[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P6EMJKHS2NVT6G3X4J9T2Y":3,"skill-same:01M6P6EMJKHS2NVT6G3X4J9T2Y":91},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":70,"commitSha":71,"skillDirectory":72,"forksCount":73,"repositoryHtmlUrl":74,"repositoryHomepageUrl":6,"ownerHtmlUrl":75,"ownerBlogUrl":76,"ownerDescription":6,"updatedAt":77,"install":78,"resources":90},"01M6P6EMJKHS2NVT6G3X4J9T2Y","seed-library",null,"Suggests and loads Dojo Seed Patches as reusable thinking modules, producing a ranked seed recommendation with a full application guide. Use when: 'which seed applies here', 'suggest a seed pattern', 'apply a seed to this', 'what pattern should we use', 'load the seed library'.","DojoGenesis\u002Fgateway","DojoGenesis","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273886418?v=4","01M6P54RXMD3TZ2082Z3Z4JMQP","Cruz Morales (TresPies)","01M6P54S269YR0ZZZ96WGQM439",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fseed-library\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"seed library","seed","library","wisdom","apply","for","which","sonnet","recommendation","problem","as","full","thinking","reusable","modules","use","guide","context","system","file","2026-11-10 10:12:30",false,"---\nname: seed-library\nmodel: sonnet\ndescription: \"Suggests and loads Dojo Seed Patches as reusable thinking modules, producing a ranked seed recommendation with a full application guide. Use when: 'which seed applies here', 'suggest a seed pattern', 'apply a seed to this', 'what pattern should we use', 'load the seed library'.\"\ncategory: wisdom-garden\ntriggers:\n  - \"which seed applies here\"\n  - \"suggest a seed pattern\"\n  - \"apply a seed to this\"\n  - \"what pattern should we use\"\n  - \"load the seed library\"\ntier: 1\nagents:\n  - \"primary\"\ntool_dependencies:\n  - \"file_system\"\n\ninputs:\n  - name: context\n    type: string\n    description: The current situation or problem context to match against seed patterns\n    required: true\noutputs:\n  - name: seed_recommendation\n    type: string\n    description: Ranked seed recommendation with full application guide for the current context\n---\n\n# Seed Module Library\n\nManage and apply the **10 Dojo Seed Patches** plus **3 field seeds** as reusable thinking modules. The core seeds derive from Dataiku research; the field seeds emerged from direct practice. Make enterprise-grade agent patterns accessible, consistent, and evolvable.\n\n## When to Use This Skill\n\nTrigger this skill when:\n- User asks \"What seed applies here?\" or \"Which pattern should I use?\"\n- Keywords match seed triggers (governance, multi-agent, cost, context, routing, etc.)\n- Architecting new features or systems\n- Debugging complex issues\n- Optimizing costs or performance\n- Building trust through transparency\n\n## The 10 Core Seeds\n\n1. **Three-Tiered Governance** - Strategic\u002FTactical\u002FOperational framework\n2. **Harness Trace** - Nested spans + events for traceability\n3. **Context Iceberg** - 6x token multiplier, hierarchical loading\n4. **Agent Connect** - Routing-first, not swarm-first\n5. **Go-Live Bundles** - Reusable artifacts (DojoPacket)\n6. **Cost Guard** - Budget for full iceberg (5-10x multiplier)\n7. **Safety Switch** - Fallback to conservative mode\n8. **Implicit Perspective Extraction** - Extract from constraints\u002Fmetaphors\n9. **Mode-Based Complexity Gating** - 3-question test\n10. **Shared Infrastructure** - Build once, reuse everywhere\n\n**Meta-Seed:** Governance Multiplies Velocity\n\n### Field Seeds (From Practice)\n11. **Voice Before Structure** - Read design language before writing structural artifacts\n12. **Pointer Directories** - Empty directories are references, not gaps\n13. **Granular Visibility** - Progress tracking serves the user, not the agent\n\n## Core Workflow\n\n### 1. Suggest Relevant Seeds\n\nBased on keywords or task context:\n\n```bash\npython3.11 \u002Fhome\u002Fubuntu\u002Fskills\u002Fseed-library\u002Fscripts\u002Fsuggest_seeds.py \u003Ckeywords...>\n```\n\n**Example:**\n```bash\npython3.11 suggest_seeds.py multi-agent architecture coordination\n```\n\n**Output:**\n- Top 3 relevant seeds ranked by relevance score\n- Brief description of each seed\n- File path to full seed content\n\n**Saved to:** `\u002Fhome\u002Fubuntu\u002Fseed-suggestions.md`\n\n### 2. Apply a Seed\n\nLoad full seed content and application guide:\n\n```bash\npython3.11 \u002Fhome\u002Fubuntu\u002Fskills\u002Fseed-library\u002Fscripts\u002Fapply_seed.py \u003Cseed_id> [session_id]\n```\n\n**Example:**\n```bash\npython3.11 apply_seed.py 04_agent_connect session_123\n```\n\n**Output:**\n- Full seed content (What It Is, Why It Matters, The Pattern, etc.)