[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7RY6HCB5FAJE777P58VJB":3,"skill-same:01M7F7RY6HCB5FAJE777P58VJB":65},{"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":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M7F7RY6HCB5FAJE777P58VJB","plan",null,"Write a markdown plan to .hermes\u002Fplans\u002F; no execution.","chaorenex1\u002Fhermes-home-content","chaorenex1","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23194925?v=4","01M7F5NA1D1D02R2MEMYQN2NZT","chan chan","01M7F5NA20KTHMTY2015CYM1TZ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fplan\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\r\nname: plan\r\ndescription: Write a markdown plan to .hermes\u002Fplans\u002F; no execution.\r\nversion: 2.0.0\r\nauthor: Hermes Agent (writing-craft adapted from obra\u002Fsuperpowers)\r\nlicense: MIT\r\nplatforms: [linux, macos, windows]\r\nmetadata:\r\n  hermes:\r\n    tags: [planning, plan-mode, implementation, workflow, design, documentation]\r\n    related_skills: [subagent-driven-development, test-driven-development, requesting-code-review]\r\n---\r\n\r\n# Plan Mode\r\n\r\nUse this skill when the user wants a plan instead of execution.\r\n\r\n## Core behavior\r\n\r\nFor this turn, you are planning only.\r\n\r\n- Do not implement code.\r\n- Do not edit project files except the plan markdown file.\r\n- Do not run mutating terminal commands, commit, push, or perform external actions.\r\n- You may inspect the repo or other context with read-only commands\u002Ftools when needed.\r\n- Your deliverable is a markdown plan saved inside the active workspace under `.hermes\u002Fplans\u002F`.\r\n\r\n## Output requirements\r\n\r\nWrite a markdown plan that is concrete and actionable.\r\n\r\nInclude, when relevant:\r\n- Goal\r\n- Current context \u002F assumptions\r\n- Proposed approach\r\n- Step-by-step plan\r\n- Files likely to change\r\n- Tests \u002F validation\r\n- Risks, tradeoffs, and open questions\r\n\r\nIf the task is code-related, include exact file paths, likely test targets, and verification steps.\r\n\r\n## Save location\r\n\r\nSave the plan with `write_file` under:\r\n- `.hermes\u002Fplans\u002FYYYY-MM-DD_HHMMSS-\u003Cslug>.md`\r\n\r\nTreat that as relative to the active working directory \u002F backend workspace. Hermes file tools are backend-aware, so using this relative path keeps the plan with the workspace on local, docker, ssh, modal, and daytona backends.\r\n\r\nIf the runtime provides a specific target path, use that exact path.\r\nIf not, create a sensible timestamped filename yourself under `.hermes\u002Fplans\u002F`.\r\n\r\n## Interaction style\r\n\r\n- If the request is clear enough, write the plan directly.\r\n- If no explicit instruction accompanies `\u002Fplan`, infer the task from the current conversation context.\r\n- If it is genuinely underspecified, ask a brief clarifying question instead of guessing.\r\n- After saving the plan, reply briefly with what you planned and the saved path.\r\n\r\n---\r\n\r\n# Writing the Plan Well\r\n\r\nThe rest of this skill is the craft of authoring a *good* implementation plan — the content that goes inside the markdown file above.\r\n\r\n## Overview\r\n\r\nWrite comprehensive implementation plans assuming the implementer has zero context for the codebase and questionable taste. Document everything they need: which files to touch, complete code, testing commands, docs to check, how to verify. Give them bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.\r\n\r\nAssume the implementer is a skilled developer but knows almost nothing about the toolset or problem domain. Assume they don't know good test design very well.\r\n\r\n**Core principle:** A good plan makes implementation obvious. If someone has to guess, the plan is incomplete.