[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B1Q5TY0PRMZFSPW6MWQCAP":3,"skill-same:01M7B1Q5TY0PRMZFSPW6MWQCAP":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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M7B1Q5TY0PRMZFSPW6MWQCAP","subagent-driven-development",null,"Execute plans via delegate_task subagents (2-stage review).","dbillion\u002Fhermes-skills-public","dbillion","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F49393855?v=4","01M7AVH8QPGCM8WKWS22TRT0T6","Oludayo Adeoye","01M7AVH8RD1JJWA0YS9CFEWAV9",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: subagent-driven-development\ndescription: \"Execute plans via delegate_task subagents (2-stage review).\"\nversion: 1.1.0\nauthor: Hermes Agent (adapted from obra\u002Fsuperpowers)\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [delegation, subagent, implementation, workflow, parallel]\n    related_skills: [writing-plans, requesting-code-review, test-driven-development]\n---\n\n# Subagent-Driven Development\n\n## Overview\n\nExecute implementation plans by dispatching fresh subagents per task with systematic two-stage review.\n\n**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.\n\n## When to Use\n\nUse this skill when:\n- You have an implementation plan (from writing-plans skill or user requirements)\n- Tasks are mostly independent\n- Quality and spec compliance are important\n- You want automated review between tasks\n\n**vs. manual execution:**\n- Fresh context per task (no confusion from accumulated state)\n- Automated review process catches issues early\n- Consistent quality checks across all tasks\n- Subagents can ask questions before starting work\n\n## The Process\n\n### 1. Read and Parse Plan\n\nRead the plan file. Extract ALL tasks with their full text and context upfront. Create a todo list:\n\n```python\n# Read the plan\nread_file(\"docs\u002Fplans\u002Ffeature-plan.md\")\n\n# Create todo list with all tasks\ntodo([\n    {\"id\": \"task-1\", \"content\": \"Create User model with email field\", \"status\": \"pending\"},\n    {\"id\": \"task-2\", \"content\": \"Add password hashing utility\", \"status\": \"pending\"},\n    {\"id\": \"task-3\", \"content\": \"Create login endpoint\", \"status\": \"pending\"},\n])\n```\n\n**Key:** Read the plan ONCE. Extract everything. Don't make subagents read the plan file — provide the full task text directly in context.\n\n### 2. Per-Task Workflow\n\nFor EACH task in the plan:\n\n#### Step 1: Dispatch Implementer Subagent\n\nUse `delegate_task` with complete context:\n\n```python\ndelegate_task(\n    goal=\"Implement Task 1: Create User model with email and password_hash fields\",\n    context=\"\"\"\n    TASK FROM PLAN:\n    - Create: src\u002Fmodels\u002Fuser.py\n    - Add User class with email (str) and password_hash (str) fields\n    - Use bcrypt for password hashing\n    - Include __repr__ for debugging\n\n    FOLLOW TDD:\n    1. Write failing test in tests\u002Fmodels\u002Ftest_user.py\n    2. Run: pytest tests\u002Fmodels\u002Ftest_user.py -v (verify FAIL)\n    3. Write minimal implementation\n    4. Run: pytest tests\u002Fmodels\u002Ftest_user.py -v (verify PASS)\n    5. Run: pytest tests\u002F -q (verify no regressions)\n    6. Commit: git add -A && git commit -m \"feat: add User model with password hashing\"\n\n    PROJECT CONTEXT:\n    - Python 3.11, Flask app in src\u002Fapp.py\n    - Existing models in src\u002Fmodels\u002F\n    - Tests use pytest, run from project root\n    - bcrypt already in requirements.txt\n    \"\"\",\n    toolsets=['terminal', 'file']\n)\n```\n\n#### Step 2: Dispatch Spec Compliance Reviewer\n\nAfter the implementer completes, verify against the original spec:\n\n```python\ndelegate_task(\n    goal=\"Review if implementation matches the spec from the plan\",\n    context=\"\"\"\n    ORIGINAL TASK SPEC:\n    - Create src\u002Fmodels\u002Fuser.py with User class\n    - Fields: email (str), password_hash (str)\n    - Use bcrypt for password hashing\n    - Include __repr__\n\n    CHECK:\n    - [ ] All requirements from spec implemented?