[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76TJMN92BFXDPAFHN8YDMKF":3,"skill-same:01M76TJMN92BFXDPAFHN8YDMKF":76},{"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":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M76TJMN92BFXDPAFHN8YDMKF","hermes-agent-skill-authoring",null,"Author in-repo SKILL.md: frontmatter, validator, structure.","SatangThevalue\u002Fai-skills","SatangThevalue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F17944930?v=4","01M756VHQQ58XSM5PDS03W79VY","Sa-Tang","01M756VHRNYXRY7HM230S4YHVV",0,"MIT","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fhermes-agent-skill-authoring\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: hermes-agent-skill-authoring\ndescription: \"Author in-repo SKILL.md: frontmatter, validator, structure.\"\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    reviewed: \\\"2026-06-01 (automated)\\\"\n    tags: [skills, authoring, hermes-agent, conventions, skill-md]\n    related_skills: [writing-plans, requesting-code-review]\n---\n\n# Authoring Hermes-Agent Skills (in-repo)\n\n## Overview\n\nThere are two places a SKILL.md can live:\n\n1. **User-local:** `~\u002F.hermes\u002Fskills\u002F\u003Cmaybe-category>\u002F\u003Cname>\u002FSKILL.md` — personal, not shared. Created via `skill_manage(action='create')`.\n2. **In-repo (this skill is about this case):** `\u002Fhome\u002Fbb\u002Fhermes-agent\u002Fskills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md` — committed, shipped with the package. Use `write_file` + `git add`. `skill_manage(action='create')` does NOT target this tree.\n\n## When to Use\n\n- User asks you to add a skill \"in this branch \u002F repo \u002F commit\"\n- You're committing a reusable workflow that should ship with hermes-agent\n- You're editing an existing skill under `\u002Fhome\u002Fbb\u002Fhermes-agent\u002Fskills\u002F` (use `patch` for small edits, `write_file` for rewrites; `skill_manage` still works for patch on in-repo skills, but not for `create`)\n\n## Required Frontmatter\n\nSource of truth: `tools\u002Fskill_manager_tool.py::_validate_frontmatter`. Hard requirements:\n\n- Starts with `---` as the first bytes (no leading blank line).\n- Closes with `\\n---\\n` before the body.\n- Parses as a YAML mapping.\n- `name` field present.\n- `description` field present, ≤ **1024 chars** (`MAX_DESCRIPTION_LENGTH`).\n- Non-empty body after the closing `---`.\n\nPeer-matched shape used by every skill under `skills\u002Fsoftware-development\u002F`:\n\n```yaml\n---\nname: my-skill-name               # lowercase, hyphens, ≤64 chars (MAX_NAME_LENGTH)\ndescription: Use when \u003Ctrigger>. \u003Cone-line behavior>.\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\nmetadata:\n  hermes:\n    tags: [short, descriptive, tags]\n    related_skills: [other-skill, another-skill]\n---\n```\n\n`version` \u002F `author` \u002F `license` \u002F `metadata` are NOT enforced by the validator, but every peer has them — omit and your skill sticks out.\n\n## Size Limits\n\n- Description: ≤ 1024 chars (enforced).\n- Full SKILL.md: ≤ 100,000 chars (enforced as `MAX_SKILL_CONTENT_CHARS`, ~36k tokens).\n- Peer skills in `software-development\u002F` sit at **8-14k chars**. Aim for that range. If you're pushing past 20k, split into `references\u002F*.md` and reference them from SKILL.md.\n\n## Peer-Matched Structure\n\nEvery in-repo skill follows roughly:\n\n```\n# \u003CTitle>\n\n## Overview\nOne or two paragraphs: what and why.\n\n## When to Use\n- Bulleted triggers\n- \"Don't use for:\" counter-triggers\n\n## \u003CTopic sections specific to the skill>\n- Quick-reference tables are common\n- Code blocks with exact commands\n- Hermes-specific recipes (tests via scripts\u002Frun_tests.sh, ui-tui paths, etc.)\n\n## Common Pitfalls\nNumbered list of mistakes and their fixes.