\r\n\r\n## When a Full Implementation Plan Helps\r\n\r\n**Always use before:**\r\n- Implementing multi-step features\r\n- Breaking down complex requirements\r\n- Delegating to subagents via subagent-driven-development\r\n\r\n**Don't skip when:**\r\n- Feature seems simple (assumptions cause bugs)\r\n- You plan to implement it yourself (future you needs guidance)\r\n- Working alone (documentation matters)\r\n\r\n## Bite-Sized Task Granularity\r\n\r\n**Each task = 2-5 minutes of focused work.**\r\n\r\nEvery step is one action:\r\n- \"Write the failing test\" — step\r\n- \"Run it to make sure it fails\" — step\r\n- \"Implement the minimal code to make the test pass\" — step\r\n- \"Run the tests and make sure they pass\" — step\r\n- \"Commit\" — step\r\n\r\n**Too big:**\r\n```markdown\r\n### Task 1: Build authentication system\r\n[50 lines of code across 5 files]\r\n```\r\n\r\n**Right size:**\r\n```markdown\r\n### Task 1: Create User model with email field\r\n[10 lines, 1 file]\r\n\r\n### Task 2: Add password hash field to User\r\n[8 lines, 1 file]\r\n\r\n### Task 3: Create password hashing utility\r\n[15 lines, 1 file]\r\n```\r\n\r\n## Plan Document Structure\r\n\r\n### Header (Required)\r\n\r\nEvery plan MUST start with:\r\n\r\n```markdown\r\n# [Feature Name] Implementation Plan\r\n\r\n> **For Hermes:** Use subagent-driven-development skill to implement this plan task-by-task.\r\n\r\n**Goal:** [One sentence describing what this builds]\r\n\r\n**Architecture:** [2-3 sentences about approach]\r\n\r\n**Tech Stack:** [Key technologies\u002Flibraries]\r\n\r\n---\r\n```\r\n\r\n### Task Structure\r\n\r\nEach task follows this format:\r\n\r\n````markdown\r\n### Task N: [Descriptive Name]\r\n\r\n**Objective:** What this task accomplishes (one sentence)\r\n\r\n**Files:**\r\n- Create: `exact\u002Fpath\u002Fto\u002Fnew_file.py`\r\n- Modify: `exact\u002Fpath\u002Fto\u002Fexisting.py:45-67` (line numbers if known)\r\n- Test: `tests\u002Fpath\u002Fto\u002Ftest_file.py`\r\n\r\n**Step 1: Write failing test**\r\n\r\n```python\r\ndef test_specific_behavior():\r\n    result = function(input)\r\n    assert result == expected\r\n```\r\n\r\n**Step 2: Run test to verify failure**\r\n\r\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_specific_behavior -v`\r\nExpected: FAIL — \"function not defined\"\r\n\r\n**Step 3: Write minimal implementation**\r\n\r\n```python\r\ndef function(input):\r\n    return expected\r\n```\r\n\r\n**Step 4: Run test to verify pass**\r\n\r\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_specific_behavior -v`\r\nExpected: PASS\r\n\r\n**Step 5: Commit**\r\n\r\n```bash\r\ngit add tests\u002Fpath\u002Ftest.py src\u002Fpath\u002Ffile.py\r\ngit commit -m \"feat: add specific feature\"\r\n```\r\n````\r\n\r\n## Writing Process\r\n\r\n### Step 1: Understand Requirements\r\n\r\nRead and understand:\r\n- Feature requirements\r\n- Design documents or user description\r\n- Acceptance criteria\r\n- Constraints\r\n\r\n### Step 2: Explore the Codebase\r\n\r\nUse Hermes tools to understand the project:\r\n\r\n```python\r\n# Understand project structure\r\nsearch_files(\"*.py\", target=\"files\", path=\"src\u002F\")\r\n\r\n# Look at similar features\r\nsearch_files(\"similar_pattern\", path=\"src\u002F\", file_glob=\"*.py\")\r\n\r\n# Check existing tests\r\nsearch_files(\"*.py\", target=\"files\", path=\"tests\u002F\")\r\n\r\n# Read key files\r\nread_file(\"src\u002Fapp.py\")\r\n```\r\n\r\n### Step 3: Design Approach\r\n\r\nDecide:\r\n- Architecture pattern\r\n- File organization\r\n- Dependencies needed\r\n- Testing strategy\r\n\r\n### Step 4: Write Tasks\r\n\r\nCreate tasks in order:\r\n1. Setup\u002Finfrastructure\r\n2. Core functionality (TDD for each)\r\n3. Edge cases\r\n4. Integration\r\n5. Cleanup\u002Fdocumentation\r\n\r\n### Step 5: Add Complete Details\r\n\r\nFor each task, include:\r\n- **Exact