\n    - [ ] File paths match spec?\n    - [ ] Function signatures match spec?\n    - [ ] Behavior matches expected?\n    - [ ] Nothing extra added (no scope creep)?\n\n    OUTPUT: PASS or list of specific spec gaps to fix.\n    \"\"\",\n    toolsets=['file']\n)\n```\n\n**If spec issues found:** Fix gaps, then re-run spec review. Continue only when spec-compliant.\n\n#### Step 3: Dispatch Code Quality Reviewer\n\nAfter spec compliance passes:\n\n```python\ndelegate_task(\n    goal=\"Review code quality for Task 1 implementation\",\n    context=\"\"\"\n    FILES TO REVIEW:\n    - src\u002Fmodels\u002Fuser.py\n    - tests\u002Fmodels\u002Ftest_user.py\n\n    CHECK:\n    - [ ] Follows project conventions and style?\n    - [ ] Proper error handling?\n    - [ ] Clear variable\u002Ffunction names?\n    - [ ] Adequate test coverage?\n    - [ ] No obvious bugs or missed edge cases?\n    - [ ] No security issues?\n\n    OUTPUT FORMAT:\n    - Critical Issues: [must fix before proceeding]\n    - Important Issues: [should fix]\n    - Minor Issues: [optional]\n    - Verdict: APPROVED or REQUEST_CHANGES\n    \"\"\",\n    toolsets=['file']\n)\n```\n\n**If quality issues found:** Fix issues, re-review. Continue only when approved.\n\n#### Step 4: Mark Complete\n\n```python\ntodo([{\"id\": \"task-1\", \"content\": \"Create User model with email field\", \"status\": \"completed\"}], merge=True)\n```\n\n### 3. Final Review\n\nAfter ALL tasks are complete, dispatch a final integration reviewer:\n\n```python\ndelegate_task(\n    goal=\"Review the entire implementation for consistency and integration issues\",\n    context=\"\"\"\n    All tasks from the plan are complete. Review the full implementation:\n    - Do all components work together?\n    - Any inconsistencies between tasks?\n    - All tests passing?\n    - Ready for merge?\n    \"\"\",\n    toolsets=['terminal', 'file']\n)\n```\n\n### 4. Verify and Commit\n\n```bash\n# Run full test suite\npytest tests\u002F -q\n\n# Review all changes\ngit diff --stat\n\n# Final commit if needed\ngit add -A && git commit -m \"feat: complete [feature name] implementation\"\n```\n\n## Task Granularity\n\n**Each task = 2-5 minutes of focused work.**\n\n**Too big:**\n- \"Implement user authentication system\"\n\n**Right size:**\n- \"Create User model with email and password fields\"\n- \"Add password hashing function\"\n- \"Create login endpoint\"\n- \"Add JWT token generation\"\n- \"Create registration endpoint\"\n\n## Red Flags — Never Do These\n\n- Start implementation without a plan\n- Skip reviews (spec compliance OR code quality)\n- Proceed with unfixed critical\u002Fimportant issues\n- Dispatch multiple implementation subagents for tasks that touch the same files\n- Make subagent read the plan file (provide full text in context instead)\n- Skip scene-setting context (subagent needs to understand where the task fits)\n- Ignore subagent questions (answer before letting them proceed)\n- Accept \"close enough\" on spec compliance\n- Skip review loops (reviewer found issues → implementer fixes → review again)\n- Let implementer self-review replace actual review (both are needed)\n- **Start code quality review before spec compliance is PASS** (wrong order)\n- Move to next task while either review has open issues\n\n## Handling Issues\n\n### If Subagent Asks Questions\n\n- Answer clearly and completely\n- Provide additional context if needed\n- Don't rush them into implementation\n\n### If Subagent Fails a Task\n\n- Dispatch a new fix subagent with specific instructions about what went wrong\n- Don't try to fix manually in the controller session (context pollution)\n\n### Bundle\u002FCompile Inside Docker\n\nNative gem compilation (pg, nokogiri, etc.) often fails on host due to missing system libraries. **Fix:** Run `bundle install` and `rake` commands inside the Docker container:\n\n```bash\n# Connect via Docker network, not localhost\ndocker run --rm --network myapp_default -v \"$(pwd)\":\u002Frails -w \u002Frails \\\n  -e DB_HOST=postgres ruby:3.4 bash -c \"bundle install && bundle exec rake db:create db:migrate\"\n```\n\nThe container has build-essential, libpq-dev, and all other dependencies pre-installed.