[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78D53MDQZB8RWTGJXZRVST9":3,"skill-same:01M78D53MDQZB8RWTGJXZRVST9":68},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M78D53MDQZB8RWTGJXZRVST9","reflect",null,"Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.","emo-eth\u002Fskills","emo-eth","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6371847?v=4","01M78CWE28WS3JH2WXYPRNC26K","James","01M78CWE2YS6Y5883W8J0D60XA",0,"MIT","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Freflect\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Freflect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: reflect\ndescription: Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.\ndisable-model-invocation: true\n---\n\n# Reflect\n\nRead `pstack-runtime` before the first host-specific operation.\n\nMine the current conversation for durable learnings, then route them into skill edits.\n\n## When to invoke\n\n- The user said \"reflect\" or \"\u002Freflect\".\n- A complex task (5+ tool calls) just landed cleanly and the recipe is worth keeping.\n- The agent hit dead ends, found the working path, and the path generalizes.\n- The user corrected the agent's approach mid-task.\n- A non-trivial workflow emerged that isn't captured anywhere.\n\nSkip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings.\n\n## Process\n\n### 1. Locate the active transcript\n\nUse `agent-conv thread \u003Ccurrent-workspace> --source omp` when available. The exact current directory is the workspace query. Otherwise inspect only the matching workspace under `~\u002F.omp\u002Fagent\u002Fsessions\u002F`, order candidates by modification time, and match the opening user prompt. If no path resolves, write a tight session digest.\n\n### 2. Spawn three reviewers in parallel\n\nLaunch three read-only reviewers in one OMP `task` batch. Read `reflect-judgment` and `reflect-tooling` from `~\u002F.config\u002Fpstack\u002Fomp-agents.json` when present. Otherwise use `reviewer` for all three. The prompts forbid file writes; the parent applies approved edits.\n\n| Lens | OMP agent role | Prompt template |\n|---|---|---|\n| Judgment | `reflect-judgment` | `references\u002Fjudgment-reviewer.md` |\n| Tooling | `reflect-tooling` | `references\u002Ftooling-reviewer.md` |\n| Divergent | `reflect-judgment` | `references\u002Fdivergent-reviewer.md` |\n\nPass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the `task` result.\n\n### 3. Synthesize\n\nSpawn one read-only synthesis task. Use `reflect-judgment` from the OMP config, or `reviewer` by default. Use `references\u002Fsynthesizer.md` verbatim and pass large reviewer outputs through `local:\u002F\u002F` artifacts. The synthesizer returns Accepted \u002F Rejected \u002F Backlog.\n\n### 4. Structural enforcement check\n\nSanity-check the synthesizer's Accepted list. For any item that would be enforced more reliably by a lint rule, script, metadata flag, or runtime check, move it from Accepted to Backlog. The synthesizer already applies this criterion; this is a final pass before edits land. See the **encode-lessons-in-structure** principle skill.\n\n### 5. Apply\n\nBefore applying any Accepted edit, present the synthesizer's full Accepted\u002FRejected\u002FBacklog output to the user and wait for explicit approval. The user picks which subset to apply and may redirect routings. Skill changes affect every future agent in the org; do not auto-apply.\n\nReport Backlog items. File one only when the user asked for tracker updates and the tracker tool is available.\n\nFor each approved Accepted item, follow the Routing field exactly:\n\n- Trivial existing-skill edit: apply it directly in `~\u002Fdev\u002Fskills\u002Fskills\u002F\u003Cname>\u002F`.\n- Substantive edit, trigger tuning, or new skill: follow `skill:\u002F\u002Fpoteto-mode\u002Fplaybooks\u002Fauthoring-a-skill.md` in `~\u002Fdev\u002Fskills`.\n- After any approved skill edit, follow `~\u002Fdev\u002Fskills\u002FAGENTS.md`: update project state when needed, commit, push `main`, and refresh the installed skill with `npx skills`.\n\nValidate every changed skill by checking its frontmatter, folder\u002Fname match, relative links, and OMP-only tool vocabulary.\n\n### 6. Summarize for the user\n\nShort list, no preamble:\n\n- Edits applied: `\u003Cskill path>`. What changed, one line each.\n- New skills created: `\u003Cskill path>`. One line each (rare).\n- Backlog reported or filed: `\u003Cissue title>` (`\u003Ctags>`). One line each.\n- Dropped: one line per rejected finding + reason from the synthesizer.\n","# Reflect\n\nRead `pstack-runtime` before the first host-specific operation.\n\nMine the current conversation for durable learnings, then route them into skill edits.\n\n## When to invoke\n\n- The user said \"reflect\" or \"\u002Freflect\".\n- A complex task (5+ tool calls) just landed cleanly and the recipe is worth keeping.\n- The agent hit dead ends, found the working path, and the path generalizes.\n- The user corrected the agent's approach mid-task.\n- A non-trivial workflow emerged that isn't captured anywhere.\n\nSkip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings.\n\n## Process\n\n### 1. Locate the active transcript\n\nUse `agent-conv thread \u003Ccurrent-workspace> --source omp` when available. The exact current directory is the workspace query. Otherwise inspect only the matching workspace under `~\u002F.omp\u002Fagent\u002Fsessions\u002F`, order candidates by modification time, and match the opening user prompt. If no path resolves, write a tight session digest.\n\n### 2. Spawn three reviewers in parallel\n\nLaunch three read-only reviewers in one OMP `task` batch. Read `reflect-judgment` and `reflect-tooling` from `~\u002F.config\u002Fpstack\u002Fomp-agents.json` when present. Otherwise use `reviewer` for all three. The prompts forbid file writes; the parent applies approved edits.