file paths** (not \"the config file\" but `src\u002Fconfig\u002Fsettings.py`)\r\n- **Complete code examples** (not \"add validation\" but the actual code)\r\n- **Exact commands** with expected output\r\n- **Verification steps** that prove the task works\r\n\r\n### Step 6: Review the Plan\r\n\r\nCheck:\r\n- [ ] Tasks are sequential and logical\r\n- [ ] Each task is bite-sized (2-5 min)\r\n- [ ] File paths are exact\r\n- [ ] Code examples are complete (copy-pasteable)\r\n- [ ] Commands are exact with expected output\r\n- [ ] No missing context\r\n- [ ] DRY, YAGNI, TDD principles applied\r\n\r\n## Principles\r\n\r\n### DRY (Don't Repeat Yourself)\r\n\r\n**Bad:** Copy-paste validation in 3 places\r\n**Good:** Extract validation function, use everywhere\r\n\r\n### YAGNI (You Aren't Gonna Need It)\r\n\r\n**Bad:** Add \"flexibility\" for future requirements\r\n**Good:** Implement only what's needed now\r\n\r\n```python\r\n# Bad — YAGNI violation\r\nclass User:\r\n    def __init__(self, name, email):\r\n        self.name = name\r\n        self.email = email\r\n        self.preferences = {}  # Not needed yet!\r\n        self.metadata = {}     # Not needed yet!\r\n\r\n# Good — YAGNI\r\nclass User:\r\n    def __init__(self, name, email):\r\n        self.name = name\r\n        self.email = email\r\n```\r\n\r\n### TDD (Test-Driven Development)\r\n\r\nEvery task that produces code should include the full TDD cycle:\r\n1. Write failing test\r\n2. Run to verify failure\r\n3. Write minimal code\r\n4. Run to verify pass\r\n\r\nSee `test-driven-development` skill for details.\r\n\r\n### Frequent Commits\r\n\r\nCommit after every task:\r\n```bash\r\ngit add [files]\r\ngit commit -m \"type: description\"\r\n```\r\n\r\n## Common Mistakes\r\n\r\n### Vague Tasks\r\n\r\n**Bad:** \"Add authentication\"\r\n**Good:** \"Create User model with email and password_hash fields\"\r\n\r\n### Incomplete Code\r\n\r\n**Bad:** \"Step 1: Add validation function\"\r\n**Good:** \"Step 1: Add validation function\" followed by the complete function code\r\n\r\n### Missing Verification\r\n\r\n**Bad:** \"Step 3: Test it works\"\r\n**Good:** \"Step 3: Run `pytest tests\u002Ftest_auth.py -v`, expected: 3 passed\"\r\n\r\n### Missing File Paths\r\n\r\n**Bad:** \"Create the model file\"\r\n**Good:** \"Create: `src\u002Fmodels\u002Fuser.py`\"\r\n\r\n## Execution Handoff\r\n\r\nAfter saving the plan, offer the execution approach:\r\n\r\n**\"Plan complete and saved. Ready to execute using subagent-driven-development — I'll dispatch a fresh subagent per task with two-stage review (spec compliance then code quality). Shall I proceed?\"**\r\n\r\nWhen executing, use the `subagent-driven-development` skill:\r\n- Fresh `delegate_task` per task with full context\r\n- Spec compliance review after each task\r\n- Code quality review after spec passes\r\n- Proceed only when both reviews approve\r\n\r\n## Remember\r\n\r\n```\r\nBite-sized tasks (2-5 min each)\r\nExact file paths\r\nComplete code (copy-pasteable)\r\nExact commands with expected output\r\nVerification steps\r\nDRY, YAGNI, TDD\r\nFrequent commits\r\n```\r\n\r\n**A good plan makes implementation obvious.**\r\n","# Plan Mode\r\n\r\nUse this skill when the user wants a plan instead of execution.\r\n\r\n## Core behavior\r\n\r\nFor this turn, you are planning only.\r\n\r\n- Do not implement code.\r\n- Do not edit project files except the plan markdown file.\r\n- Do not run mutating terminal commands, commit, push, or perform external actions.\r\n- You may inspect the repo or other context with read-only commands\u002Ftools when needed.\r\n- Your deliverable is a markdown plan saved inside the active workspace under `.hermes\u002Fplans\u002F`.\r\n\r\n## Output requirements\r\n\r\nWrite a markdown plan that is concrete and actionable.