\n- Repeat until approved\n- Don't skip the re-review\n\n### If Subagent Fails a Task\n\n- Dispatch a new fix subagent with specific instructions about what went wrong\n- Don't try to fix manually in the controller session (context pollution)\n\n## Efficiency Notes\n\n**Why fresh subagent per task:**\n- Prevents context pollution from accumulated state\n- Each subagent gets clean, focused context\n- No confusion from prior tasks' code or reasoning\n\n**Why two-stage review:**\n- Spec review catches under\u002Fover-building early\n- Quality review ensures the implementation is well-built\n- Catches issues before they compound across tasks\n\n**Cost trade-off:**\n- More subagent invocations (implementer + 2 reviewers per task)\n- But catches issues early (cheaper than debugging compounded problems later)\n\n## Integration with Other Skills\n\n### With writing-plans\n\nThis skill EXECUTES plans created by the writing-plans skill:\n1. User requirements → writing-plans → implementation plan\n2. Implementation plan → subagent-driven-development → working code\n\n### With test-driven-development\n\nImplementer subagents should follow TDD:\n1. Write failing test first\n2. Implement minimal code\n3. Verify test passes\n4. Commit\n\nInclude TDD instructions in every implementer context.\n\n### With requesting-code-review\n\nThe two-stage review process IS the code review. For final integration review, use the requesting-code-review skill's review dimensions.\n\n### With systematic-debugging\n\nIf a subagent encounters bugs during implementation:\n1. Follow systematic-debugging process\n2. Find root cause before fixing\n3. Write regression test\n4. Resume implementation\n\n## Example Workflow\n\n```\n[Read plan: docs\u002Fplans\u002Fauth-feature.md]\n[Create todo list with 5 tasks]\n\n--- Task 1: Create User model ---\n[Dispatch implementer subagent]\n  Implementer: \"Should email be unique?\"\n  You: \"Yes, email must be unique\"\n  Implementer: Implemented, 3\u002F3 tests passing, committed.\n\n[Dispatch spec reviewer]\n  Spec reviewer: ✅ PASS — all requirements met\n\n[Dispatch quality reviewer]\n  Quality reviewer: ✅ APPROVED — clean code, good tests\n\n[Mark Task 1 complete]\n\n--- Task 2: Password hashing ---\n[Dispatch implementer subagent]\n  Implementer: No questions, implemented, 5\u002F5 tests passing.\n\n[Dispatch spec reviewer]\n  Spec reviewer: ❌ Missing: password strength validation (spec says \"min 8 chars\")\n\n[Implementer fixes]\n  Implementer: Added validation, 7\u002F7 tests passing.\n\n[Dispatch spec reviewer again]\n  Spec reviewer: ✅ PASS\n\n[Dispatch quality reviewer]\n  Quality reviewer: Important: Magic number 8, extract to constant\n  Implementer: Extracted MIN_PASSWORD_LENGTH constant\n  Quality reviewer: ✅ APPROVED\n\n[Mark Task 2 complete]\n\n... (continue for all tasks)\n\n[After all tasks: dispatch final integration reviewer]\n[Run full test suite: all passing]\n[Done!]\n```\n\n## Remember\n\n```\nFresh subagent per task\nTwo-stage review every time\nSpec compliance FIRST\nCode quality SECOND\nNever skip reviews\nCatch issues early\n```\n\n**Quality is not an accident. It's the result of systematic process.**\n\n## Further reading (load when relevant)\n\nWhen the orchestration involves significant context usage, long review loops, or complex validation checkpoints, load these references for the specific discipline:\n\n- **`references\u002Fcontext-budget-discipline.md`** — Four-tier context degradation model (PEAK \u002F GOOD \u002F DEGRADING \u002F POOR), read-depth rules that scale with context window size, and early warning signs of silent degradation. Load when a run will clearly consume significant context (multi-phase plans, many subagents, large artifacts).