constraints\n- Budget\u002Fresource constraints\n\n#### Step 3: Set the decision criteria before scoring\n\nChoose criteria, scoring definitions and weights before evaluating the options.\nUse the user's stated priorities. If priorities are missing, state the assumed\nweights and the effect those assumptions may have. Weights must total 100%.\nKeep the same criteria and weights for every option. Do not change them to\nmake a preferred option win; record any later revision and rescore all options.\n\n\n### Phase 2: Generate Options\n\n#### Step 1: Identify Viable Approaches\n\nGenerate 2-4 distinct options, including the status quo. Always include doing\nnothing as the comparison baseline and state its cost, risks and consequences\nof delay. If it violates a requirement, retain it for comparison and explain\nwhy it is not viable. Do not assume that changing something is beneficial.\n\n| Option Type | When to Include |\n|-------------|-----------------|\n| **Status quo \u002F do nothing** | Always; include its ongoing cost and cost of delay |\n| **Conservative** | Low risk, proven approach |\n| **Moderate** | Balanced risk\u002Freward |\n| **Innovative** | Higher risk, potentially better outcome |\n| **Minimal** | Simplest possible solution |\n\n**Except for the required status-quo baseline, don't generate options that:**\n- Violate stated constraints\n- Are clearly inferior to others\n- Are essentially the same with minor tweaks\n\n#### Step 2: Research Each Option\n\nFor each option, understand:\n- How it works\n- What it requires\n- What the outcome looks like\n- What could go wrong\n\n\n### Phase 3: Trade-off Analysis\n\nFor each option, analyze the trade-offs below, then score it against the criteria\nand weights set in Phase 1. Show raw scores beside weighted scores and the total.\nLabel uncertain inputs and assumptions; do not invent measurements to fill a\nscoring table. Choose the recommendation only after this analysis, with reasons\nthat refer to the user's requirements and the comparison baseline.\n\n```markdown\n### Option N: [Name]\n\n**Description:**\n[1-2 sentence description]\n\n**Pros:**\n- ✅ [Advantage 1]\n- ✅ [Advantage 2]\n- ✅ [Advantage 3]\n\n**Cons:**\n- ❌ [Disadvantage 1]\n- ❌ [Disadvantage 2]\n- ❌ [Disadvantage 3]\n\n**Effort:** [Low\u002FMedium\u002FHigh]\n**Risk:** [Low\u002FMedium\u002FHigh]\n**Reversibility:** [Easy\u002FModerate\u002FDifficult to undo]\n\n**Best for:** [when this option makes sense]\n```\n\n#### Optional scenario stress test\n\nFor a decision that depends on uncertain assumptions, select the two drivers\nwith the most uncertainty and impact. Describe three or four plausible futures\nand check how each option performs in each. Report which option holds up across\nthe futures and which assumptions would change the recommendation. Keep this\noptional; do not add provider calls without the user's existing authorization.\n\n\n### Phase 4: Present Options\n\n#### Format for Presentation\n\nOmit unused option sections and table columns when presenting fewer than four options.\n\n```markdown\n# Decision: [What needs to be decided]\n\n**Context:** [Brief summary of why this decision is needed]\n\n\n## Option 1: [Option name]\n\n**What it is:**\n[Clear explanation in 1-2 sentences]\n\n**Pros:**\n- ✅ [Pro 1]\n- ✅ [Pro 2]\n- ✅ [Pro 3]\n\n**Cons:**\n- ❌ [Con 1]\n- ❌ [Con 2]\n\n**Implementation:**\n[Brief overview of what's involved]\n\n**Timeline:** [estimate]\n**Risk Level:** Low\u002FMedium\u002FHigh\n\n\n## Option 2: [Option name]\n\n[Same structure as Option 1]\n\n\n## Option 3: [Option name, if needed]\n\n[Same structure as Option 1]\n\n\n## Option 4: [Option name, if needed]\n\n[Same structure as Option 1]\n\n\n## Quick Comparison\n\n| Criteria | Option 1 | Option 2 | Option 3 | Option 4 |\n|----------|----------|----------|----------|----------|\n| Effort | [level] | [level] | [level] | [level] |\n| Risk | [level] | [level] | [level] | [level] |\n| Reversible | [yes\u002Fno] | [yes\u002Fno] | [yes\u002Fno] | [yes\u002Fno] |\n| Timeline | [time] | [time] | [time] | [time] |\n| Best for | [scenario] | [scenario] | [scenario] | [scenario] |\n\n## Criteria