\r\n\r\nInclude, when relevant:\r\n- Goal\r\n- Current context \u002F assumptions\r\n- Proposed approach\r\n- Step-by-step plan\r\n- Files likely to change\r\n- Tests \u002F validation\r\n- Risks, tradeoffs, and open questions\r\n\r\nIf the task is code-related, include exact file paths, likely test targets, and verification steps.\r\n\r\n## Save location\r\n\r\nSave the plan with `write_file` under:\r\n- `.hermes\u002Fplans\u002FYYYY-MM-DD_HHMMSS-\u003Cslug>.md`\r\n\r\nTreat that as relative to the active working directory \u002F backend workspace. Hermes file tools are backend-aware, so using this relative path keeps the plan with the workspace on local, docker, ssh, modal, and daytona backends.\r\n\r\nIf the runtime provides a specific target path, use that exact path.\r\nIf not, create a sensible timestamped filename yourself under `.hermes\u002Fplans\u002F`.\r\n\r\n## Interaction style\r\n\r\n- If the request is clear enough, write the plan directly.\r\n- If no explicit instruction accompanies `\u002Fplan`, infer the task from the current conversation context.\r\n- If it is genuinely underspecified, ask a brief clarifying question instead of guessing.\r\n- After saving the plan, reply briefly with what you planned and the saved path.\r\n\r\n---\r\n\r\n# Writing the Plan Well\r\n\r\nThe rest of this skill is the craft of authoring a *good* implementation plan — the content that goes inside the markdown file above.\r\n\r\n## Overview\r\n\r\nWrite comprehensive implementation plans assuming the implementer has zero context for the codebase and questionable taste. Document everything they need: which files to touch, complete code, testing commands, docs to check, how to verify. Give them bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.\r\n\r\nAssume the implementer is a skilled developer but knows almost nothing about the toolset or problem domain. Assume they don't know good test design very well.\r\n\r\n**Core principle:** A good plan makes implementation obvious. If someone has to guess, the plan is incomplete.\r\n\r\n## When a Full Implementation Plan Helps\r\n\r\n**Always use before:**\r\n- Implementing multi-step features\r\n- Breaking down complex requirements\r\n- Delegating to subagents via subagent-driven-development\r\n\r\n**Don't skip when:**\r\n- Feature seems simple (assumptions cause bugs)\r\n- You plan to implement it yourself (future you needs guidance)\r\n- Working alone (documentation matters)\r\n\r\n## Bite-Sized Task Granularity\r\n\r\n**Each task = 2-5 minutes of focused work.**\r\n\r\nEvery step is one action:\r\n- \"Write the failing test\" — step\r\n- \"Run it to make sure it fails\" — step\r\n- \"Implement the minimal code to make the test pass\" — step\r\n- \"Run the tests and make sure they pass\" — step\r\n- \"Commit\" — step\r\n\r\n**Too big:**\r\n```markdown\r\n### Task 1: Build authentication system\r\n[50 lines of code across 5 files]\r\n```\r\n\r\n**Right size:**\r\n```markdown\r\n### Task 1: Create User model with email field\r\n[10 lines, 1 file]\r\n\r\n### Task 2: Add password hash field to User\r\n[8 lines, 1 file]\r\n\r\n### Task 3: Create password hashing utility\r\n[15 lines, 1 file]\r\n```\r\n\r\n## Plan Document Structure\r\n\r\n### Header (Required)\r\n\r\nEvery plan MUST start with:\r\n\r\n```markdown\r\n# [Feature Name] Implementation Plan\r\n\r\n> **For Hermes:** Use subagent-driven-development skill to implement this plan task-by-task.