\n- **`references\u002Fgates-taxonomy.md`** — The four canonical gate types (Pre-flight, Revision, Escalation, Abort) with behavior, recovery, and examples. Load when designing or reviewing any workflow that has validation checkpoints — use the vocabulary explicitly so each gate has defined entry, failure behavior, and resumption rules.\n\nBoth references adapted from gsd-build\u002Fget-shit-done (MIT © 2025 Lex Christopherson).\n","# Subagent-Driven Development\n\n## Overview\n\nExecute implementation plans by dispatching fresh subagents per task with systematic two-stage review.\n\n**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.\n\n## When to Use\n\nUse this skill when:\n- You have an implementation plan (from writing-plans skill or user requirements)\n- Tasks are mostly independent\n- Quality and spec compliance are important\n- You want automated review between tasks\n\n**vs. manual execution:**\n- Fresh context per task (no confusion from accumulated state)\n- Automated review process catches issues early\n- Consistent quality checks across all tasks\n- Subagents can ask questions before starting work\n\n## The Process\n\n### 1. Read and Parse Plan\n\nRead the plan file. Extract ALL tasks with their full text and context upfront. Create a todo list:\n\n```python\n# Read the plan\nread_file(\"docs\u002Fplans\u002Ffeature-plan.md\")\n\n# Create todo list with all tasks\ntodo([\n    {\"id\": \"task-1\", \"content\": \"Create User model with email field\", \"status\": \"pending\"},\n    {\"id\": \"task-2\", \"content\": \"Add password hashing utility\", \"status\": \"pending\"},\n    {\"id\": \"task-3\", \"content\": \"Create login endpoint\", \"status\": \"pending\"},\n])\n```\n\n**Key:** Read the plan ONCE. Extract everything. Don't make subagents read the plan file — provide the full task text directly in context.\n\n### 2. Per-Task Workflow\n\nFor EACH task in the plan:\n\n#### Step 1: Dispatch Implementer Subagent\n\nUse `delegate_task` with complete context:\n\n```python\ndelegate_task(\n    goal=\"Implement Task 1: Create User model with email and password_hash fields\",\n    context=\"\"\"\n    TASK FROM PLAN:\n    - Create: src\u002Fmodels\u002Fuser.py\n    - Add User class with email (str) and password_hash (str) fields\n    - Use bcrypt for password hashing\n    - Include __repr__ for debugging\n\n    FOLLOW TDD:\n    1. Write failing test in tests\u002Fmodels\u002Ftest_user.py\n    2. Run: pytest tests\u002Fmodels\u002Ftest_user.py -v (verify FAIL)\n    3. Write minimal implementation\n    4. Run: pytest tests\u002Fmodels\u002Ftest_user.py -v (verify PASS)\n    5. Run: pytest tests\u002F -q (verify no regressions)\n    6. Commit: git add -A && git commit -m \"feat: add User model with password hashing\"\n\n    PROJECT CONTEXT:\n    - Python 3.11, Flask app in src\u002Fapp.py\n    - Existing models in src\u002Fmodels\u002F\n    - Tests use pytest, run from project root\n    - bcrypt already in requirements.txt\n    \"\"\",\n    toolsets=['terminal', 'file']\n)\n```\n\n#### Step 2: Dispatch Spec Compliance Reviewer\n\nAfter the implementer completes, verify against the original spec:\n\n```python\ndelegate_task(\n    goal=\"Review if implementation matches the spec from the plan\",\n    context=\"\"\"\n    ORIGINAL TASK SPEC:\n    - Create src\u002Fmodels\u002Fuser.py with User class\n    - Fields: email (str), password_hash (str)\n    - Use bcrypt for password hashing\n    - Include __repr__\n\n    CHECK:\n    - [ ] All requirements from spec implemented?\n    - [ ] File paths match spec?\n    - [ ] Function signatures match spec?\n    - [ ] Behavior matches expected?\n    - [ ] Nothing extra added (no scope creep)?\n\n    OUTPUT: PASS or list of specific spec gaps to fix.\n    \"\"\",\n    toolsets=['file']\n)\n```\n\n**If spec issues found:** Fix gaps, then re-run spec review. Continue only when spec-compliant.