[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P7Y6XM9PS4T0GAEMVW0CWV":3,"skill-same:01M6P7Y6XM9PS4T0GAEMVW0CWV":87},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":45,"updatedAt":46,"install":47,"resources":59},"01M6P7Y6XM9PS4T0GAEMVW0CWV","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.","sarthchawla\u002FSetupMyAI","sarthchawla","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F41484686?v=4","01M6P7D22NFMY9MA11Q2YGPKV2","Sarthak Chawla","01M6P7D26JJ9KW98SD1G8BB83R",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Fpstack\u002Fskills\u002Freflect\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"review","transcript","parallel","edit","user","spawn","subagents","use","learnings","route","three","existing skill","active","true","Existing","2026-11-10 10:12:30",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\nMine the current conversation for durable learnings, then route them into skill edits.\n\nInvoke when the user says \"reflect\" or \"\u002Freflect\". Skip 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## 1. Locate the active transcript\n\nBefore fanning out, find this conversation's transcript in the active workspace's session directory. Do not glob across every project's directory. That crosses workspace boundaries and reads private chats from unrelated projects.\n\nWhere the transcript lives depends on your harness:\n\n- **Cursor:** the `agent-transcripts\u002F` directory the system prompt names.\n\n  ```bash\n  ls -t \u003Cagent-transcripts>\u002F*.jsonl \u003Cagent-transcripts>\u002F*\u002F*.jsonl \u003Cagent-transcripts>\u002F*\u002Fsubagents\u002F*.jsonl 2>\u002Fdev\u002Fnull | head -10\n  ```\n\n  That covers the legacy flat (`\u003Cid>.jsonl`), current nested (`\u003Cid>\u002F\u003Cid>.jsonl`), and subagent (`\u003Cparent>\u002Fsubagents\u002F\u003Cchild>.jsonl`) layouts. For each candidate, read the first JSONL line. Take the file whose `message.content[0].text` contains the conversation's opening user prompt.\n- **Claude Code:** `~\u002F.claude\u002Fprojects\u002F\u003Cslug>\u002F\u003Csession-id>.jsonl`, where `\u003Cslug>` is the workspace path with every character that isn't a letter or digit turned into \"-\".\n- **Pi:** `~\u002F.pi\u002Fagent\u002Fsessions\u002F--\u003Cslug>--\u002F*.jsonl`, where `\u003Cslug>` is the workspace path with the leading slash dropped and each \"\u002F\" turned into \"-\".\n- **Codex:** `~\u002F.codex\u002Fsessions\u002FYYYY\u002FMM\u002FDD\u002Frollout-*.jsonl`. Keep only files whose first line has `payload.cwd` equal to the workspace path.\n- **Other harnesses:** check the harness's session directory for this workspace.\n\nOutside Cursor, take the newest candidates first and confirm one by finding the conversation's opening user prompt in its first user message. If none matches, pass a tight digest of the session instead.\n\n## 2. Spawn three reviewers in parallel\n\nOne message, three `Task` calls, `subagent_type: generalPurpose`, agent mode (`readonly: false`). Reviewers need MCP access to look up the tickets, chat threads, and observability traces the transcript references, and readonly strips MCPs.\n\n**Other harnesses.** The spawns in this skill use Cursor's `Task` tool. In another harness, use its subagent tool: `Agent` in Claude Code (`subagent_type: general-purpose`), `task` in OpenCode (`subagent_type: general`), `spawn_agent` in Codex. Keep the prompt and the model. Drop parameters your tool doesn't have. If your harness has no subagent tool, as in Pi without an extension, run each role yourself, one after another.\n\nEach reviewer and the synthesizer name a role line in the pstack settings file (`~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` in Cursor, `~\u002F.claude\u002Frules\u002Fpstack-models.md` in Claude Code, `~\u002F.agents\u002Fpstack-models.md` in other harnesses) and a default. Set `model` to that line's value, or to the default if the file or the line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If your subagent tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message or your harness's model list. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill.\n\n| Lens | Role line | Default `model` | Prompt template |\n|---|---|---|---|\n| Judgment | `reflect judgment, divergent, synthesizer` | `claude-opus-5-5-xhigh` | `references\u002Fjudgment-reviewer.md` |\n| Tooling | `reflect tooling` | `grok-4.7-xhigh-fast` | `references\u002Ftooling-reviewer.md` |\n| Divergent | `reflect judgment, divergent, synthesizer` | `claude-opus-5-5-xhigh` | `references\u002Fdivergent-reviewer.md` |\n\nPass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the `Task` response body.\n\n## 3. Synthesize\n\nOne `Task` call, `subagent_type: generalPurpose`, `model` from the `reflect judgment, divergent, synthesizer` line (default `claude-opus-5-5-xhigh`), agent mode (`readonly: false`). It spot-verifies citations through MCP, and readonly strips MCPs. Pass `references\u002Fsynthesizer.md` verbatim, with each reviewer's full output inlined where marked. It returns an Accepted \u002F Rejected \u002F Backlog list.\n\n## 4. Structural enforcement check\n\nMove any Accepted item that a lint rule, script, metadata flag, or runtime check would enforce more reliably to Backlog. See the **encode-lessons-in-structure** principle skill.\n\n## 5. Apply\n\nPresent the synthesizer's full Accepted \u002F Rejected \u002F Backlog output and wait for explicit approval before applying any Accepted edit. The user picks the subset and may redirect routings. Skill changes affect every future agent in the org. Do not auto-apply.\n\nFile each Backlog item to your team's devex or backlog tracker without waiting. Only the Accepted list waits for approval.\n\nFollow each approved row's Routing exactly:\n\n- Trivial existing-skill edit (a one-line bullet, a tightened sentence, a stale fact corrected): the parent does it directly.\n- Substantive existing-skill edit (a new section, a new pattern table, more than ~10 lines): hand to your harness's skill-authoring skill and run its draft \u002F test \u002F iterate loop. That is `create-skill` in Cursor (built in) or Anthropic's `skill-creator`. If you have neither, follow the Agent Skills format at agentskills.io. \"`create-skill`\" below means whichever of these you use.\n- `tune description: \u003Cskill path>` (the skill exists but didn't trigger when it should have): hand to `create-skill` and run its description-optimization loop.\n- `new skill via create-skill: \u003Ckebab-name>`: hand creation to `create-skill`. Do not invent the shape ad hoc.\n\nIf your environment ships a SKILL.md validator, run it on every touched skill before declaring done.\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 filed to the devex tracker: `\u003Cissue title>` (`\u003Ctags>`). One line each.\n- Dropped: one line per rejected finding + reason from the synthesizer.\n","# Reflect\n\nMine the current conversation for durable learnings, then route them into skill edits.\n\nInvoke when the user says \"reflect\" or \"\u002Freflect\". Skip 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## 1. Locate the active transcript\n\nBefore fanning out, find this conversation's transcript in the active workspace's session directory. Do not glob across every project's directory. That crosses workspace boundaries and reads private chats from unrelated projects.\n\nWhere the transcript lives depends on your harness:\n\n- **Cursor:** the `agent-transcripts\u002F` directory the system prompt names.\n\n  ```bash\n  ls -t \u003Cagent-transcripts>\u002F*.jsonl \u003Cagent-transcripts>\u002F*\u002F*.jsonl \u003Cagent-transcripts>\u002F*\u002Fsubagents\u002F*.jsonl 2>\u002Fdev\u002Fnull | head -10\n  ```\n\n  That covers the legacy flat (`\u003Cid>.jsonl`), current nested (`\u003Cid>\u002F\u003Cid>.jsonl`), and subagent (`\u003Cparent>\u002Fsubagents\u002F\u003Cchild>.jsonl`) layouts. For each candidate, read the first JSONL line. Take the file whose `message.content[0].text` contains the conversation's opening user prompt.\n- **Claude Code:** `~\u002F.claude\u002Fprojects\u002F\u003Cslug>\u002F\u003Csession-id>.jsonl`, where `\u003Cslug>` is the workspace path with every character that isn't a letter or digit turned into \"-\".\n- **Pi:** `~\u002F.pi\u002Fagent\u002Fsessions\u002F--\u003Cslug>--\u002F*.jsonl`, where `\u003Cslug>` is the workspace path with the leading slash dropped and each \"\u002F\" turned into \"-\".\n- **Codex:** `~\u002F.codex\u002Fsessions\u002FYYYY\u002FMM\u002FDD\u002Frollout-*.jsonl`. Keep only files whose first line has `payload.cwd` equal to the workspace path.\n- **Other harnesses:** check the harness's session directory for this workspace.