and scores\n\n| Criterion | Weight | Option 1 raw \u002F weighted | Option 2 raw \u002F weighted | Option 3 raw \u002F weighted | Option 4 raw \u002F weighted |\n|-----------|--------|-------------------------|-------------------------|-------------------------|-------------------------|\n| [Criterion fixed before scoring] | [percentage] | [raw \u002F weighted] | [raw \u002F weighted] | [raw \u002F weighted] | [raw \u002F weighted] |\n| **Total** | **100%** | [weighted total] | [weighted total] | [weighted total] | [weighted total] |\n\n[State the scoring scale, evidence and uncertainty. Include the status quo as\none of the options above and explain its ongoing cost and the cost of delay.]\n\n\n## Recommendation\n\n**I recommend Option [N]: [Name]**\n\n[Select N from the completed analysis. No option is recommended by default.]\n\n**Why:**\n1. [Reason 1]\n2. [Reason 2]\n3. [Reason 3]\n\n**This option is best because:** [summary of key advantage relative to context]\n\n\n**Which option would you like to proceed with?**\n```\n\n#### Guidelines for Presentation\n\n1. **Mark the analyzed recommendation clearly**, after comparing every option.\n2. **Limit to 2-4 options including the status quo** (too many = decision paralysis)\n3. **Be honest about cons** (don't oversell any option)\n4. **Make comparison easy** (use consistent structure)\n5. **Support with reasoning** (explain why recommendation makes sense)\n\n\n### Phase 5: Support the Choice\n\nAfter user chooses:\n\n```markdown\n✅ **Proceeding with Option [N]: [Name]**\n\n**Next steps:**\n1. [Step 1]\n2. [Step 2]\n3. [Step 3]\n\n**I'll now [begin implementation \u002F gather more details \u002F create plan].**\n```\n\nIf user asks for more info on a specific option:\n\n```markdown\n**Deep dive on Option [N]:**\n\n**How it works:**\n[Detailed explanation]\n\n**Implementation steps:**\n1. [Detailed step 1]\n2. [Detailed step 2]\n...\n\n**Potential issues and mitigations:**\n- Issue: [potential problem]\n  Mitigation: [how to handle it]\n\n**Would you like to proceed with this option?**\n```\n\n\n## Common Patterns\n\n### Pattern 1: \"Fix or Provide Options\"\n\n```\nUser: \"The auth system is broken. Fix or provide options.\"\n\nResponse structure:\n1. Assess: Is the fix obvious or are there choices?\n2. If obvious: Present the fix + ask for confirmation\n3. If choices: Present options with trade-offs\n\nExample:\n\nI can see the auth issue. Here are your options:\n\n**Option 1: Quick Fix**\n- Patch the current JWT validation\n- Pros: Fast, low risk\n- Cons: Doesn't address underlying architecture\n\n**Option 2: Comprehensive Refactor**\n- Rebuild auth with better patterns\n- Pros: Long-term solution\n- Cons: Takes longer, more testing needed\n\n**Option 3: Keep the current implementation**\n- State the ongoing cost, risk and consequences of delaying the fix.\n\nRecommend an option only after comparing these against the agreed criteria.\n\n**Which approach fits your timeline?**\n```\n\n### Pattern 2: \"What Are My Options\"\n\n```\nUser: \"I need to add caching. What are my options?\"\n\nResponse structure:\n1. Understand requirements (what needs caching, scale, etc.)\n2. Generate 2-4 options including keeping the API uncached\n3. Present with trade-offs\n4. Recommend based on their context\n\nExample:\n\nFor caching your API responses, here are the main options:\n\n**Option 1: In-Memory Cache (Node-cache)**\n- Best for: Single-server setup\n- Pros: Simple, fast, no external dependencies\n- Cons: Lost on restart, doesn't scale across servers\n\n**Option 2: Redis**\n- Best for: Multi-server or persistence needed\n- Pros: Persistent, distributed, feature-rich\n- Cons: Requires Redis server, more complex\n\n**Option 3: CDN Caching (Cloudflare\u002FFastly)**\n- Best for: Static\u002Fsemi-static content\n- Pros: Global distribution, handles scale\n- Cons: Less control, costs, public content only\n\n**Option 4: Keep the API uncached**\n- State the current operating cost, latency and consequences of delaying a change.\n\n**After scoring against the agreed criteria, recommend Option [N] because [evidence].**\nWhich would you like to use?