\n\n#### Step 3: Dispatch Code Quality Reviewer\n\nAfter spec compliance passes:\n\n```python\ndelegate_task(\n    goal=\"Review code quality for Task 1 implementation\",\n    context=\"\"\"\n    FILES TO REVIEW:\n    - src\u002Fmodels\u002Fuser.py\n    - tests\u002Fmodels\u002Ftest_user.py\n\n    CHECK:\n    - [ ] Follows project conventions and style?\n    - [ ] Proper error handling?\n    - [ ] Clear variable\u002Ffunction names?\n    - [ ] Adequate test coverage?\n    - [ ] No obvious bugs or missed edge cases?\n    - [ ] No security issues?\n\n    OUTPUT FORMAT:\n    - Critical Issues: [must fix before proceeding]\n    - Important Issues: [should fix]\n    - Minor Issues: [optional]\n    - Verdict: APPROVED or REQUEST_CHANGES\n    \"\"\",\n    toolsets=['file']\n)\n```\n\n**If quality issues found:** Fix issues, re-review. Continue only when approved.\n\n#### Step 4: Mark Complete\n\n```python\ntodo([{\"id\": \"task-1\", \"content\": \"Create User model with email field\", \"status\": \"completed\"}], merge=True)\n```\n\n### 3. Final Review\n\nAfter ALL tasks are complete, dispatch a final integration reviewer:\n\n```python\ndelegate_task(\n    goal=\"Review the entire implementation for consistency and integration issues\",\n    context=\"\"\"\n    All tasks from the plan are complete. Review the full implementation:\n    - Do all components work together?\n    - Any inconsistencies between tasks?\n    - All tests passing?\n    - Ready for merge?\n    \"\"\",\n    toolsets=['terminal', 'file']\n)\n```\n\n### 4. Verify and Commit\n\n```bash\n# Run full test suite\npytest tests\u002F -q\n\n# Review all changes\ngit diff --stat\n\n# Final commit if needed\ngit add -A && git commit -m \"feat: complete [feature name] implementation\"\n```\n\n## Task Granularity\n\n**Each task = 2-5 minutes of focused work.**\n\n**Too big:**\n- \"Implement user authentication system\"\n\n**Right size:**\n- \"Create User model with email and password fields\"\n- \"Add password hashing function\"\n- \"Create login endpoint\"\n- \"Add JWT token generation\"\n- \"Create registration endpoint\"\n\n## Red Flags — Never Do These\n\n- Start implementation without a plan\n- Skip reviews (spec compliance OR code quality)\n- Proceed with unfixed critical\u002Fimportant issues\n- Dispatch multiple implementation subagents for tasks that touch the same files\n- Make subagent read the plan file (provide full text in context instead)\n- Skip scene-setting context (subagent needs to understand where the task fits)\n- Ignore subagent questions (answer before letting them proceed)\n- Accept \"close enough\" on spec compliance\n- Skip review loops (reviewer found issues → implementer fixes → review again)\n- Let implementer self-review replace actual review (both are needed)\n- **Start code quality review before spec compliance is PASS** (wrong order)\n- Move to next task while either review has open issues\n\n## Handling Issues\n\n### If Subagent Asks Questions\n\n- Answer clearly and completely\n- Provide additional context if needed\n- Don't rush them into implementation\n\n### If Subagent Fails a Task\n\n- Dispatch a new fix subagent with specific instructions about what went wrong\n- Don't try to fix manually in the controller session (context pollution)\n\n### Bundle\u002FCompile Inside Docker\n\nNative gem compilation (pg, nokogiri, etc.) often fails on host due to missing system libraries. **Fix:** Run `bundle install` and `rake` commands inside the Docker container:\n\n```bash\n# Connect via Docker network, not localhost\ndocker run --rm --network myapp_default -v \"$(pwd)\":\u002Frails -w \u002Frails \\\n  -e DB_HOST=postgres ruby:3.4 bash -c \"bundle install && bundle exec rake db:create db:migrate\"\n```\n\nThe container has build-essential, libpq-dev, and all other dependencies pre-installed.