\n\n## Verification Checklist\n- [ ] Checkbox list of post-action verifications\n\n## One-Shot Recipes (optional)\nNamed scenarios → concrete command sequences.\n```\n\nNot every section is mandatory, but `Overview` + `When to Use` + actionable body + pitfalls are the minimum for the skill to feel like a peer.\n\n## Directory Placement\n\n```\nskills\u002F\u003Ccategory>\u002F\u003Cskill-name>\u002FSKILL.md\n```\n\nCategories currently in repo (confirm with `ls skills\u002F`): `autonomous-ai-agents`, `creative`, `data-science`, `devops`, `dogfood`, `email`, `gaming`, `github`, `leisure`, `mcp`, `media`, `mlops\u002F*`, `note-taking`, `productivity`, `red-teaming`, `research`, `smart-home`, `social-media`, `software-development`.\n\nPick the closest existing category. Don't invent new top-level categories casually.\n\n## Workflow\n\n1. **Survey peers** in the target category:\n   ```\n   ls skills\u002F\u003Ccategory>\u002F\n   ```\n   Read 2-3 peer SKILL.md files to match tone and structure.\n2. **Check validator constraints** in `tools\u002Fskill_manager_tool.py` if unsure.\n3. **Draft** with `write_file` to `skills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md`.\n4. **Validate locally**:\n   ```python\n   import yaml, re, pathlib\n   content = pathlib.Path(\"skills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md\").read_text()\n   assert content.startswith(\"---\")\n   m = re.search(r'\\n---\\s*\\n', content[3:])\n   fm = yaml.safe_load(content[3:m.start()+3])\n   assert \"name\" in fm and \"description\" in fm\n   assert len(fm[\"description\"]) \u003C= 1024\n   assert len(content) \u003C= 100_000\n   ```\n5. **Git add + commit** on the active branch.\n6. **Note:** the CURRENT session's skill loader is cached — `skill_view` \u002F `skills_list` will not see the new skill until a new session. This is expected, not a bug.\n\n## Cross-Referencing Other Skills\n\n`metadata.hermes.related_skills` unions both trees (`skills\u002F` in-repo and `~\u002F.hermes\u002Fskills\u002F`) at load time. You CAN reference a user-local skill from an in-repo skill, but it won't resolve for other users who clone the repo fresh. Prefer referencing only in-repo skills from in-repo skills. If a frequently-referenced skill lives only in `~\u002F.hermes\u002Fskills\u002F`, consider promoting it to the repo.\n\n## Editing Existing In-Repo Skills\n\n- **Small fix (typo, added pitfall, tightened trigger):** `skill_manage(action='patch', name=..., old_string=..., new_string=...)` works fine on in-repo skills.\n- **Major rewrite:** `write_file` the whole SKILL.md. `skill_manage(action='edit')` also works but requires supplying the full new content.\n- **Adding supporting files:** `write_file` to `skills\u002F\u003Ccategory>\u002F\u003Cname>\u002Freferences\u002F\u003Cfile>.md`, `templates\u002F\u003Cfile>`, or `scripts\u002F\u003Cfile>`. `skill_manage(action='write_file')` also works and enforces the references\u002Ftemplates\u002Fscripts\u002Fassets subdir allowlist.\n- **Always commit** the edit — in-repo skills are source, not runtime state.\n\n## User Preference Embedding\n\nWhen a user corrects the agent's style, tone, format, verbosity, or workflow, encode that correction into a class-level skill or into the current skill's `references\u002F` material. This ensures future sessions start with the correct behavior instead of repeating the same mistake.\n\nRecommended minimal edits when a corrective signal appears:\n\n- Add a one-line explicit rule under a skill's `When to Use` or `Preferences` section (e.g. \"Prefer concise, action-first replies; run tooling immediately when the user requests it and show real outputs\").\n- Create a small `references\u002F\u003Csession-id>.md` that records what changed, what command was run, and the exact tool outputs (redacting secrets). Link to it from the SKILL.md body so future readers and agents can reproduce the change.