\n```\n\n### Pattern 3: \"Help Me Decide\"\n\n```\nUser: \"Should I use TypeScript or stick with JavaScript? Help me decide.\"\n\nResponse structure:\n1. Clarify decision factors (team size, project scope, timeline)\n2. Agree on criteria, scoring definitions and weights totaling 100% before evaluating either option\n3. Compare the alternatives, including the current setup and its cost of delay, with raw and weighted scores\n4. Recommend after comparing the weighted totals and checking constraints\n5. Support whatever they choose\n\nExample:\n\nLet me help you decide between TypeScript and JavaScript.\n\nBefore evaluating either option, agree on the criteria, scoring definitions and\nweights. Keep those weights fixed across both options.\n\n**Option 1: TypeScript**\nPros: Type safety, better tooling, catches errors early\nCons: Learning curve, build step, more setup\nBest for: Larger teams, long-term projects, complex domains\n\n**Option 2: Keep JavaScript, the current setup**\nPros: Simpler, no build step, familiar to all devs\nCons: Runtime errors, less IDE support, harder to refactor\nBest for: Small projects, prototypes, simple applications\nOngoing cost and cost of delay: [Quantify current maintenance costs and any consequences of delaying migration. State when no change is needed.]\n\n**Comparison using the criteria agreed before evaluation**\n\n| Criterion and scoring definition | Weight | TypeScript raw \u002F weighted | JavaScript raw \u002F weighted |\n|---|---|---|---|\n| [Agreed criterion and score meanings] | [weight %] | [raw score] \u002F [weighted contribution] | [raw score] \u002F [weighted contribution] |\n| **Total** | **100%** | [weighted total] | [weighted total] |\n\nRepeat the criterion row for every agreed criterion. Weighted contribution is\nthe raw score multiplied by the percentage weight divided by 100. Label\nuncertain inputs and explain any constraint that the totals do not capture.\n\n**After comparing against the agreed criteria, recommend Option [N] because [evidence].**\n\nWhich option would you like to proceed with?\n```\n\n\n## Integration with Other Skills\n\n### With flow-probe\n\n```\nNeed to research options thoroughly?\n→ Use flow-probe to gather information\n→ Use skill-decision-support to present findings as options\n```\n\n### With flow-tangle\n\n```\nUser chose an option?\n→ Use flow-tangle to implement the chosen approach\n```\n\n### With skill-debug\n\n```\nBug could be fixed multiple ways?\n→ Use skill-decision-support to present fix options\n→ Use skill-debug to implement chosen fix systematically\n```\n\n\n## Best Practices\n\n### 1. Tailor to User's Needs\n\n**Ask about constraints:**\n```markdown\nBefore presenting options, I need to understand:\n- Timeline: How urgent is this?\n- Resources: What's available (team size, budget, infrastructure)?\n- Risk tolerance: Is this production-critical or experimental?\n- Reversibility: Must this decision be reversible?\n```\n\n### 2. Quantify When Possible\n\n**Good:**\n```\n**Timeline:**\n- Option 1: 2-3 hours\n- Option 2: 1-2 days\n- Option 3: 1 week\n```\n\n**Poor:**\n```\n**Timeline:**\n- Option 1: Quick\n- Option 2: A while\n- Option 3: Longer\n```\n\n### 3. Be Honest About Unknowns\n\n```\n**Option 2: Microservices Architecture**\n\n⚠️ **Unknown:** Migration effort could be 2-4 weeks depending on current coupling.\nWould need to audit codebase to give accurate estimate.\n```\n\n### 4. Provide \"Escape Hatch\"\n\nAlways include:\n```\n**Not satisfied with these options?