\n- Repeat until approved\n- Don't skip the re-review\n\n### If Subagent Fails a Task\n\n- Dispatch a new fix subagent with specific instructions about what went wrong\n- Don't try to fix manually in the controller session (context pollution)\n\n## Efficiency Notes\n\n**Why fresh subagent per task:**\n- Prevents context pollution from accumulated state\n- Each subagent gets clean, focused context\n- No confusion from prior tasks' code or reasoning\n\n**Why two-stage review:**\n- Spec review catches under\u002Fover-building early\n- Quality review ensures the implementation is well-built\n- Catches issues before they compound across tasks\n\n**Cost trade-off:**\n- More subagent invocations (implementer + 2 reviewers per task)\n- But catches issues early (cheaper than debugging compounded problems later)\n\n## Integration with Other Skills\n\n### With writing-plans\n\nThis skill EXECUTES plans created by the writing-plans skill:\n1. User requirements → writing-plans → implementation plan\n2. Implementation plan → subagent-driven-development → working code\n\n### With test-driven-development\n\nImplementer subagents should follow TDD:\n1. Write failing test first\n2. Implement minimal code\n3. Verify test passes\n4. Commit\n\nInclude TDD instructions in every implementer context.\n\n### With requesting-code-review\n\nThe two-stage review process IS the code review. For final integration review, use the requesting-code-review skill's review dimensions.\n\n### With systematic-debugging\n\nIf a subagent encounters bugs during implementation:\n1. Follow systematic-debugging process\n2. Find root cause before fixing\n3. Write regression test\n4. Resume implementation\n\n## Example Workflow\n\n```\n[Read plan: docs\u002Fplans\u002Fauth-feature.md]\n[Create todo list with 5 tasks]\n\n--- Task 1: Create User model ---\n[Dispatch implementer subagent]\n  Implementer: \"Should email be unique?\"\n  You: \"Yes, email must be unique\"\n  Implementer: Implemented, 3\u002F3 tests passing, committed.\n\n[Dispatch spec reviewer]\n  Spec reviewer: ✅ PASS — all requirements met\n\n[Dispatch quality reviewer]\n  Quality reviewer: ✅ APPROVED — clean code, good tests\n\n[Mark Task 1 complete]\n\n--- Task 2: Password hashing ---\n[Dispatch implementer subagent]\n  Implementer: No questions, implemented, 5\u002F5 tests passing.\n\n[Dispatch spec reviewer]\n  Spec reviewer: ❌ Missing: password strength validation (spec says \"min 8 chars\")\n\n[Implementer fixes]\n  Implementer: Added validation, 7\u002F7 tests passing.\n\n[Dispatch spec reviewer again]\n  Spec reviewer: ✅ PASS\n\n[Dispatch quality reviewer]\n  Quality reviewer: Important: Magic number 8, extract to constant\n  Implementer: Extracted MIN_PASSWORD_LENGTH constant\n  Quality reviewer: ✅ APPROVED\n\n[Mark Task 2 complete]\n\n... (continue for all tasks)\n\n[After all tasks: dispatch final integration reviewer]\n[Run full test suite: all passing]\n[Done!]\n```\n\n## Remember\n\n```\nFresh subagent per task\nTwo-stage review every time\nSpec compliance FIRST\nCode quality SECOND\nNever skip reviews\nCatch issues early\n```\n\n**Quality is not an accident. It's the result of systematic process.**\n\n## Further reading (load when relevant)\n\nWhen the orchestration involves significant context usage, long review loops, or complex validation checkpoints, load these references for the specific discipline:\n\n- **`references\u002Fcontext-budget-discipline.md`** — Four-tier context degradation model (PEAK \u002F GOOD \u002F DEGRADING \u002F POOR), read-depth rules that scale with context window size, and early warning signs of silent degradation. Load when a run will clearly consume significant context (multi-phase plans, many subagents, large artifacts).\n- **`references\u002Fgates-taxonomy.md`** — The four canonical gate types (Pre-flight, Revision, Escalation, Abort) with behavior, recovery, and examples. Load when designing or reviewing any workflow that has validation checkpoints — use the vocabulary explicitly so each gate has defined entry, failure behavior, and resumption rules.