\n\nOutside Cursor, take the newest candidates first and confirm one by finding the conversation's opening user prompt in its first user message. If none matches, pass a tight digest of the session instead.\n\n## 2. Spawn three reviewers in parallel\n\nOne message, three `Task` calls, `subagent_type: generalPurpose`, agent mode (`readonly: false`). Reviewers need MCP access to look up the tickets, chat threads, and observability traces the transcript references, and readonly strips MCPs.\n\n**Other harnesses.** The spawns in this skill use Cursor's `Task` tool. In another harness, use its subagent tool: `Agent` in Claude Code (`subagent_type: general-purpose`), `task` in OpenCode (`subagent_type: general`), `spawn_agent` in Codex. Keep the prompt and the model. Drop parameters your tool doesn't have. If your harness has no subagent tool, as in Pi without an extension, run each role yourself, one after another.\n\nEach reviewer and the synthesizer name a role line in the pstack settings file (`~\u002F.cursor\u002Frules\u002Fpstack-models.mdc` in Cursor, `~\u002F.claude\u002Frules\u002Fpstack-models.md` in Claude Code, `~\u002F.agents\u002Fpstack-models.md` in other harnesses) and a default. Set `model` to that line's value, or to the default if the file or the line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If your subagent tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message or your harness's model list. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the **poteto-mode** skill.\n\n| Lens | Role line | Default `model` | Prompt template |\n|---|---|---|---|\n| Judgment | `reflect judgment, divergent, synthesizer` | `claude-opus-5-5-xhigh` | `references\u002Fjudgment-reviewer.md` |\n| Tooling | `reflect tooling` | `grok-4.7-xhigh-fast` | `references\u002Ftooling-reviewer.md` |\n| Divergent | `reflect judgment, divergent, synthesizer` | `claude-opus-5-5-xhigh` | `references\u002Fdivergent-reviewer.md` |\n\nPass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the `Task` response body.\n\n## 3. Synthesize\n\nOne `Task` call, `subagent_type: generalPurpose`, `model` from the `reflect judgment, divergent, synthesizer` line (default `claude-opus-5-5-xhigh`), agent mode (`readonly: false`). It spot-verifies citations through MCP, and readonly strips MCPs. Pass `references\u002Fsynthesizer.md` verbatim, with each reviewer's full output inlined where marked. It returns an Accepted \u002F Rejected \u002F Backlog list.\n\n## 4. Structural enforcement check\n\nMove any Accepted item that a lint rule, script, metadata flag, or runtime check would enforce more reliably to Backlog. See the **encode-lessons-in-structure** principle skill.\n\n## 5. Apply\n\nPresent the synthesizer's full Accepted \u002F Rejected \u002F Backlog output and wait for explicit approval before applying any Accepted edit. The user picks the subset and may redirect routings. Skill changes affect every future agent in the org. Do not auto-apply.\n\nFile each Backlog item to your team's devex or backlog tracker without waiting. Only the Accepted list waits for approval.\n\nFollow each approved row's Routing exactly:\n\n- Trivial existing-skill edit (a one-line bullet, a tightened sentence, a stale fact corrected): the parent does it directly.\n- Substantive existing-skill edit (a new section, a new pattern table, more than ~10 lines): hand to your harness's skill-authoring skill and run its draft \u002F test \u002F iterate loop. That is `create-skill` in Cursor (built in) or Anthropic's `skill-creator`. If you have neither, follow the Agent Skills format at agentskills.io. \"`create-skill`\" below means whichever of these you use.\n- `tune description: \u003Cskill path>` (the skill exists but didn't trigger when it should have): hand to `create-skill` and run its description-optimization loop.\n- `new skill via create-skill: \u003Ckebab-name>`: hand creation to `create-skill`. Do not invent the shape ad hoc.\n\nIf your environment ships a SKILL.md validator, run it on every touched skill before declaring done.