**\n\nI can also:\n- Research more alternatives\n- Combine aspects of multiple options\n- Deep-dive on any specific approach\n- Prototype a solution to test viability\n```\n\n\n## Red Flags - Don't Do This\n\n| Action | Why It's Wrong |\n|--------|----------------|\n| Only present one \"option\" | That's not a choice |\n| Present 8+ options | Decision paralysis |\n| Hide significant cons | User can't make informed choice |\n| Recommend without reasoning | User can't evaluate recommendation |\n| Ignore stated constraints | Wasting user's time |\n| Present obviously bad options as viable | Undermines trust |\n\n\n## Quick Reference\n\n| User Request | Action |\n|--------------|--------|\n| \"fix or provide options\" | Assess if fix obvious → If yes: present fix, if no: present options |\n| \"what are my options\" | Understand context → Generate 2-4 options → Present with trade-offs |\n| \"help me decide\" | Clarify decision factors → Compare approaches → Recommend with reasoning |\n| \"show alternatives\" | Generate alternatives → Analyze pros\u002Fcons → Present structured comparison |\n\n\n## The Bottom Line\n\n```\nDecision support → Clear options + Honest trade-offs + Reasoned recommendation\nOtherwise → Confusion + Poor decisions + Regret\n```\n\n**Understand context. Present real choices. Support with reasoning. Respect their decision.**\n","> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Decision Support & Options Presentation\n\n## Overview\n\nStructured approach to presenting options and alternatives with clear trade-offs, enabling informed decision-making.\n\n**Core principle:** Understand context → Generate options → Analyze trade-offs → Present clearly → Support choice.\n\n\n## When to Use\n\n**Use this skill when user:**\n- Asks for options or alternatives\n- Says \"fix or provide options\"\n- Needs help deciding between approaches\n- Wants to see different ways to solve a problem\n- Is uncertain about best path forward\n\n**Do NOT use for:**\n- General research (\"what is X?\") → use flow-probe\n- Implementation work → use flow-tangle\n- Simple yes\u002Fno questions\n- Already-decided approaches\n\n\n## The Process\n\n### Phase 1: Context Understanding\n\n#### Step 1: Understand the Decision Point\n\n```markdown\n**Decision Context:**\n\nWhat needs to be decided: [the core question]\nWhy it matters: [impact of this decision]\nConstraints: [time, resources, compatibility, etc.]\nCurrent state: [what exists now]\n```\n\n#### Step 2: Gather Requirements\n\nUse AskUserQuestion if needed to understand:\n- Must-have requirements\n- Nice-to-have features\n- Deal-breakers\n- Timeline constraints\n- Budget\u002Fresource constraints\n\n#### Step 3: Set the decision criteria before scoring\n\nChoose criteria, scoring definitions and weights before evaluating the options.\nUse the user's stated priorities. If priorities are missing, state the assumed\nweights and the effect those assumptions may have. Weights must total 100%.\nKeep the same criteria and weights for every option. Do not change them to\nmake a preferred option win; record any later revision and rescore all options.\n\n\n### Phase 2: Generate Options\n\n#### Step 1: Identify Viable Approaches\n\nGenerate 2-4 distinct options, including the status quo. Always include doing\nnothing as the comparison baseline and state its cost, risks and consequences\nof delay. If it violates a requirement, retain it for comparison and explain\nwhy it is not viable. Do not assume that changing something is beneficial.\n\n| Option Type | When to Include |\n|-------------|-----------------|\n| **Status quo \u002F do nothing** | Always; include its ongoing cost and cost of delay |\n| **Conservative** | Low risk, proven approach |\n| **Moderate** | Balanced risk\u002Freward |\n| **Innovative** | Higher risk, potentially better outcome |\n| **Minimal** | Simplest possible solution |\n\n**Except for the required status-quo baseline, don't generate options that:**\n- Violate stated constraints\n- Are clearly inferior to others\n- Are essentially the same with minor tweaks\n\n#### Step 2: Research Each Option\n\nFor each option, understand:\n- How it works\n- What it requires\n- What the outcome looks like\n- What could go wrong\n\n\n### Phase 3: Trade-off Analysis\n\nFor each option, analyze the trade-offs below, then score it against the criteria\nand weights set in Phase 1. Show raw scores beside weighted scores and the total.\nLabel uncertain inputs and assumptions; do not invent measurements to fill a\nscoring table. Choose the recommendation only after this analysis, with reasons\nthat refer to the user's requirements and the comparison baseline.