\n- Application checklist\n- Next steps\n- Usage tracked automatically\n\n**Saved to:** `\u002Fhome\u002Fubuntu\u002Fseed-\u003Cseed_id>-applied.md`\n\n## Script Reference\n\n### suggest_seeds.py\n\n**Purpose:** Suggest relevant seeds based on keywords\n\n**Usage:**\n```bash\npython3.11 suggest_seeds.py \u003Ckeywords...>\n```\n\n**How it works:**\n1. Matches keywords to seed triggers\n2. Calculates relevance score\n3. Returns top 3 suggestions\n\n**Trigger Keywords by Seed:**\n\n- **01 (Governance):** governance, capabilities, complexity, multi-agent, coordination, policy, standards\n- **02 (Trace):** debugging, trace, transparency, performance, evaluation, logging, monitoring\n- **03 (Context):** token, cost, context, window, limit, budget, pruning, memory, overhead\n- **04 (Agent Connect):** multi-agent, routing, coordination, specialized, handoff, permission, swarm\n- **05 (Bundles):** export, sharing, reuse, artifact, package, bundle, repeatability, trust\n- **06 (Cost Guard):** cost, budget, estimation, planning, infrastructure, investment, pricing\n- **07 (Safety Switch):** fallback, conservative, alert, drift, failure, recovery, validation, error\n- **08 (Perspective):** perspective, constraint, metaphor, scope, extraction, implicit, natural\n- **09 (Complexity):** mode, complexity, routing, simple, query, reasoning, adaptive\n- **10 (Infrastructure):** infrastructure, reuse, duplication, foundation, shared, common, service\n- **11 (Voice):** voice, philosophy, design-language, manifest, description, ecosystem, grounding, plugin\n- **12 (Pointers):** empty, missing, pointer, provenance, registry, audit, gap, coverage, directory\n- **13 (Visibility):** progress, tracking, visibility, todo, granular, steering, trust, delegation\n\n### apply_seed.py\n\n**Purpose:** Load and explain how to apply a seed\n\n**Usage:**\n```bash\npython3.11 apply_seed.py \u003Cseed_id> [session_id]\n```\n\n**What it does:**\n1. Loads full seed content from `\u002Fseeds\u002F\u003Cseed_id>.md`\n2. Generates application guide with checklist\n3. Tracks usage in `\u002Fhome\u002Fubuntu\u002F.seed-usage.json`\n4. Saves guide to file\n\n**Seed IDs:**\n- `01_three_tiered_governance`\n- `02_harness_trace`\n- `03_context_iceberg`\n- `04_agent_connect`\n- `05_go_live_bundles`\n- `06_cost_guard`\n- `07_safety_switch`\n- `08_implicit_perspective_extraction`\n- `09_mode_based_complexity_gating`\n- `10_shared_infrastructure`\n- `meta_governance_multiplies_velocity`\n- `11_voice_before_structure`\n- `12_pointer_directories`\n- `13_granular_visibility`\n\n## Seed Files\n\nAll seeds are stored in `\u002Fhome\u002Fubuntu\u002Fskills\u002Fseed-library\u002Fseeds\u002F` as markdown files.\n\n### Seed File Structure\n\n```markdown\n---\nseed_id: 01\nname: Three-Tiered Governance\nversion: 1.0\ncreated: 2026-01-12\nsource: Dataiku Research\nstatus: active\n---\n\n# Seed Name\n\n## What It Is\n{description}\n\n## Why It Matters\n{rationale}\n\n## The Pattern\n{pattern description}\n\n## Revisit Trigger\n{when to apply this seed}\n\n## Dojo Application\n{how Dojo uses this pattern}\n\n## What It Refuses\n{what this pattern explicitly rejects}\n\n## Checks\n- [ ] {validation check 1}\n- [ ] {validation check 2}\n\n## Related Seeds\n- {seed name}: {relationship}\n```\n\n## Usage Tracking\n\nThe skill automatically tracks seed usage in `\u002Fhome\u002Fubuntu\u002F.seed-usage.json`:\n\n```json\n{\n  \"seeds\": {\n    \"04_agent_connect\": {\n      \"usage_count\": 3,\n      \"last_used\": \"2026-01-29T12:00:00Z\",\n      \"sessions\": [\"session_123\", \"session_456\"]\n    }\n  },\n  \"session_seeds\": {\n    \"session_123\": [\"04_agent_connect\", \"10_shared_infrastructure\"]\n  }\n}\n```\n\n## Reference Documents\n\n### seed_catalog.md\n\nQuick reference to all 10 seeds plus meta-seed:\n- One-line descriptions\n- Triggers and refusals\n- Seed relationships\n- Usage patterns (5 common scenarios)\n- Maintenance guidelines\n\n**Read this when:**\n- Getting overview of all seeds\n- Understanding seed relationships\n- Learning usage patterns\n\n## Common Use Cases\n\n### Use Case 1: Architecting Multi-Agent System\n\n**User says:** \"How should we architect the multi-agent system?\"\n\n**Workflow:**\n1. Run `suggest_seeds.py multi-agent architecture coordination`\n2. Top suggestions: Agent Connect, Shared Infrastructure, Three-Tiered Governance\n3. Apply Seed 04 (Agent Connect)\n4. Follow application checklist\n5. Track usage\n\n**Output:**\n> Based on your query, I recommend **Agent Connect** (Seed 04). This seed provides a routing-first pattern where the Supervisor acts as a single entry point, routing to specialized agents (Dojo, Librarian, Debugger, Builder) based on context. This prevents agent sprawl and keeps coordination manageable.\n\n### Use Case 2: Optimizing Token Usage\n\n**User says:** \"Token usage is spiking, how do we optimize?