\n- If the correction is about _how_ to run a class of tasks (order of steps, approvals, safety prompts), add a short \"Pitfall\" entry that shows the wrong way and the corrected sequence.\n- Do NOT harden ephemeral environment details into skill text; put those in references\u002F and mark them as reproducible examples only.\n\nPointers:\n\n- Micro-skill to hold user-level preferences: `productivity\u002Fuser-communication-preferences` (contains references\u002Fsession-2026-06-01.md with a session log).\n- When patching an in-repo skill programmatically, use `skill_manage(action='patch')` for targeted edits and `write_file` for adding `references\u002F` files. Keep patches minimal and reversible.\n\n## Common Pitfalls\n\n1. **Using `skill_manage(action='create')` for an in-repo skill.** It writes to `~\u002F.hermes\u002Fskills\u002F`, not the repo tree. Use `write_file` for in-repo creation.\n\n2. **Leading whitespace before `---`.** The validator checks `content.startswith(\"---\")`; any leading blank line or BOM fails validation.\n\n3. **Description too generic.** Peer descriptions start with \"Use when ...\" and describe the *trigger class*, not the one task. \"Use when debugging X\" > \"Debug X\".\n\n4. **Forgetting the author\u002Flicense\u002Fmetadata block.** Not validator-enforced, but every peer has it; omitting makes the skill look half-finished.\n\n5. **Writing a skill that duplicates a peer.** Before creating, `ls skills\u002F\u003Ccategory>\u002F` and open 2-3 peers. Prefer extending an existing skill to creating a narrow sibling.\n\n6. **Expecting the current session to see the new skill.** It won't. The skill loader is initialized at session start. Verify in a fresh session or via `skill_view` using the exact path.\n\n7. **Linking to skills that don't exist in-repo.** `related_skills: [some-user-local-skill]` works for you but breaks for other clones. Prefer only in-repo links.\n\n## Verification Checklist\n\n- [ ] File is at `skills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md` (not in `~\u002F.hermes\u002Fskills\u002F`)\n- [ ] Frontmatter starts at byte 0 with `---`, closes with `\\n---\\n`\n- [ ] `name`, `description`, `version`, `author`, `license`, `metadata.hermes.{tags, related_skills}` all present\n- [ ] Name ≤ 64 chars, lowercase + hyphens\n- [ ] Description ≤ 1024 chars and starts with \"Use when ...\"\n- [ ] Total file ≤ 100,000 chars (aim for 8-15k)\n- [ ] Structure: `# Title` → `## Overview` → `## When to Use` → body → `## Common Pitfalls` → `## Verification Checklist`\n- [ ] `related_skills` references resolve in-repo (or are explicitly OK to be user-local)\n- [ ] `git add skills\u002F\u003Ccategory>\u002F\u003Cname>\u002F && git commit` completed on the intended branch\n","# Authoring Hermes-Agent Skills (in-repo)\n\n## Overview\n\nThere are two places a SKILL.md can live:\n\n1. **User-local:** `~\u002F.hermes\u002Fskills\u002F\u003Cmaybe-category>\u002F\u003Cname>\u002FSKILL.md` — personal, not shared. Created via `skill_manage(action='create')`.\n2. **In-repo (this skill is about this case):** `\u002Fhome\u002Fbb\u002Fhermes-agent\u002Fskills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md` — committed, shipped with the package. Use `write_file` + `git add`. `skill_manage(action='create')` does NOT target this tree.\n\n## When to Use\n\n- User asks you to add a skill \"in this branch \u002F repo \u002F commit\"\n- You're committing a reusable workflow that should ship with hermes-agent\n- You're editing an existing skill under `\u002Fhome\u002Fbb\u002Fhermes-agent\u002Fskills\u002F` (use `patch` for small edits, `write_file` for rewrites; `skill_manage` still works for patch on in-repo skills, but not for `create`)\n\n## Required Frontmatter\n\nSource of truth: `tools\u002Fskill_manager_tool.py::_validate_frontmatter`. Hard requirements:\n\n- Starts with `---` as the first bytes (no leading blank line).