\n\n```markdown\n### Option N: [Name]\n\n**Description:**\n[1-2 sentence description]\n\n**Pros:**\n- ✅ [Advantage 1]\n- ✅ [Advantage 2]\n- ✅ [Advantage 3]\n\n**Cons:**\n- ❌ [Disadvantage 1]\n- ❌ [Disadvantage 2]\n- ❌ [Disadvantage 3]\n\n**Effort:** [Low\u002FMedium\u002FHigh]\n**Risk:** [Low\u002FMedium\u002FHigh]\n**Reversibility:** [Easy\u002FModerate\u002FDifficult to undo]\n\n**Best for:** [when this option makes sense]\n```\n\n#### Optional scenario stress test\n\nFor a decision that depends on uncertain assumptions, select the two drivers\nwith the most uncertainty and impact. Describe three or four plausible futures\nand check how each option performs in each. Report which option holds up across\nthe futures and which assumptions would change the recommendation. Keep this\noptional; do not add provider calls without the user's existing authorization.\n\n\n### Phase 4: Present Options\n\n#### Format for Presentation\n\nOmit unused option sections and table columns when presenting fewer than four options.\n\n```markdown\n# Decision: [What needs to be decided]\n\n**Context:** [Brief summary of why this decision is needed]\n\n\n## Option 1: [Option name]\n\n**What it is:**\n[Clear explanation in 1-2 sentences]\n\n**Pros:**\n- ✅ [Pro 1]\n- ✅ [Pro 2]\n- ✅ [Pro 3]\n\n**Cons:**\n- ❌ [Con 1]\n- ❌ [Con 2]\n\n**Implementation:**\n[Brief overview of what's involved]\n\n**Timeline:** [estimate]\n**Risk Level:** Low\u002FMedium\u002FHigh\n\n\n## Option 2: [Option name]\n\n[Same structure as Option 1]\n\n\n## Option 3: [Option name, if needed]\n\n[Same structure as Option 1]\n\n\n## Option 4: [Option name, if needed]\n\n[Same structure as Option 1]\n\n\n## Quick Comparison\n\n| Criteria | Option 1 | Option 2 | Option 3 | Option 4 |\n|----------|----------|----------|----------|----------|\n| Effort | [level] | [level] | [level] | [level] |\n| Risk | [level] | [level] | [level] | [level] |\n| Reversible | [yes\u002Fno] | [yes\u002Fno] | [yes\u002Fno] | [yes\u002Fno] |\n| Timeline | [time] | [time] | [time] | [time] |\n| Best for | [scenario] | [scenario] | [scenario] | [scenario] |\n\n## Criteria and scores\n\n| Criterion | Weight | Option 1 raw \u002F weighted | Option 2 raw \u002F weighted | Option 3 raw \u002F weighted | Option 4 raw \u002F weighted |\n|-----------|--------|-------------------------|-------------------------|-------------------------|-------------------------|\n| [Criterion fixed before scoring] | [percentage] | [raw \u002F weighted] | [raw \u002F weighted] | [raw \u002F weighted] | [raw \u002F weighted] |\n| **Total** | **100%** | [weighted total] | [weighted total] | [weighted total] | [weighted total] |\n\n[State the scoring scale, evidence and uncertainty. Include the status quo as\none of the options above and explain its ongoing cost and the cost of delay.]\n\n\n## Recommendation\n\n**I recommend Option [N]: [Name]**\n\n[Select N from the completed analysis. No option is recommended by default.]\n\n**Why:**\n1. [Reason 1]\n2. [Reason 2]\n3. [Reason 3]\n\n**This option is best because:** [summary of key advantage relative to context]\n\n\n**Which option would you like to proceed with?**\n```\n\n#### Guidelines for Presentation\n\n1. **Mark the analyzed recommendation clearly**, after comparing every option.\n2. **Limit to 2-4 options including the status quo** (too many = decision paralysis)\n3. **Be honest about cons** (don't oversell any option)\n4. **Make comparison easy** (use consistent structure)\n5. **Support with reasoning** (explain why recommendation makes sense)\n\n\n### Phase 5: Support the Choice\n\nAfter user chooses:\n\n```markdown\n✅ **Proceeding with Option [N]: [Name]**\n\n**Next steps:**\n1. [Step 1]\n2. [Step 2]\n3. [Step 3]\n\n**I'll now [begin implementation \u002F gather more details \u002F create plan].**\n```\n\nIf user asks for more info on a specific option:\n\n```markdown\n**Deep dive on Option [N]:**\n\n**How it works:**\n[Detailed explanation]\n\n**Implementation steps:**\n1. [Detailed step 1]\n2. [Detailed step 2]\n...\n\n**Potential issues and mitigations:**\n- Issue: [potential problem]\n  Mitigation: [how to handle it]\n\n**Would you like to proceed with this option?