[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD031C3GSZE2P5FN3JKTWE":3,"skill-same:01M7FD031C3GSZE2P5FN3JKTWE":70},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7FD031C3GSZE2P5FN3JKTWE","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.","Abhiman67\u002Fbatcave","Abhiman67","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F137296581?v=4","01M7FCTFR2F0WBMG11VKWGN0KB","ABHISHEK CHHANDAK","01M7FCTFRWXRGV9ZY0060XPK62",0,"MIT","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Freflect\u002FSKILL.md",[],[],"2026-11-16 10:05:34",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.\n---\n\n# Reflect\n\nOn Codex, read the [platform mapping](..\u002Fbatcave-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fbatcave-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\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 Claude Code's per-project transcripts directory at `~\u002F.claude\u002Fprojects\u002F\u003Cencoded-cwd>\u002F`. Do not glob across `~\u002F.claude\u002Fprojects\u002F`. That crosses workspace boundaries and reads private chats from unrelated projects.\n\nRun the finder at `skills\u002Freflect\u002Fscripts\u002Ffind-transcript.mjs` under the installed plugin with the projects directory and a fragment of the conversation's opening user prompt:\n\n```bash\nnode \u003Cplugin>\u002Fskills\u002Freflect\u002Fscripts\u002Ffind-transcript.mjs ~\u002F.claude\u002Fprojects\u002F\u003Cencoded-cwd> \"\u003Copening prompt fragment>\"\n```\n\nIt covers the three layouts (flat `\u003Cid>.jsonl`, nested `\u003Cid>\u002F\u003Cid>.jsonl`, subagent `\u003Cparent>\u002Fsubagents\u002F\u003Cchild>.jsonl`), newest first, and prints the first path whose opening typed prompt carries the fragment. Do not reimplement the scan by hand: the first line of a transcript is session metadata, not a message, a session that starts with `\u002Fclear` or a `!` shell command records that command's wrapper and output as `user` records before the prompt, and files run to several megabytes, so the finder streams each candidate and stops at its first typed `user` record. If it exits 1, write a tight digest of the session and pass that instead. It lists, one line each in turn order, the user's prompts and corrections, the tool calls and their results, and the files touched. It states no diagnosis, verdict, or cause. The reviewers judge the session, not your conclusions about it.\n\n## 2. Spawn three reviewers in parallel\n\nOne message, three `Agent` calls, `subagent_type: \"general-purpose\"`. Reviewers need MCP access to look up the tickets, chat threads, and observability traces the transcript references, so pick a subagent_type that retains MCP access. The prompt forbids file writes. The parent applies edits.\n\nEach reviewer and the synthesizer name a role line in `batcave-models.md` and a default in [Models](#models). Set `model` to that line's value, or to the default if the sheet or the line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If the `Agent` 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. Pick each subagent's reasoning level for the job, per the Subagents section of the **batcave-mode** skill.\n\n| Lens | Role line | Prompt template |\n|---|---|---|\n| Judgment | `reflect judgment, divergent, synthesizer` | `references\u002Fjudgment-reviewer.md` |\n| Tooling | `reflect tooling` | `references\u002Ftooling-reviewer.md` |\n| Divergent | `reflect judgment, divergent, synthesizer` | `references\u002Fdivergent-reviewer.md` |\n\nPass each template verbatim, substituting the transcript path or digest where marked. Add nothing beside a transcript path, not even a focus note for a long transcript. Reviewers return findings in the `Agent` response body.\n\n## 3. Synthesize\n\nOne `Agent` call, `subagent_type: \"general-purpose\"`, `model` from the `reflect judgment, divergent, synthesizer` line (default in [Models](#models)). It spot-verifies citations through MCP, so pick a subagent_type that retains MCP access. 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 the **plugin-dev:skill-development** skill and run its draft \u002F test \u002F iterate loop.\n- `tune description: \u003Cskill path>` (the skill exists but didn't trigger when it should have): hand to `plugin-dev:skill-development` and run its description-optimization loop.\n- `new skill via plugin-dev:skill-development: \u003Ckebab-name>`: hand creation to `plugin-dev:skill-development`. 