\r\n\r\n**Goal:** [One sentence describing what this builds]\r\n\r\n**Architecture:** [2-3 sentences about approach]\r\n\r\n**Tech Stack:** [Key technologies\u002Flibraries]\r\n\r\n---\r\n```\r\n\r\n### Task Structure\r\n\r\nEach task follows this format:\r\n\r\n````markdown\r\n### Task N: [Descriptive Name]\r\n\r\n**Objective:** What this task accomplishes (one sentence)\r\n\r\n**Files:**\r\n- Create: `exact\u002Fpath\u002Fto\u002Fnew_file.py`\r\n- Modify: `exact\u002Fpath\u002Fto\u002Fexisting.py:45-67` (line numbers if known)\r\n- Test: `tests\u002Fpath\u002Fto\u002Ftest_file.py`\r\n\r\n**Step 1: Write failing test**\r\n\r\n```python\r\ndef test_specific_behavior():\r\n    result = function(input)\r\n    assert result == expected\r\n```\r\n\r\n**Step 2: Run test to verify failure**\r\n\r\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_specific_behavior -v`\r\nExpected: FAIL — \"function not defined\"\r\n\r\n**Step 3: Write minimal implementation**\r\n\r\n```python\r\ndef function(input):\r\n    return expected\r\n```\r\n\r\n**Step 4: Run test to verify pass**\r\n\r\nRun: `pytest tests\u002Fpath\u002Ftest.py::test_specific_behavior -v`\r\nExpected: PASS\r\n\r\n**Step 5: Commit**\r\n\r\n```bash\r\ngit add tests\u002Fpath\u002Ftest.py src\u002Fpath\u002Ffile.py\r\ngit commit -m \"feat: add specific feature\"\r\n```\r\n````\r\n\r\n## Writing Process\r\n\r\n### Step 1: Understand Requirements\r\n\r\nRead and understand:\r\n- Feature requirements\r\n- Design documents or user description\r\n- Acceptance criteria\r\n- Constraints\r\n\r\n### Step 2: Explore the Codebase\r\n\r\nUse Hermes tools to understand the project:\r\n\r\n```python\r\n# Understand project structure\r\nsearch_files(\"*.py\", target=\"files\", path=\"src\u002F\")\r\n\r\n# Look at similar features\r\nsearch_files(\"similar_pattern\", path=\"src\u002F\", file_glob=\"*.py\")\r\n\r\n# Check existing tests\r\nsearch_files(\"*.py\", target=\"files\", path=\"tests\u002F\")\r\n\r\n# Read key files\r\nread_file(\"src\u002Fapp.py\")\r\n```\r\n\r\n### Step 3: Design Approach\r\n\r\nDecide:\r\n- Architecture pattern\r\n- File organization\r\n- Dependencies needed\r\n- Testing strategy\r\n\r\n### Step 4: Write Tasks\r\n\r\nCreate tasks in order:\r\n1. Setup\u002Finfrastructure\r\n2. Core functionality (TDD for each)\r\n3. Edge cases\r\n4. Integration\r\n5. Cleanup\u002Fdocumentation\r\n\r\n### Step 5: Add Complete Details\r\n\r\nFor each task, include:\r\n- **Exact file paths** (not \"the config file\" but `src\u002Fconfig\u002Fsettings.py`)\r\n- **Complete code examples** (not \"add validation\" but the actual code)\r\n- **Exact commands** with expected output\r\n- **Verification steps** that prove the task works\r\n\r\n### Step 6: Review the Plan\r\n\r\nCheck:\r\n- [ ] Tasks are sequential and logical\r\n- [ ] Each task is bite-sized (2-5 min)\r\n- [ ] File paths are exact\r\n- [ ] Code examples are complete (copy-pasteable)\r\n- [ ] Commands are exact with expected output\r\n- [ ] No missing context\r\n- [ ] DRY, YAGNI, TDD principles applied\r\n\r\n## Principles\r\n\r\n### DRY (Don't Repeat Yourself)\r\n\r\n**Bad:** Copy-paste validation in 3 places\r\n**Good:** Extract validation function, use everywhere\r\n\r\n### YAGNI (You Aren't Gonna Need It)\r\n\r\n**Bad:** Add \"flexibility\" for future requirements\r\n**Good:** Implement only what's needed now\r\n\r\n```python\r\n# Bad — YAGNI violation\r\nclass User:\r\n    def __init__(self, name, email):\r\n        self.name = name\r\n        self.email = email\r\n        self.preferences = {}  # Not needed yet!\r\n        self.metadata = {}     # Not needed yet!\r\n\r\n# Good — YAGNI\r\nclass User:\r\n    def __init__(self, name, email):\r\n        self.name = name\r\n        self.email = email\r\n```\r\n\r\n### TDD (Test-Driven Development)\r\n\r\nEvery task that produces code should include the full TDD cycle:\r\n1. Write failing test\r\n2. Run to verify failure\r\n3. Write minimal code\r\n4. Run to verify pass\r\n\r\nSee `test-driven-development` skill for details.