**\n```\n\n\n## Common Patterns\n\n### Pattern 1: \"Fix or Provide Options\"\n\n```\nUser: \"The auth system is broken. Fix or provide options.\"\n\nResponse structure:\n1. Assess: Is the fix obvious or are there choices?\n2. If obvious: Present the fix + ask for confirmation\n3. If choices: Present options with trade-offs\n\nExample:\n\nI can see the auth issue. Here are your options:\n\n**Option 1: Quick Fix**\n- Patch the current JWT validation\n- Pros: Fast, low risk\n- Cons: Doesn't address underlying architecture\n\n**Option 2: Comprehensive Refactor**\n- Rebuild auth with better patterns\n- Pros: Long-term solution\n- Cons: Takes longer, more testing needed\n\n**Option 3: Keep the current implementation**\n- State the ongoing cost, risk and consequences of delaying the fix.\n\nRecommend an option only after comparing these against the agreed criteria.\n\n**Which approach fits your timeline?**\n```\n\n### Pattern 2: \"What Are My Options\"\n\n```\nUser: \"I need to add caching. What are my options?\"\n\nResponse structure:\n1. Understand requirements (what needs caching, scale, etc.)\n2. Generate 2-4 options including keeping the API uncached\n3. Present with trade-offs\n4. Recommend based on their context\n\nExample:\n\nFor caching your API responses, here are the main options:\n\n**Option 1: In-Memory Cache (Node-cache)**\n- Best for: Single-server setup\n- Pros: Simple, fast, no external dependencies\n- Cons: Lost on restart, doesn't scale across servers\n\n**Option 2: Redis**\n- Best for: Multi-server or persistence needed\n- Pros: Persistent, distributed, feature-rich\n- Cons: Requires Redis server, more complex\n\n**Option 3: CDN Caching (Cloudflare\u002FFastly)**\n- Best for: Static\u002Fsemi-static content\n- Pros: Global distribution, handles scale\n- Cons: Less control, costs, public content only\n\n**Option 4: Keep the API uncached**\n- State the current operating cost, latency and consequences of delaying a change.\n\n**After scoring against the agreed criteria, recommend Option [N] because [evidence].**\nWhich would you like to use?\n```\n\n### Pattern 3: \"Help Me Decide\"\n\n```\nUser: \"Should I use TypeScript or stick with JavaScript? Help me decide.\"\n\nResponse structure:\n1. Clarify decision factors (team size, project scope, timeline)\n2. Agree on criteria, scoring definitions and weights totaling 100% before evaluating either option\n3. Compare the alternatives, including the current setup and its cost of delay, with raw and weighted scores\n4. Recommend after comparing the weighted totals and checking constraints\n5. Support whatever they choose\n\nExample:\n\nLet me help you decide between TypeScript and JavaScript.\n\nBefore evaluating either option, agree on the criteria, scoring definitions and\nweights. Keep those weights fixed across both options.\n\n**Option 1: TypeScript**\nPros: Type safety, better tooling, catches errors early\nCons: Learning curve, build step, more setup\nBest for: Larger teams, long-term projects, complex domains\n\n**Option 2: Keep JavaScript, the current setup**\nPros: Simpler, no build step, familiar to all devs\nCons: Runtime errors, less IDE support, harder to refactor\nBest for: Small projects, prototypes, simple applications\nOngoing cost and cost of delay: [Quantify current maintenance costs and any consequences of delaying migration. State when no change is needed.]\n\n**Comparison using the criteria agreed before evaluation**\n\n| Criterion and scoring definition | Weight | TypeScript raw \u002F weighted | JavaScript raw \u002F weighted |\n|---|---|---|---|\n| [Agreed criterion and score meanings] | [weight %] | [raw score] \u002F [weighted contribution] | [raw score] \u002F [weighted contribution] |\n| **Total** | **100%** | [weighted total] | [weighted total] |\n\nRepeat the criterion row for every agreed criterion. Weighted contribution is\nthe raw score multiplied by the percentage weight divided by 100. Label\nuncertain inputs and explain any constraint that the totals do not capture.\n\n**After comparing against the agreed criteria, recommend Option [N] because [evidence].**\n\nWhich option would you like to proceed with?