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\n## Models\n\nRole defaults, stamped from `plugins\u002Fbatcave\u002Fmodels.json` (edit there, rerun `tools\u002Fgenerate.mjs`). A matching role line in the `batcave-models.md` override sheet overrides each at runtime; `\u002Fsetup-batcave` writes it and lists its path per runtime.\n\n- reflect tooling: `opus`\n- reflect judgment, divergent, synthesizer: `opus`\n\n## Reasoning effort\n\nA role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. `session` sets no effort, so the dispatch is the usual one. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. On Claude Code, a level picks the effort agent from the `subagent_type` you would otherwise use. `batcave:batcave-agent` becomes `subagent_type: \"batcave:batcave-agent-\u003Clevel>\"`. `general-purpose`, or no `subagent_type`, becomes `subagent_type: \"batcave:effort-\u003Clevel>\"`. The effort agents set only `effort`, so the model you pass still decides the model. On Codex, pass the level as `spawn_agent`'s `reasoning_effort` and keep the usual instructions.\n","# Reflect\n\nOn Codex, read the [platform mapping](..\u002Fbatcave-mode\u002Freferences\u002Fcodex-tools.md), including its per-skill notes, before following this skill.\n\nOn GitHub Copilot, read the [platform mapping](..\u002Fbatcave-mode\u002Freferences\u002Fcopilot-tools.md), including its per-skill notes, before following this skill.\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 Claude Code's per-project transcripts directory at `~\u002F.claude\u002Fprojects\u002F\u003Cencoded-cwd>\u002F`. Do not glob across `~\u002F.claude\u002Fprojects\u002F`. That crosses workspace boundaries and reads private chats from unrelated projects.\n\nRun the finder at `skills\u002Freflect\u002Fscripts\u002Ffind-transcript.mjs` under the installed plugin with the projects directory and a fragment of the conversation's opening user prompt:\n\n```bash\nnode \u003Cplugin>\u002Fskills\u002Freflect\u002Fscripts\u002Ffind-transcript.mjs ~\u002F.claude\u002Fprojects\u002F\u003Cencoded-cwd> \"\u003Copening prompt fragment>\"\n```\n\nIt covers the three layouts (flat `\u003Cid>.jsonl`, nested `\u003Cid>\u002F\u003Cid>.jsonl`, subagent `\u003Cparent>\u002Fsubagents\u002F\u003Cchild>.jsonl`), newest first, and prints the first path whose opening typed prompt carries the fragment. Do not reimplement the scan by hand: the first line of a transcript is session metadata, not a message, a session that starts with `\u002Fclear` or a `!` shell command records that command's wrapper and output as `user` records before the prompt, and files run to several megabytes, so the finder streams each candidate and stops at its first typed `user` record. If it exits 1, write a tight digest of the session and pass that instead. It lists, one line each in turn order, the user's prompts and corrections, the tool calls and their results, and the files touched. It states no diagnosis, verdict, or cause. The reviewers judge the session, not your conclusions about it.\n\n## 2. Spawn three reviewers in parallel\n\nOne message, three `Agent` calls, `subagent_type: \"general-purpose\"`. Reviewers need MCP access to look up the tickets, chat threads, and observability traces the transcript references, so pick a subagent_type that retains MCP access. The prompt forbids file writes. The parent applies edits.\n\nEach reviewer and the synthesizer name a role line in `batcave-models.md` and a default in [Models](#models). Set `model` to that line's value, or to the default if the sheet or the line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If the `Agent` 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. Pick each subagent's reasoning level for the job, per the Subagents section of the **batcave-mode** skill.\n\n| Lens | Role line | Prompt template |\n|---|---|---|\n| Judgment | `reflect judgment, divergent, synthesizer` | `references\u002Fjudgment-reviewer.md` |\n| Tooling | `reflect tooling` | `references\u002Ftooling-reviewer.md` |\n| Divergent | `reflect judgment, divergent, synthesizer` | `references\u002Fdivergent-reviewer.md` |\n\nPass each template verbatim, substituting the transcript path or digest where marked. Add nothing beside a transcript path, not even a focus note for a long transcript. Reviewers return findings in the `Agent` response body.\n\n## 3. Synthesize\n\nOne `Agent` call, `subagent_type: \"general-purpose\"`, `model` from the `reflect judgment, divergent, synthesizer` line (default in [Models](#models)). It spot-verifies citations through MCP, so pick a subagent_type that retains MCP access. 