\"\n\n**Workflow:**\n1. Run `suggest_seeds.py token cost context optimization`\n2. Top suggestions: Context Iceberg, Cost Guard, Mode-Based Complexity Gating\n3. Apply Seed 03 (Context Iceberg)\n4. Implement hierarchical context loading (Tier 1-4)\n5. Set pruning triggers (80%, 90%, 95%)\n\n**Output:**\n> The **Context Iceberg** pattern (Seed 03) explains the 6x token multiplier from demo to production. Implement hierarchical context loading with 4 tiers, and set pruning triggers at 80% (prune Tier 4), 90% (prune Tier 3), and 95% (alert user).\n\n### Use Case 3: Debugging Unexpected Behavior\n\n**User says:** \"Why did Dojo choose Scout instead of Mirror?\"\n\n**Workflow:**\n1. Run `suggest_seeds.py debugging trace transparency`\n2. Top suggestion: Harness Trace\n3. Apply Seed 02 (Harness Trace)\n4. Review trace spans for `mode_selection`\n5. Read `metadata.reasoning`\n\n**Output:**\n> Use the **Harness Trace** (Seed 02) to inspect the decision path. Check the `mode_selection` span in the trace JSON. The `metadata.reasoning` field will explain why Scout was chosen over Mirror.\n\n### Use Case 4: Building Trust with Users\n\n**User says:** \"Users don't understand our recommendations\"\n\n**Workflow:**\n1. Run `suggest_seeds.py trust transparency trace`\n2. Top suggestions: Harness Trace, Go-Live Bundles, Governance Multiplies Velocity\n3. Apply Seed 02 (Harness Trace) for transparency\n4. Apply Seed 05 (Go-Live Bundles) for repeatability\n5. Apply Meta-Seed for philosophy\n\n**Output:**\n> Build trust through **Harness Trace** (transparency), **Go-Live Bundles** (repeatability), and the **Governance Multiplies Velocity** philosophy. Show users the decision path, make sessions exportable and inspectable, and emphasize that governance accelerates delivery.\n\n### Use Case 5: Planning New Feature\n\n**User says:** \"Let's plan the Workbench feature\"\n\n**Workflow:**\n1. Run `suggest_seeds.py planning feature governance`\n2. Top suggestions: Three-Tiered Governance, Cost Guard, Shared Infrastructure\n3. Apply Seed 01 (Three-Tiered Governance)\n4. Define strategic (principles), tactical (standards), operational (tools)\n5. Apply Seed 06 (Cost Guard) to budget for 5-10x multiplier\n\n**Output:**\n> Start with **Three-Tiered Governance** (Seed 01). Define strategic principles (does this align with \"no autopilot\"?), tactical standards (DojoPacket schema, routing logic), and operational tools (tests, traces). Then apply **Cost Guard** (Seed 06) to budget for the full iceberg, not just API costs.\n\n## Integration with Dojo Agent\n\nWhen Dojo is reasoning, it can reference seeds:\n\n**Example:**\n> \"Considering **Agent Connect** (Seed 04) for this multi-agent architecture. Using Supervisor as router with transparent handoffs.\"\n\n**Example:**\n> \"Applying **Context Iceberg** (Seed 03) to manage token usage. Loading Tier 1 + Tier 2 context for this query.\"\n\n## Seed Relationships\n\n### Foundational Seeds (Start Here)\n- **01. Three-Tiered Governance** - Framework for all other seeds\n- **Meta. Governance Multiplies Velocity** - Philosophy\n\n### Operational Seeds (Day-to-Day)\n- **02. Harness Trace** - Transparency and debugging\n- **03. Context Iceberg** - Token and cost management\n- **07. Safety Switch** - Error handling\n- **09. Mode-Based Complexity Gating** - Query routing\n\n### Architectural Seeds (System Design)\n- **04. Agent Connect** - Multi-agent coordination\n- **10. Shared Infrastructure** - Reusable services\n\n### Delivery Seeds (Shipping)\n- **05. Go-Live Bundles** - Packaging and reuse\n- **06. Cost Guard** - Budgeting and planning\n\n### UX Seeds (User Experience)\n- **08. Implicit Perspective Extraction** - Reduce friction\n\n### Field Seeds (From Practice)\n- **11. Voice Before Structure** - Ground in philosophy before writing\n- **12. Pointer Directories** - Understand provenance before filling gaps\n- **13. Granular Visibility** - Track progress for the user, not the agent\n\n## Seed Maintenance\n\n### When to Update a Seed\n- Pattern evolves based on new learnings\n- Better approach discovered\n- User feedback suggests improvement\n\n### When to Archive a Seed\n- Pattern no longer applies\n- Superseded by better approach\n- Context has fundamentally changed\n\n### Versioning Convention\n- **1.0** - Initial version from Dataiku research\n- **1.1** - Minor update (clarification, example added)\n- **2.0** - Major update (pattern changed)\n\n### Update Process\n1. Identify need for update\n2. Draft new version\n3. Test with real scenarios\n4. Update seed file with \"Revised:\" section\n5. Update seed_catalog.md\n6. Notify users of change\n\n## Best Practices\n\n### Frequency\n- **Proactive:** Suggest seeds during planning and design\n- **Reactive:** Apply seeds when debugging or optimizing\n- **Continuous:** Track usage to identify most valuable