\n```\n\n\n## Integration with Other Skills\n\n### With flow-probe\n\n```\nNeed to research options thoroughly?\n→ Use flow-probe to gather information\n→ Use skill-decision-support to present findings as options\n```\n\n### With flow-tangle\n\n```\nUser chose an option?\n→ Use flow-tangle to implement the chosen approach\n```\n\n### With skill-debug\n\n```\nBug could be fixed multiple ways?\n→ Use skill-decision-support to present fix options\n→ Use skill-debug to implement chosen fix systematically\n```\n\n\n## Best Practices\n\n### 1. Tailor to User's Needs\n\n**Ask about constraints:**\n```markdown\nBefore presenting options, I need to understand:\n- Timeline: How urgent is this?\n- Resources: What's available (team size, budget, infrastructure)?\n- Risk tolerance: Is this production-critical or experimental?\n- Reversibility: Must this decision be reversible?\n```\n\n### 2. Quantify When Possible\n\n**Good:**\n```\n**Timeline:**\n- Option 1: 2-3 hours\n- Option 2: 1-2 days\n- Option 3: 1 week\n```\n\n**Poor:**\n```\n**Timeline:**\n- Option 1: Quick\n- Option 2: A while\n- Option 3: Longer\n```\n\n### 3. Be Honest About Unknowns\n\n```\n**Option 2: Microservices Architecture**\n\n⚠️ **Unknown:** Migration effort could be 2-4 weeks depending on current coupling.\nWould need to audit codebase to give accurate estimate.\n```\n\n### 4. Provide \"Escape Hatch\"\n\nAlways include:\n```\n**Not satisfied with these options?**\n\nI can also:\n- Research more alternatives\n- Combine aspects of multiple options\n- Deep-dive on any specific approach\n- Prototype a solution to test viability\n```\n\n\n## Red Flags - Don't Do This\n\n| Action | Why It's Wrong |\n|--------|----------------|\n| Only present one \"option\" | That's not a choice |\n| Present 8+ options | Decision paralysis |\n| Hide significant cons | User can't make informed choice |\n| Recommend without reasoning | User can't evaluate recommendation |\n| Ignore stated constraints | Wasting user's time |\n| Present obviously bad options as viable | Undermines trust |\n\n\n## Quick Reference\n\n| User Request | Action |\n|--------------|--------|\n| \"fix or provide options\" | Assess if fix obvious → If yes: present fix, if no: present options |\n| \"what are my options\" | Understand context → Generate 2-4 options → Present with trade-offs |\n| \"help me decide\" | Clarify decision factors → Compare approaches → Recommend with reasoning |\n| \"show alternatives\" | Generate alternatives → Analyze pros\u002Fcons → Present structured comparison |\n\n\n## The Bottom Line\n\n```\nDecision support → Clear options + Honest trade-offs + Reasoned recommendation\nOtherwise → Confusion + Poor decisions + Regret\n```\n\n**Understand context. Present real choices. Support with reasoning. Respect their decision.**\n",{"name":5,"description":7,"disable-model-invocation":43},true,"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-decision-support",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":43},[56,59,62],{"tool":57,"command":58},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-decision-support",{"tool":60,"command":61},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-decision-support",{"tool":63,"command":64},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill skill-decision-support","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-decision-support\u002FSKILL.md",[67],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"agents\u002Fopenai.yaml","REFERENCE","参考文档",160,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnyldn\u002Fclaude-octopus\u002Fskills\u002Fskill-decision-support\u002Fagents\u002Fopenai.yaml",[74,84,92,100,108,116],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":83},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":83},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\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":78,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":83},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":83},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":83},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":83},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]