\r\n\r\n### Frequent Commits\r\n\r\nCommit after every task:\r\n```bash\r\ngit add [files]\r\ngit commit -m \"type: description\"\r\n```\r\n\r\n## Common Mistakes\r\n\r\n### Vague Tasks\r\n\r\n**Bad:** \"Add authentication\"\r\n**Good:** \"Create User model with email and password_hash fields\"\r\n\r\n### Incomplete Code\r\n\r\n**Bad:** \"Step 1: Add validation function\"\r\n**Good:** \"Step 1: Add validation function\" followed by the complete function code\r\n\r\n### Missing Verification\r\n\r\n**Bad:** \"Step 3: Test it works\"\r\n**Good:** \"Step 3: Run `pytest tests\u002Ftest_auth.py -v`, expected: 3 passed\"\r\n\r\n### Missing File Paths\r\n\r\n**Bad:** \"Create the model file\"\r\n**Good:** \"Create: `src\u002Fmodels\u002Fuser.py`\"\r\n\r\n## Execution Handoff\r\n\r\nAfter saving the plan, offer the execution approach:\r\n\r\n**\"Plan complete and saved. Ready to execute using subagent-driven-development — I'll dispatch a fresh subagent per task with two-stage review (spec compliance then code quality). Shall I proceed?\"**\r\n\r\nWhen executing, use the `subagent-driven-development` skill:\r\n- Fresh `delegate_task` per task with full context\r\n- Spec compliance review after each task\r\n- Code quality review after spec passes\r\n- Proceed only when both reviews approve\r\n\r\n## Remember\r\n\r\n```\r\nBite-sized tasks (2-5 min each)\r\nExact file paths\r\nComplete code (copy-pasteable)\r\nExact commands with expected output\r\nVerification steps\r\nDRY, YAGNI, TDD\r\nFrequent commits\r\n```\r\n\r\n**A good plan makes implementation obvious.**\r\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":39,"description":7},"Hermes Agent (writing-craft adapted from obra\u002Fsuperpowers)","2.0.0",{"hermes":27},{"tags":28,"related_skills":35},[29,30,31,32,33,34],"planning","plan-mode","implementation","workflow","design","documentation",[36,37,38],"subagent-driven-development","test-driven-development","requesting-code-review",[40,41,42],"linux","macos","windows","main","a3f3199bb87ec3c91248f68a39d88527e1847ae9","skills\u002Fsoftware-development\u002Fplan","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content","https:\u002F\u002Fgithub.com\u002Fchaorenex1","https:\u002F\u002Fblog.aduib.com","A programmer whose only hobby in life is coding","2026-10-20 00:34:32",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add chaorenex1\u002Fhermes-home-content --skill plan",{"tool":57,"command":58},"bunx","bunx skills add chaorenex1\u002Fhermes-home-content --skill plan",{"tool":60,"command":61},"pnpm","pnpm dlx skills add chaorenex1\u002Fhermes-home-content --skill plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fplan\u002FSKILL.md",true,[],[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7F8GF32YD5MBQW2TGSRH1YP","web-retrieval-resilience","Web tools fail or search rules break: repair or fall back.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fweb-retrieval-resilience\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7F8FP46QESQMCZ1KBT3TW3R","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7F8ER6VXHBNVRQBZS7X08SE","verification-loop","Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS\u002FFAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7F8E4BQJ38KVQVM3MT20PYV","unreal-world-builder","开放世界与环境专家——精通 UE5 World Partition、Landscape、程序化植被、HLOD 和大规模关卡流式加载，打造无缝开放世界体验","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-world-builder\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7F8D747SQW2FTP7GBSX38BR","unreal-technical-artist","Unreal Engine 视觉管线专家——精通材质编辑器、Niagara 特效、程序化内容生成和 UE5 项目的美术到引擎管线","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-technical-artist\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7F8CKHYJVZVBTN0321J88T2","unreal-systems-engineer","性能与混合架构专家——精通 C++\u002FBlueprint 边界、Nanite 几何体、Lumen GI 和 Gameplay Ability System，面向 AAA 级 Unreal Engine 项目","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-systems-engineer\u002FSKILL.md",[],[]]