seeds\n\n### Application\n- **Read the full seed** before applying (don't just skim)\n- **Follow the checklist** to validate application\n- **Note what it refuses** to avoid anti-patterns\n- **Track usage** to measure effectiveness\n\n### Evolution\n- **Update when patterns evolve** (not just for the sake of updating)\n- **Archive when obsolete** (don't hoard outdated seeds)\n- **Version carefully** (breaking changes = major version bump)\n\n## Limitations\n\n### What This Skill Does\n- Suggest relevant seeds based on keywords\n- Load and explain how to apply seeds\n- Track usage over time\n- Provide quick reference to all seeds\n\n### What This Skill Doesn't Do\n- Automatically apply seeds (you still need to implement)\n- Make architectural decisions for you\n- Guarantee success (seeds are patterns, not silver bullets)\n- Replace deep thinking (seeds guide, they don't replace reasoning)\n\n## Quick Reference\n\n| Task | Command |\n|------|---------|\n| Suggest seeds | `python3.11 suggest_seeds.py \u003Ckeywords...>` |\n| Apply seed | `python3.11 apply_seed.py \u003Cseed_id>` |\n| View catalog | `file read references\u002Fseed_catalog.md` |\n| Check usage | `cat \u002Fhome\u002Fubuntu\u002F.seed-usage.json` |\n| List all seeds | `ls \u002Fhome\u002Fubuntu\u002Fskills\u002Fseed-library\u002Fseeds\u002F` |\n\n## Success Metrics\n\n- **Accessibility:** Find relevant seed in \u003C 10 seconds\n- **Consistency:** Seeds applied correctly 90%+ of the time\n- **Evolution:** Seeds updated when patterns improve\n- **Reuse:** Seeds used across multiple sessions\n- **Learning:** New seeds added as patterns emerge\n\n## Output\n\n- A seed recommendation saved to `\u002Fhome\u002Fubuntu\u002Fseed-suggestions.md` — top 3 ranked seeds with relevance scores and file paths\n- A seed application guide saved to `\u002Fhome\u002Fubuntu\u002Fseed-\u003Cseed_id>-applied.md` — full seed content, application checklist, and next steps\n- Usage tracked automatically in `\u002Fhome\u002Fubuntu\u002F.seed-usage.json`\n\n## Examples\n\n**Scenario 1:** User says \"which seed applies to multi-agent coordination?\" → runs `suggest_seeds.py multi-agent coordination`, returns top 3 (Agent Connect, Three-Tiered Governance, Shared Infrastructure) with relevance scores, saves to `seed-suggestions.md`.\n\n**Scenario 2:** User says \"apply the Context Iceberg seed\" → runs `apply_seed.py 03_context_iceberg`, loads full seed content, generates application checklist for the current task, saves guide to `seed-03_context_iceberg-applied.md`.\n\n## Edge Cases\n\n- If no keywords match any seed triggers, prompt the user for the core problem being solved (cost? coordination? trust?) rather than returning an empty result.\n- If the user requests a seed by name that does not exist in the library, list the 13 available seeds and ask for clarification.\n\n## Anti-Patterns\n\n- Suggesting a seed without running the suggestion script — keyword matching is essential for relevance; do not rely on recall alone.\n- Applying a seed without reading the full seed content — skimming the trigger and skipping \"What It Refuses\" leads to misapplication.\n","# Seed Module Library\n\nManage and apply the **10 Dojo Seed Patches** plus **3 field seeds** as reusable thinking modules. The core seeds derive from Dataiku research; the field seeds emerged from direct practice. Make enterprise-grade agent patterns accessible, consistent, and evolvable.\n\n## When to Use This Skill\n\nTrigger this skill when:\n- User asks \"What seed applies here?\" or \"Which pattern should I use?\"\n- Keywords match seed triggers (governance, multi-agent, cost, context, routing, etc.)\n- Architecting new features or systems\n- Debugging complex issues\n- Optimizing costs or performance\n- Building trust through transparency\n\n## The 10 Core Seeds\n\n1. **Three-Tiered Governance** - Strategic\u002FTactical\u002FOperational framework\n2. **Harness Trace** - Nested spans + events for traceability\n3. **Context Iceberg** - 6x token multiplier, hierarchical loading\n4. **Agent Connect** - Routing-first, not swarm-first\n5. **Go-Live Bundles** - Reusable artifacts (DojoPacket)\n6. **Cost Guard** - Budget for full iceberg (5-10x multiplier)\n7. **Safety Switch** - Fallback to conservative mode\n8. **Implicit Perspective Extraction** - Extract from constraints\u002Fmetaphors\n9. **Mode-Based Complexity Gating** - 3-question test\n10. **Shared Infrastructure** - Build once, reuse everywhere\n\n**Meta-Seed:** Governance Multiplies Velocity\n\n### Field Seeds (From Practice)\n11. **Voice Before Structure** - Read design language before writing structural artifacts\n12. **Pointer Directories** - Empty directories are references, not gaps\n13. **Granular Visibility** - Progress tracking serves the user, not the agent\n\n## Core Workflow\n\n### 1. Suggest Relevant Seeds\n\nBased on keywords or task context:\n\n```bash\npython3.11 \u002Fhome\u002Fubuntu\u002Fskills\u002Fseed-library\u002Fscripts\u002Fsuggest_seeds.py \u003Ckeywords...