\n\nBoth references adapted from gsd-build\u002Fget-shit-done (MIT © 2025 Lex Christopherson).\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":38,"description":7},"Hermes Agent (adapted from obra\u002Fsuperpowers)","1.1.0",{"hermes":27},{"tags":28,"related_skills":34},[29,30,31,32,33],"delegation","subagent","implementation","workflow","parallel",[35,36,37],"writing-plans","requesting-code-review","test-driven-development",[39,40,41],"linux","macos","windows","master","f341c46fed021656175d5c9ccc67a72126e50bfb","skills\u002Fsoftware-development\u002Fsubagent-driven-development","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public","https:\u002F\u002Fgithub.com\u002Fdbillion","I enjoy writing codes,teaching programming, solving problems, tasted automation in Python and never looked back😋😋😋💞","2026-10-14 03:31:55",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add dbillion\u002Fhermes-skills-public --skill subagent-driven-development",{"tool":55,"command":56},"bunx","bunx skills add dbillion\u002Fhermes-skills-public --skill subagent-driven-development",{"tool":58,"command":59},"pnpm","pnpm dlx skills add dbillion\u002Fhermes-skills-public --skill subagent-driven-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",true,[63,69],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fcontext-budget-discipline.md","REFERENCE","参考文档",4209,"https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002Freferences\u002Fcontext-budget-discipline.md",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fgates-taxonomy.md",4668,"https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002Freferences\u002Fgates-taxonomy.md",[74,81,88,97,104,111],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7B25T0V7RBKES86Y3RTXQRN","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7B25DSBBMZRHVD28MAX7N5X","gemini-vision-fallback","Vision fallback: Gemini REST API if vision_analyze blocked.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fvision\u002Fgemini-vision-fallback\u002FSKILL.md",[],[],{"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":92,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7B22XW9QXT2ZWWXVZDFWYZP","twitter-cli","Use twitter-cli for ALL Twitter\u002FX operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, user lookups. Invoke whenever user requests any Twitter interaction.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ftwitter-cli\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ftwitter-cli\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7B22QMWY1B4F7BC114RG4S6","prism-scan","Structural analysis through dynamically generated cognitive lenses. Generates the optimal analytical lens for the specific code\u002Fartifact, then executes it. Finds conservation laws, structural invariants, and concrete bugs that vanilla analysis misses. Use on any code file, system design, or text artifact.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-scan\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":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7B22JA5XCAP1ACT6V50WYR1","prism-reflect","Constraint transparency: analyzes an artifact structurally, then analyzes what its own analysis concealed. Produces a conservation law AND a constraint report showing what was maximized, what was sacrificed, and what to investigate next. The only AI skill that knows what it can't see.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-reflect\u002FSKILL.md",[],[],{"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":117,"publishedAt":19},"01M7B22EB15M75M4X3C52YGDCC","prism-full","Full Prism: multi-pass structural analysis with mandatory adversarial self-correction. Designs custom analytical passes, executes them with chaining, then attacks its own findings before synthesizing. Use for maximum depth on important code or artifacts.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-full\u002FSKILL.md",[],[]]