\n- Closes with `\\n---\\n` before the body.\n- Parses as a YAML mapping.\n- `name` field present.\n- `description` field present, ≤ **1024 chars** (`MAX_DESCRIPTION_LENGTH`).\n- Non-empty body after the closing `---`.\n\nPeer-matched shape used by every skill under `skills\u002Fsoftware-development\u002F`:\n\n```yaml\n---\nname: my-skill-name               # lowercase, hyphens, ≤64 chars (MAX_NAME_LENGTH)\ndescription: Use when \u003Ctrigger>. \u003Cone-line behavior>.\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\nmetadata:\n  hermes:\n    tags: [short, descriptive, tags]\n    related_skills: [other-skill, another-skill]\n---\n```\n\n`version` \u002F `author` \u002F `license` \u002F `metadata` are NOT enforced by the validator, but every peer has them — omit and your skill sticks out.\n\n## Size Limits\n\n- Description: ≤ 1024 chars (enforced).\n- Full SKILL.md: ≤ 100,000 chars (enforced as `MAX_SKILL_CONTENT_CHARS`, ~36k tokens).\n- Peer skills in `software-development\u002F` sit at **8-14k chars**. Aim for that range. If you're pushing past 20k, split into `references\u002F*.md` and reference them from SKILL.md.\n\n## Peer-Matched Structure\n\nEvery in-repo skill follows roughly:\n\n```\n# \u003CTitle>\n\n## Overview\nOne or two paragraphs: what and why.\n\n## When to Use\n- Bulleted triggers\n- \"Don't use for:\" counter-triggers\n\n## \u003CTopic sections specific to the skill>\n- Quick-reference tables are common\n- Code blocks with exact commands\n- Hermes-specific recipes (tests via scripts\u002Frun_tests.sh, ui-tui paths, etc.)\n\n## Common Pitfalls\nNumbered list of mistakes and their fixes.\n\n## Verification Checklist\n- [ ] Checkbox list of post-action verifications\n\n## One-Shot Recipes (optional)\nNamed scenarios → concrete command sequences.\n```\n\nNot every section is mandatory, but `Overview` + `When to Use` + actionable body + pitfalls are the minimum for the skill to feel like a peer.\n\n## Directory Placement\n\n```\nskills\u002F\u003Ccategory>\u002F\u003Cskill-name>\u002FSKILL.md\n```\n\nCategories currently in repo (confirm with `ls skills\u002F`): `autonomous-ai-agents`, `creative`, `data-science`, `devops`, `dogfood`, `email`, `gaming`, `github`, `leisure`, `mcp`, `media`, `mlops\u002F*`, `note-taking`, `productivity`, `red-teaming`, `research`, `smart-home`, `social-media`, `software-development`.\n\nPick the closest existing category. Don't invent new top-level categories casually.\n\n## Workflow\n\n1. **Survey peers** in the target category:\n   ```\n   ls skills\u002F\u003Ccategory>\u002F\n   ```\n   Read 2-3 peer SKILL.md files to match tone and structure.\n2. **Check validator constraints** in `tools\u002Fskill_manager_tool.py` if unsure.\n3. **Draft** with `write_file` to `skills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md`.\n4. **Validate locally**:\n   ```python\n   import yaml, re, pathlib\n   content = pathlib.Path(\"skills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md\").read_text()\n   assert content.startswith(\"---\")\n   m = re.search(r'\\n---\\s*\\n', content[3:])\n   fm = yaml.safe_load(content[3:m.start()+3])\n   assert \"name\" in fm and \"description\" in fm\n   assert len(fm[\"description\"]) \u003C= 1024\n   assert len(content) \u003C= 100_000\n   ```\n5. **Git add + commit** on the active branch.\n6. **Note:** the CURRENT session's skill loader is cached — `skill_view` \u002F `skills_list` will not see the new skill until a new session. This is expected, not a bug.\n\n## Cross-Referencing Other Skills\n\n`metadata.hermes.related_skills` unions both trees (`skills\u002F` in-repo and `~\u002F.hermes\u002Fskills\u002F`) at load time. You CAN reference a user-local skill from an in-repo skill, but it won't resolve for other users who clone the repo fresh. Prefer referencing only in-repo skills from in-repo skills. If a frequently-referenced skill lives only in `~\u002F.hermes\u002Fskills\u002F`, consider promoting it to the repo.