>\n```\n\n**Example:**\n```bash\npython3.11 suggest_seeds.py multi-agent architecture coordination\n```\n\n**Output:**\n- Top 3 relevant seeds ranked by relevance score\n- Brief description of each seed\n- File path to full seed content\n\n**Saved to:** `\u002Fhome\u002Fubuntu\u002Fseed-suggestions.md`\n\n### 2. Apply a Seed\n\nLoad full seed content and application guide:\n\n```bash\npython3.11 \u002Fhome\u002Fubuntu\u002Fskills\u002Fseed-library\u002Fscripts\u002Fapply_seed.py \u003Cseed_id> [session_id]\n```\n\n**Example:**\n```bash\npython3.11 apply_seed.py 04_agent_connect session_123\n```\n\n**Output:**\n- Full seed content (What It Is, Why It Matters, The Pattern, etc.)\n- Application checklist\n- Next steps\n- Usage tracked automatically\n\n**Saved to:** `\u002Fhome\u002Fubuntu\u002Fseed-\u003Cseed_id>-applied.md`\n\n## Script Reference\n\n### suggest_seeds.py\n\n**Purpose:** Suggest relevant seeds based on keywords\n\n**Usage:**\n```bash\npython3.11 suggest_seeds.py \u003Ckeywords...>\n```\n\n**How it works:**\n1. Matches keywords to seed triggers\n2. Calculates relevance score\n3. Returns top 3 suggestions\n\n**Trigger Keywords by Seed:**\n\n- **01 (Governance):** governance, capabilities, complexity, multi-agent, coordination, policy, standards\n- **02 (Trace):** debugging, trace, transparency, performance, evaluation, logging, monitoring\n- **03 (Context):** token, cost, context, window, limit, budget, pruning, memory, overhead\n- **04 (Agent Connect):** multi-agent, routing, coordination, specialized, handoff, permission, swarm\n- **05 (Bundles):** export, sharing, reuse, artifact, package, bundle, repeatability, trust\n- **06 (Cost Guard):** cost, budget, estimation, planning, infrastructure, investment, pricing\n- **07 (Safety Switch):** fallback, conservative, alert, drift, failure, recovery, validation, error\n- **08 (Perspective):** perspective, constraint, metaphor, scope, extraction, implicit, natural\n- **09 (Complexity):** mode, complexity, routing, simple, query, reasoning, adaptive\n- **10 (Infrastructure):** infrastructure, reuse, duplication, foundation, shared, common, service\n- **11 (Voice):** voice, philosophy, design-language, manifest, description, ecosystem, grounding, plugin\n- **12 (Pointers):** empty, missing, pointer, provenance, registry, audit, gap, coverage, directory\n- **13 (Visibility):** progress, tracking, visibility, todo, granular, steering, trust, delegation\n\n### apply_seed.py\n\n**Purpose:** Load and explain how to apply a seed\n\n**Usage:**\n```bash\npython3.11 apply_seed.py \u003Cseed_id> [session_id]\n```\n\n**What it does:**\n1. Loads full seed content from `\u002Fseeds\u002F\u003Cseed_id>.md`\n2. Generates application guide with checklist\n3. Tracks usage in `\u002Fhome\u002Fubuntu\u002F.seed-usage.json`\n4. Saves guide to file\n\n**Seed IDs:**\n- `01_three_tiered_governance`\n- `02_harness_trace`\n- `03_context_iceberg`\n- `04_agent_connect`\n- `05_go_live_bundles`\n- `06_cost_guard`\n- `07_safety_switch`\n- `08_implicit_perspective_extraction`\n- `09_mode_based_complexity_gating`\n- `10_shared_infrastructure`\n- `meta_governance_multiplies_velocity`\n- `11_voice_before_structure`\n- `12_pointer_directories`\n- `13_granular_visibility`\n\n## Seed Files\n\nAll seeds are stored in `\u002Fhome\u002Fubuntu\u002Fskills\u002Fseed-library\u002Fseeds\u002F` as markdown files.\n\n### Seed File Structure\n\n```markdown\n---\nseed_id: 01\nname: Three-Tiered Governance\nversion: 1.0\ncreated: 2026-01-12\nsource: Dataiku Research\nstatus: active\n---\n\n# Seed Name\n\n## What It Is\n{description}\n\n## Why It Matters\n{rationale}\n\n## The Pattern\n{pattern description}\n\n## Revisit Trigger\n{when to apply this seed}\n\n## Dojo Application\n{how Dojo uses this pattern}\n\n## What It Refuses\n{what this pattern explicitly rejects}\n\n## Checks\n- [ ] {validation check 1}\n- [ ] {validation check 2}\n\n## Related Seeds\n- {seed name}: {relationship}\n```\n\n## Usage Tracking\n\nThe skill automatically tracks seed usage in `\u002Fhome\u002Fubuntu\u002F.seed-usage.json`:\n\n```json\n{\n  \"seeds\": {\n    \"04_agent_connect\": {\n      \"usage_count\": 3,\n      \"last_used\": \"2026-01-29T12:00:00Z\",\n      \"sessions\": [\"session_123\", \"session_456\"]\n    }\n  },\n  \"session_seeds\": {\n    \"session_123\": [\"04_agent_connect\", \"10_shared_infrastructure\"]\n  }\n}\n```\n\n## Reference Documents\n\n### seed_catalog.md\n\nQuick reference to all 10 seeds plus meta-seed:\n- One-line descriptions\n- Triggers and refusals\n- Seed relationships\n- Usage patterns (5 common scenarios)\n- Maintenance guidelines\n\n**Read this when:**\n- Getting overview of all seeds\n- Understanding seed relationships\n- Learning usage patterns\n\n## Common Use Cases\n\n### Use Case 1: Architecting Multi-Agent System\n\n**User says:** \"How should we architect the multi-agent system?