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 the **plugin-dev:skill-development** skill and run its draft \u002F test \u002F iterate loop.\n- `tune description: \u003Cskill path>` (the skill exists but didn't trigger when it should have): hand to `plugin-dev:skill-development` and run its description-optimization loop.\n- `new skill via plugin-dev:skill-development: \u003Ckebab-name>`: hand creation to `plugin-dev:skill-development`. 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\n## Models\n\nRole defaults, stamped from `plugins\u002Fbatcave\u002Fmodels.json` (edit there, rerun `tools\u002Fgenerate.mjs`). A matching role line in the `batcave-models.md` override sheet overrides each at runtime; `\u002Fsetup-batcave` writes it and lists its path per runtime.\n\n- reflect tooling: `opus`\n- reflect judgment, divergent, synthesizer: `opus`\n\n## Reasoning effort\n\nA role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. `session` sets no effort, so the dispatch is the usual one. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. On Claude Code, a level picks the effort agent from the `subagent_type` you would otherwise use. `batcave:batcave-agent` becomes `subagent_type: \"batcave:batcave-agent-\u003Clevel>\"`. `general-purpose`, or no `subagent_type`, becomes `subagent_type: \"batcave:effort-\u003Clevel>\"`. The effort agents set only `effort`, so the model you pass still decides the model. On Codex, pass the level as `spawn_agent`'s `reasoning_effort` and keep the usual instructions.\n",{"name":5,"description":7},"master","ffa275487ca7faa89d4a38dbc6eecab994d812dd","plugins\u002Fbatcave\u002Fskills\u002Freflect","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave","https:\u002F\u002Fgithub.com\u002FAbhiman67","https:\u002F\u002Fabhishekchhandak.vercel.app\u002F","hehehehehe\r\n","2026-11-12 08:25:16",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Abhiman67\u002Fbatcave --skill reflect",{"tool":38,"command":39},"bunx","bunx skills add Abhiman67\u002Fbatcave --skill reflect",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Abhiman67\u002Fbatcave --skill reflect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Freflect\u002FSKILL.md",true,[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdivergent-reviewer.md","REFERENCE","参考文档",3669,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Freflect\u002Freferences\u002Fdivergent-reviewer.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fjudgment-reviewer.md",3108,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Freflect\u002Freferences\u002Fjudgment-reviewer.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fsynthesizer.md",4189,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Freflect\u002Freferences\u002Fsynthesizer.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftooling-reviewer.md",4449,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Freflect\u002Freferences\u002Ftooling-reviewer.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Ffind-transcript.mjs","SCRIPT","脚本",7864,"https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Freflect\u002Fscripts\u002Ffind-transcript.mjs",[71,78,85,92,99,106],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7FD1NSBZDQSC0TP75CQN7A8","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\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7FD1KGG5Q5MZ3T8C0TQG7CN","what-did-i-get-done","Summarize authored commits over a user-specified time period into a concise update","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fwhat-did-i-get-done\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7FD1HZPM0F0YKYXMYASCPA7","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Funslop\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":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7FD1FXWCE2MY0VZYZ0TRBMW","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7FD1D8QPK5VVKABPGX4CENW","thermos","Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug\u002Fsecurity and code-quality branch audits.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fthermos\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7FD18VJ6EGHPFKXFJB8PN3S","thermo-nuclear-review","Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch\u002FPR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.","https:\u002F\u002Fgithub.com\u002FAbhiman67\u002Fbatcave\u002Fblob\u002Fmaster\u002Fplugins\u002Fbatcave\u002Fskills\u002Fthermo-nuclear-review\u002FSKILL.md",[],[]]