\n\n## Editing Existing In-Repo Skills\n\n- **Small fix (typo, added pitfall, tightened trigger):** `skill_manage(action='patch', name=..., old_string=..., new_string=...)` works fine on in-repo skills.\n- **Major rewrite:** `write_file` the whole SKILL.md. `skill_manage(action='edit')` also works but requires supplying the full new content.\n- **Adding supporting files:** `write_file` to `skills\u002F\u003Ccategory>\u002F\u003Cname>\u002Freferences\u002F\u003Cfile>.md`, `templates\u002F\u003Cfile>`, or `scripts\u002F\u003Cfile>`. `skill_manage(action='write_file')` also works and enforces the references\u002Ftemplates\u002Fscripts\u002Fassets subdir allowlist.\n- **Always commit** the edit — in-repo skills are source, not runtime state.\n\n## User Preference Embedding\n\nWhen a user corrects the agent's style, tone, format, verbosity, or workflow, encode that correction into a class-level skill or into the current skill's `references\u002F` material. This ensures future sessions start with the correct behavior instead of repeating the same mistake.\n\nRecommended minimal edits when a corrective signal appears:\n\n- Add a one-line explicit rule under a skill's `When to Use` or `Preferences` section (e.g. \"Prefer concise, action-first replies; run tooling immediately when the user requests it and show real outputs\").\n- Create a small `references\u002F\u003Csession-id>.md` that records what changed, what command was run, and the exact tool outputs (redacting secrets). Link to it from the SKILL.md body so future readers and agents can reproduce the change.\n- If the correction is about _how_ to run a class of tasks (order of steps, approvals, safety prompts), add a short \"Pitfall\" entry that shows the wrong way and the corrected sequence.\n- Do NOT harden ephemeral environment details into skill text; put those in references\u002F and mark them as reproducible examples only.\n\nPointers:\n\n- Micro-skill to hold user-level preferences: `productivity\u002Fuser-communication-preferences` (contains references\u002Fsession-2026-06-01.md with a session log).\n- When patching an in-repo skill programmatically, use `skill_manage(action='patch')` for targeted edits and `write_file` for adding `references\u002F` files. Keep patches minimal and reversible.\n\n## Common Pitfalls\n\n1. **Using `skill_manage(action='create')` for an in-repo skill.** It writes to `~\u002F.hermes\u002Fskills\u002F`, not the repo tree. Use `write_file` for in-repo creation.\n\n2. **Leading whitespace before `---`.** The validator checks `content.startswith(\"---\")`; any leading blank line or BOM fails validation.\n\n3. **Description too generic.** Peer descriptions start with \"Use when ...\" and describe the *trigger class*, not the one task. \"Use when debugging X\" > \"Debug X\".\n\n4. **Forgetting the author\u002Flicense\u002Fmetadata block.** Not validator-enforced, but every peer has it; omitting makes the skill look half-finished.\n\n5. **Writing a skill that duplicates a peer.** Before creating, `ls skills\u002F\u003Ccategory>\u002F` and open 2-3 peers. Prefer extending an existing skill to creating a narrow sibling.\n\n6. **Expecting the current session to see the new skill.** It won't. The skill loader is initialized at session start. Verify in a fresh session or via `skill_view` using the exact path.\n\n7. **Linking to skills that don't exist in-repo.** `related_skills: [some-user-local-skill]` works for you but breaks for other clones. Prefer only in-repo links.\n\n## Verification Checklist\n\n- [ ] File is at `skills\u002F\u003Ccategory>\u002F\u003Cname>\u002FSKILL.md` (not in `~\u002F.hermes\u002Fskills\u002F`)\n- [ ] Frontmatter starts at byte 0 with `---`, closes with `\\n---\\n`\n- [ ] `name`, `description`, `version`, `author`, `license`, `metadata.hermes.