\"\n\n**Workflow:**\n1. Run `suggest_seeds.py multi-agent architecture coordination`\n2. Top suggestions: Agent Connect, Shared Infrastructure, Three-Tiered Governance\n3. Apply Seed 04 (Agent Connect)\n4. Follow application checklist\n5. Track usage\n\n**Output:**\n> Based on your query, I recommend **Agent Connect** (Seed 04). This seed provides a routing-first pattern where the Supervisor acts as a single entry point, routing to specialized agents (Dojo, Librarian, Debugger, Builder) based on context. This prevents agent sprawl and keeps coordination manageable.\n\n### Use Case 2: Optimizing Token Usage\n\n**User says:** \"Token usage is spiking, how do we optimize?\"\n\n**Workflow:**\n1. Run `suggest_seeds.py token cost context optimization`\n2. Top suggestions: Context Iceberg, Cost Guard, Mode-Based Complexity Gating\n3. Apply Seed 03 (Context Iceberg)\n4. Implement hierarchical context loading (Tier 1-4)\n5. Set pruning triggers (80%, 90%, 95%)\n\n**Output:**\n> The **Context Iceberg** pattern (Seed 03) explains the 6x token multiplier from demo to production. Implement hierarchical context loading with 4 tiers, and set pruning triggers at 80% (prune Tier 4), 90% (prune Tier 3), and 95% (alert user).\n\n### Use Case 3: Debugging Unexpected Behavior\n\n**User says:** \"Why did Dojo choose Scout instead of Mirror?\"\n\n**Workflow:**\n1. Run `suggest_seeds.py debugging trace transparency`\n2. Top suggestion: Harness Trace\n3. Apply Seed 02 (Harness Trace)\n4. Review trace spans for `mode_selection`\n5. Read `metadata.reasoning`\n\n**Output:**\n> Use the **Harness Trace** (Seed 02) to inspect the decision path. Check the `mode_selection` span in the trace JSON. The `metadata.reasoning` field will explain why Scout was chosen over Mirror.\n\n### Use Case 4: Building Trust with Users\n\n**User says:** \"Users don't understand our recommendations\"\n\n**Workflow:**\n1. Run `suggest_seeds.py trust transparency trace`\n2. Top suggestions: Harness Trace, Go-Live Bundles, Governance Multiplies Velocity\n3. Apply Seed 02 (Harness Trace) for transparency\n4. Apply Seed 05 (Go-Live Bundles) for repeatability\n5. Apply Meta-Seed for philosophy\n\n**Output:**\n> Build trust through **Harness Trace** (transparency), **Go-Live Bundles** (repeatability), and the **Governance Multiplies Velocity** philosophy. Show users the decision path, make sessions exportable and inspectable, and emphasize that governance accelerates delivery.\n\n### Use Case 5: Planning New Feature\n\n**User says:** \"Let's plan the Workbench feature\"\n\n**Workflow:**\n1. Run `suggest_seeds.py planning feature governance`\n2. Top suggestions: Three-Tiered Governance, Cost Guard, Shared Infrastructure\n3. Apply Seed 01 (Three-Tiered Governance)\n4. Define strategic (principles), tactical (standards), operational (tools)\n5. Apply Seed 06 (Cost Guard) to budget for 5-10x multiplier\n\n**Output:**\n> Start with **Three-Tiered Governance** (Seed 01). Define strategic principles (does this align with \"no autopilot\"?), tactical standards (DojoPacket schema, routing logic), and operational tools (tests, traces). Then apply **Cost Guard** (Seed 06) to budget for the full iceberg, not just API costs.\n\n## Integration with Dojo Agent\n\nWhen Dojo is reasoning, it can reference seeds:\n\n**Example:**\n> \"Considering **Agent Connect** (Seed 04) for this multi-agent architecture. Using Supervisor as router with transparent handoffs.\"\n\n**Example:**\n> \"Applying **Context Iceberg** (Seed 03) to manage token usage. Loading Tier 1 + Tier 2 context for this query.\"\n\n## Seed Relationships\n\n### Foundational Seeds (Start Here)\n- **01. Three-Tiered Governance** - Framework for all other seeds\n- **Meta. Governance Multiplies Velocity** - Philosophy\n\n### Operational Seeds (Day-to-Day)\n- **02. Harness Trace** - Transparency and debugging\n- **03. Context Iceberg** - Token and cost management\n- **07. Safety Switch** - Error handling\n- **09. Mode-Based Complexity Gating** - Query routing\n\n### Architectural Seeds (System Design)\n- **04. Agent Connect** - Multi-agent coordination\n- **10. Shared Infrastructure** - Reusable services\n\n### Delivery Seeds (Shipping)\n- **05. Go-Live Bundles** - Packaging and reuse\n- **06. Cost Guard** - Budgeting and planning\n\n### UX Seeds (User Experience)\n- **08. Implicit Perspective Extraction** - Reduce friction\n\n### Field Seeds (From Practice)\n- **11. Voice Before Structure** - Ground in philosophy before writing\n- **12. Pointer Directories** - Understand provenance before filling gaps\n- **13. Granular