\n\n| Lens | OMP agent role | Prompt template |\n|---|---|---|\n| Judgment | `reflect-judgment` | `references\u002Fjudgment-reviewer.md` |\n| Tooling | `reflect-tooling` | `references\u002Ftooling-reviewer.md` |\n| Divergent | `reflect-judgment` | `references\u002Fdivergent-reviewer.md` |\n\nPass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the `task` result.\n\n### 3. Synthesize\n\nSpawn one read-only synthesis task. Use `reflect-judgment` from the OMP config, or `reviewer` by default. Use `references\u002Fsynthesizer.md` verbatim and pass large reviewer outputs through `local:\u002F\u002F` artifacts. The synthesizer returns Accepted \u002F Rejected \u002F Backlog.\n\n### 4. Structural enforcement check\n\nSanity-check the synthesizer's Accepted list. For any item that would be enforced more reliably by a lint rule, script, metadata flag, or runtime check, move it from Accepted to Backlog. The synthesizer already applies this criterion; this is a final pass before edits land. See the **encode-lessons-in-structure** principle skill.\n\n### 5. Apply\n\nBefore applying any Accepted edit, present the synthesizer's full Accepted\u002FRejected\u002FBacklog output to the user and wait for explicit approval. The user picks which subset to apply and may redirect routings. Skill changes affect every future agent in the org; do not auto-apply.\n\nReport Backlog items. File one only when the user asked for tracker updates and the tracker tool is available.\n\nFor each approved Accepted item, follow the Routing field exactly:\n\n- Trivial existing-skill edit: apply it directly in `~\u002Fdev\u002Fskills\u002Fskills\u002F\u003Cname>\u002F`.\n- Substantive edit, trigger tuning, or new skill: follow `skill:\u002F\u002Fpoteto-mode\u002Fplaybooks\u002Fauthoring-a-skill.md` in `~\u002Fdev\u002Fskills`.\n- After any approved skill edit, follow `~\u002Fdev\u002Fskills\u002FAGENTS.md`: update project state when needed, commit, push `main`, and refresh the installed skill with `npx skills`.\n\nValidate every changed skill by checking its frontmatter, folder\u002Fname match, relative links, and OMP-only tool vocabulary.\n\n### 6. Summarize for the user\n\nShort list, no preamble:\n\n- Edits applied: `\u003Cskill path>`. What changed, one line each.\n- New skills created: `\u003Cskill path>`. One line each (rare).\n- Backlog reported or filed: `\u003Cissue title>` (`\u003Ctags>`). One line each.\n- Dropped: one line per rejected finding + reason from the synthesizer.\n",{"name":5,"description":7,"disable-model-invocation":25},true,"main","556c6b2a01f1f75137a940333ffc8bd95cf0756e","skills\u002Fpstack\u002Freflect","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills","https:\u002F\u002Fgithub.com\u002Femo-eth","I make music and write code","2026-11-13 05:13:04",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add emo-eth\u002Fskills --skill reflect",{"tool":39,"command":40},"bunx","bunx skills add emo-eth\u002Fskills --skill reflect",{"tool":42,"command":43},"pnpm","pnpm dlx skills add emo-eth\u002Fskills --skill reflect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Freflect\u002FSKILL.md",[46,50,56,60,64],{"path":47,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":16},"LICENSE","许可证",1067,{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdivergent-reviewer.md","REFERENCE","参考文档",3914,"https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Freflect\u002Freferences\u002Fdivergent-reviewer.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fjudgment-reviewer.md",3280,"https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Freflect\u002Freferences\u002Fjudgment-reviewer.md",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsynthesizer.md",4164,"https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Freflect\u002Freferences\u002Fsynthesizer.md",{"path":65,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftooling-reviewer.md",4753,"https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Freflect\u002Freferences\u002Ftooling-reviewer.md",[69,76,84,92,100,108],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":20},"01M78D75SMNM5JJXJGN9W6Z304","system-vibe","Personal operating-system contract for the home fleet, sync, SSH, skills, Herdr, and local inference. Use when diagnosing or changing machines, chezmoi, SSH, skill distribution, Windows sleep\u002Fwake, or the local model router. This is the qualitative list of what must stay true; agents invent enforcement from the clauses, not from tribal setup lore.","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsystem-vibe\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":80,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":20},"01M78D65Z8HK3VTSAWKC59TR94","rubber-stamp-travel-field-note","Use for rubber-stamp travel field-note photo posters.","CC-BY-4.0","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frubber-stamp-travel-field-note\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":20},"01M78D5VXYSJZVTGETSYGZWQPQ","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":20},"01M78D5SMN2NTGT19B2T5WY83T","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Funslop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Funslop\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":20},"01M78D5PN73KA6B88JVHABNTKY","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftypescript-best-practices\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":20},"01M78D5JHTG4B6YPZ8TNN18Y6D","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftechnical-writing\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Femo-eth\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftechnical-writing\u002FSKILL.md",[],[]]