{tags, related_skills}` all present\n- [ ] Name ≤ 64 chars, lowercase + hyphens\n- [ ] Description ≤ 1024 chars and starts with \"Use when ...\"\n- [ ] Total file ≤ 100,000 chars (aim for 8-15k)\n- [ ] Structure: `# Title` → `## Overview` → `## When to Use` → body → `## Common Pitfalls` → `## Verification Checklist`\n- [ ] `related_skills` references resolve in-repo (or are explicitly OK to be user-local)\n- [ ] `git add skills\u002F\u003Ccategory>\u002F\u003Cname>\u002F && git commit` completed on the intended branch\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":38,"description":7},"Hermes Agent","1.0.0",{"hermes":27},{"tags":28,"reviewed":34,"related_skills":35},[29,30,31,32,33],"skills","authoring","hermes-agent","conventions","skill-md","\\\"2026-06-01 (automated)\\\"",[36,37],"writing-plans","requesting-code-review",[39,40,41],"linux","macos","windows","main","236825fbf4e5956a8cd2b0bf843494f0a5dfaf04","skills\u002Fsoftware-development\u002Fhermes-agent-skill-authoring","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills","https:\u002F\u002Fgithub.com\u002FSatangThevalue","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fsatangthevalue\u002F","Hi, I'm Sa-Tang. 🖐️🖐️🖐️\r\nThanks for following.\r\nสวัสดีครับ สตังค์ครับผม\r\nขอบคุณหรับการติดตามครับ","2026-10-10 12:10:40",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add SatangThevalue\u002Fai-skills --skill hermes-agent-skill-authoring",{"tool":56,"command":57},"bunx","bunx skills add SatangThevalue\u002Fai-skills --skill hermes-agent-skill-authoring",{"tool":59,"command":60},"pnpm","pnpm dlx skills add SatangThevalue\u002Fai-skills --skill hermes-agent-skill-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fhermes-agent-skill-authoring\u002FSKILL.md",true,[64,70],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fuser-preference-embed-guidelines.md","REFERENCE","参考文档",759,"https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fhermes-agent-skill-authoring\u002Freferences\u002Fuser-preference-embed-guidelines.md",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"SKILL.md.bak","OTHER","其他",7618,"https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fhermes-agent-skill-authoring\u002FSKILL.md.bak",[77,83,90,97,104,111],{"skillNo":78,"name":36,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M76TQY0W54NCMRVE9HB8MMTA","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M76TNN9AYY91KD4DT415K1FF","subagent-driven-development","Execute plans via delegate_task subagents (2-stage review).","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M76TME6SXP9SYJZCXX5FFZHR","react-composition-2026","Teaches modern React composition patterns for 2025\u002F2026. Use when designing component APIs, building shared UI libraries, or refactoring prop-heavy components.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Freact-composition-2026\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},"01M76TMAR2D5G9BKZWGEFJKWT2","react-2026","Provides a comprehensive guide to the modern React 2026 stack. Use when starting a new React project or modernizing an existing one with current frameworks, build tools, routing, state management, or AI integration.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Freact-2026\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},"01M76TM2FA8ZFZR1S6ZM34WFFK","plan","Plan mode: write markdown plan to .hermes\u002Fplans\u002F, no exec.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fplan\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},"01M76TJVNAWDZ7DYQK3ZS0X09J","hermes-s6-container-supervision","Modify, debug, or extend the s6-overlay supervision tree inside the Hermes Agent Docker image — adding new services, debugging profile gateways, understanding the Architecture B main-program pattern.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fhermes-s6-container-supervision\u002FSKILL.md",[],[]]