Visibility** - Track progress for the user, not the agent\n\n## Seed Maintenance\n\n### When to Update a Seed\n- Pattern evolves based on new learnings\n- Better approach discovered\n- User feedback suggests improvement\n\n### When to Archive a Seed\n- Pattern no longer applies\n- Superseded by better approach\n- Context has fundamentally changed\n\n### Versioning Convention\n- **1.0** - Initial version from Dataiku research\n- **1.1** - Minor update (clarification, example added)\n- **2.0** - Major update (pattern changed)\n\n### Update Process\n1. Identify need for update\n2. Draft new version\n3. Test with real scenarios\n4. Update seed file with \"Revised:\" section\n5. Update seed_catalog.md\n6. Notify users of change\n\n## Best Practices\n\n### Frequency\n- **Proactive:** Suggest seeds during planning and design\n- **Reactive:** Apply seeds when debugging or optimizing\n- **Continuous:** Track usage to identify most valuable seeds\n\n### Application\n- **Read the full seed** before applying (don't just skim)\n- **Follow the checklist** to validate application\n- **Note what it refuses** to avoid anti-patterns\n- **Track usage** to measure effectiveness\n\n### Evolution\n- **Update when patterns evolve** (not just for the sake of updating)\n- **Archive when obsolete** (don't hoard outdated seeds)\n- **Version carefully** (breaking changes = major version bump)\n\n## Limitations\n\n### What This Skill Does\n- Suggest relevant seeds based on keywords\n- Load and explain how to apply seeds\n- Track usage over time\n- Provide quick reference to all seeds\n\n### What This Skill Doesn't Do\n- Automatically apply seeds (you still need to implement)\n- Make architectural decisions for you\n- Guarantee success (seeds are patterns, not silver bullets)\n- Replace deep thinking (seeds guide, they don't replace reasoning)\n\n## Quick Reference\n\n| Task | Command |\n|------|---------|\n| Suggest seeds | `python3.11 suggest_seeds.py \u003Ckeywords...>` |\n| Apply seed | `python3.11 apply_seed.py \u003Cseed_id>` |\n| View catalog | `file read references\u002Fseed_catalog.md` |\n| Check usage | `cat \u002Fhome\u002Fubuntu\u002F.seed-usage.json` |\n| List all seeds | `ls \u002Fhome\u002Fubuntu\u002Fskills\u002Fseed-library\u002Fseeds\u002F` |\n\n## Success Metrics\n\n- **Accessibility:** Find relevant seed in \u003C 10 seconds\n- **Consistency:** Seeds applied correctly 90%+ of the time\n- **Evolution:** Seeds updated when patterns improve\n- **Reuse:** Seeds used across multiple sessions\n- **Learning:** New seeds added as patterns emerge\n\n## Output\n\n- A seed recommendation saved to `\u002Fhome\u002Fubuntu\u002Fseed-suggestions.md` — top 3 ranked seeds with relevance scores and file paths\n- A seed application guide saved to `\u002Fhome\u002Fubuntu\u002Fseed-\u003Cseed_id>-applied.md` — full seed content, application checklist, and next steps\n- Usage tracked automatically in `\u002Fhome\u002Fubuntu\u002F.seed-usage.json`\n\n## Examples\n\n**Scenario 1:** User says \"which seed applies to multi-agent coordination?\" → runs `suggest_seeds.py multi-agent coordination`, returns top 3 (Agent Connect, Three-Tiered Governance, Shared Infrastructure) with relevance scores, saves to `seed-suggestions.md`.\n\n**Scenario 2:** User says \"apply the Context Iceberg seed\" → runs `apply_seed.py 03_context_iceberg`, loads full seed content, generates application checklist for the current task, saves guide to `seed-03_context_iceberg-applied.md`.\n\n## Edge Cases\n\n- If no keywords match any seed triggers, prompt the user for the core problem being solved (cost? coordination? trust?) rather than returning an empty result.\n- If the user requests a seed by name that does not exist in the library, list the 13 available seeds and ask for clarification.\n\n## Anti-Patterns\n\n- Suggesting a seed without running the suggestion script — keyword matching is essential for relevance; do not rely on recall alone.\n- Applying a seed without reading the full seed content — skimming the trigger and skipping \"What It Refuses\" leads to misapplication.\n",{"name":5,"tier":49,"model":31,"agents":50,"inputs":52,"outputs":57,"category":61,"triggers":62,"description":7,"tool_dependencies":68},1,[51],"primary",[53],{"name":41,"type":54,"required":55,"description":56},"string",true,"The current situation or problem context to match against seed patterns",[58],{"name":59,"type":54,"description":60},"seed_recommendation","Ranked seed recommendation with full application guide for the current context","wisdom-garden",[63,64,65,66,67],"which seed applies here","suggest a seed pattern","apply a seed to this","what pattern should we use","load the seed