\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 filed to the devex tracker: `\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":39},true,"main","3934845b800ff514cb89eb81d43f3dc4cbf51ff2","packages\u002Fpstack\u002Fskills\u002Freflect","https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI","https:\u002F\u002Fgithub.com\u002Fsarthchawla","there ain't no problem i can't solve","2026-10-23 01:26:57",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":39},[49,52,55],{"tool":50,"command":51},"npx","npx skills add sarthchawla\u002FSetupMyAI --skill reflect",{"tool":53,"command":54},"bunx","bunx skills add sarthchawla\u002FSetupMyAI --skill reflect",{"tool":56,"command":57},"pnpm","pnpm dlx skills add sarthchawla\u002FSetupMyAI --skill reflect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Fpstack\u002Fskills\u002Freflect\u002FSKILL.md",[60,66,71,75,79,83],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"agents\u002Fopenai.yaml","REFERENCE","参考文档",43,"https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Fpstack\u002Fskills\u002Freflect\u002Fagents\u002Fopenai.yaml",{"path":67,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"LICENSE","许可证",1067,"https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Fpstack\u002Fskills\u002Freflect\u002FLICENSE",{"path":72,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fdivergent-reviewer.md",4010,"https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Fpstack\u002Fskills\u002Freflect\u002Freferences\u002Fdivergent-reviewer.md",{"path":76,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fjudgment-reviewer.md",3449,"https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Fpstack\u002Fskills\u002Freflect\u002Freferences\u002Fjudgment-reviewer.md",{"path":80,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fsynthesizer.md",4141,"https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Fpstack\u002Fskills\u002Freflect\u002Freferences\u002Fsynthesizer.md",{"path":84,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Ftooling-reviewer.md",4790,"https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Fpstack\u002Fskills\u002Freflect\u002Freferences\u002Ftooling-reviewer.md",[88,101,117,126,134,154],{"skillNo":89,"name":90,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":98,"publishedAt":34},"01M6P8953HNC422WFQSPP2FMQE","sample-skill","https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-repo\u002F.claude\u002Fskills\u002Fsample-skill\u002FSKILL.md",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[99,100],"sample","sample skill",{"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":34},"01M6P8924ZSDAZ88Y5Q9P3KAQV","synthetic-review-candidate","Candidate for smoke testing an evaluation runner only.","https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fscripts\u002Fskill-eval\u002Ffixtures\u002Fcandidate\u002FSKILL.md",[],[108,109,110,19,111,112,113,114,115,116],"synthetic review candidate","candidate","synthetic","only","testing","Evaluation","smoke","runner","for",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":34},"01M6P88FEGGNH8EZY0PDHD9KQA","synthetic-review-baseline","Baseline for smoke testing an evaluation runner only.","https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fscripts\u002Fskill-eval\u002Ffixtures\u002Fbaseline\u002FSKILL.md",[],[124,110,125,19,114,115,116,111,112,113],"synthetic review baseline","baseline",{"skillNo":127,"name":19,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":34},"01M6P87ZXVEHRM860960DB5FEQ","Run the existing user-invoked review bundle and independently adjudicate its findings.","https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Funiversal\u002Fskills\u002Freview\u002FSKILL.md",[],[19,132,23,133,33],"run","bundle",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":34},"01M6P87FC73MZTRB6ZBP4GR1VQ","review-adjudication","Verify generated or human review findings before fixing, defending, replying, resolving, or reusing them as learned guidance. Use within a review, review-comment fix, monitor, or readiness workflow.","https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Funiversal\u002Fskills\u002Freview-adjudication\u002FSKILL.md",[],[141,19,142,143,144,145,146,147,148,149,150,151,26,152,153],"review adjudication","workflow","generated","human review","guidance","human","as","readiness","learned","review findings","fix","verify","monitor",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":34},"01M6P871Q44KQES293T60JQETA","monitor-mr","Monitor review findings and CI using the shared adjudication procedure.","https:\u002F\u002Fgithub.com\u002Fsarthchawla\u002FSetupMyAI\u002Fblob\u002Fmain\u002Fpackages\u002Funiversal\u002Fskills\u002Fmonitor-mr\u002FSKILL.md",[],[153,161,162,150,163,164,19],"mr","monitor mr","shared","ci"]