library",[69],"file_system","main","ff07df5fd8f75762c2a131e6e26d297e8ae403ee","plugins\u002Fwisdom-garden\u002Fskills\u002Fseed-library",0,"https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway","https:\u002F\u002Fgithub.com\u002FDojoGenesis","dojogenesis.com","2026-10-25 22:59:58",{"source":8,"skillName":5,"commands":79,"prompt":89,"zipAvailable":55},[80,83,86],{"tool":81,"command":82},"npx","npx skills add DojoGenesis\u002Fgateway --skill seed-library",{"tool":84,"command":85},"bunx","bunx skills add DojoGenesis\u002Fgateway --skill seed-library",{"tool":87,"command":88},"pnpm","pnpm dlx skills add DojoGenesis\u002Fgateway --skill seed-library","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fseed-library\u002FSKILL.md",[],[92,111,122,130,171,195],{"skillNo":93,"name":94,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":100,"publishedAt":44},"01M6P6J0WYSD1MTGA3ZX6MGGZ5","kata-test-echo","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-test-echo\u002FSKILL.md",[97],{"categoryNo":98,"categoryName":99,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[101,102,103,104,105,106,107,108,109,110],"kata test echo","Echo","test","json","v1","output","input","structured","contracts","schema",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":118,"publishedAt":44},"01M6P6HQJNGG4WPZW0DEWMAY2N","kata-plain","An ordinary prose skill; not dispatchable.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-plain\u002FSKILL.md",[117],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[119,120,121],"kata plain","prose skill","prose",{"skillNo":123,"name":124,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":44},"01M6P6HH6Y7K8K6606MF7VZ1HB","kata-broken","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-broken\u002FSKILL.md",[],[128,129,108,109,102,110,104,103,107,105,106],"kata broken","broken",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":150,"publishedAt":44},"01M6P6GW520QJ03A6K7Y5PWJ52","voice-before-structure","Read the project's design language and philosophy before writing structural artifacts. Ground manifests, READMEs, and descriptions in the project's voice, not boilerplate. Use when creating manifests or READMEs for established projects, writing ecosystem-level documentation, building plugin descriptions or marketplace metadata, or authoring metadata that carries a project's identity. Trigger phrases: 'write the manifest', 'create a README', 'describe this plugin', 'ground yourself in the philosophy', 'ecosystem-level work'.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fvoice-before-structure\u002FSKILL.md",[136,139,142,147],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":143,"categoryName":144,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":148,"categoryName":149,"taxonomyType":145,"taxonomyTypeDesc":146},"01JBSEEDCAT000000000000036","内容创作者",[151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170],"voice before structure","structure","voice","manifests","ecosystem","false","authoring","structural","project","artifact","philosophy","design","writing","identity","documentation","create","projects","work","read","write",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":178,"publishedAt":44},"01M6P6GMNA4HJ4D5RRM3BQZ73M","system-prompt-archaeology","Produces a named ADA disposition preset (YAML) and a layered behavioral analysis (structural decomposition + evidence-cited classifications) from a system prompt. Use when: \"analyze this system prompt\", \"extract disposition from prompt\", \"reverse-engineer agent behavior\", \"what patterns does this prompt use\", \"build a preset from this prompt\".","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fsystem-prompt-archaeology\u002FSKILL.md",[177],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[179,180,181,42,182,183,158,184,27,185,186,187,188,189,190,191,192,31,193,194],"system prompt archaeology","system prompt","prompt","behavioral","classify","decomposition","patterns","engineer","decompose","evidence","ada","analyze","analysis","STRING","true","reverse",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":202,"publishedAt":44},"01M6P6G2D70T9R00HX6K154X5Y","session-lifecycle-automation","Designs and configures all three loops of solo-operator session automation — session bookends, background maintenance agents, and a delegation flywheel. Use when setting up a new workspace, recovering from the 44% zero-artifact session leak, or preparing to scale delegation across multiple concurrent agents.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fsession-lifecycle-automation\u002FSKILL.md",[201],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[203,204,205,206,207,208,209,210,211,212,213,214,215,160,216,217,218,219,220,221],"automation","session lifecycle automation","session lifecycle","lifecycle","session","markdown","configure","directory","config","delegation","audit","SET","files","solo","across","scheduled","loops","up","template"]