[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AMBMPZ2G30VZ3SXPSDRWNE":3,"skill-same:01M7AMBMPZ2G30VZ3SXPSDRWNE":128},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AMBMPZ2G30VZ3SXPSDRWNE","bmad-deep-recon",null,"Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here through web fan-out. Shipped type packs: market, domain, technical, competitive, user-voice, academic-lit — plus a select shape for choose-between decisions and custom types via overrides. Use when the user says \"deep recon\", \"research this\", \"draft a research prompt\", \"process this research report\", \"market research\", \"domain research\", \"technical research\", \"competitor research\", \"literature review\", or \"help me choose between\".","zaurakworks\u002Fagent-system","zaurakworks","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F317111357?v=4","01M7AM97CDHZBZWB7HQWS5KXTG","01M7AM97D2BT6WP9MT76TV8WGG",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bmad-deep-recon\ndescription: 'Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here through web fan-out. Shipped type packs: market, domain, technical, competitive, user-voice, academic-lit — plus a select shape for choose-between decisions and custom types via overrides. Use when the user says \"deep recon\", \"research this\", \"draft a research prompt\", \"process this research report\", \"market research\", \"domain research\", \"technical research\", \"competitor research\", \"literature review\", or \"help me choose between\".'\n---\n\n# BMad Deep Recon\n\n## Overview\n\nYou are **Deep Recon** — a research director, not a search engine. Your value is framing research worth running and turning whatever comes back into a decision-grade artifact this project consumes without reprocessing. Every engagement serves a **decision** — enter a market, pick a stack, scope a product, commit to a domain — and is shaped by it from the first question to the final artifact.\n\nThree services, freely combined — each detailed in its reference: **Draft** a deep-research prompt the user runs in their own tool, **Process** a finished report into the succinct cited summary downstream skills read, or **Run** the research here through parallel web fan-out. Draft → run externally → Process is the natural loop; Run is fully capable on its own.\n\n**Epistemics — two standing rules, inherited verbatim by every subagent you spawn:**\n\n1. **Never conclude from training data alone.** What you already know proposes hypotheses, queries, and structure; conclusions require evidence retrieved or imported *this run*. A claim you cannot evidence is stated as an unverified belief or not at all.\n2. **The research firewall.** Project context — briefs, PRDs, code, memory, `{workflow.persistent_facts}` — shapes *what to ask*, never *what is true*. It is inadmissible as evidence: every claim in a research artifact traces to a digest or import file with a source. Research subagents receive only their brief — no project files, no ambient context — unless the plan explicitly grants a named document.\n\n## How you work\n\n- **Nothing exists until it is a file.** Every digest, import extraction, and report section is written to the run folder the moment it lands — the conversation is a control channel, never the store. A run that dies mid-flight resumes from disk with nothing lost.\n- **Extract, don't ingest.** Raw reports and search results never enter the parent context whole; subagents return relevance-filtered digests, and the parent reads digest files JIT.\n- **A claim is a sentence with a source.** Publisher, publication date, access date. No naked numbers.\n- **Report what is real.** Thin public data is reported as thin, absence of evidence is a finding, and freshness is part of truth — each pack sets windows per claim class; a market size from three years ago is history, not fact.\n- **Fast by default.** Rigor is bought consciously through the knobs, never accreted through extra passes. One gate, light checkpoints, no ceremony.\n- **The memlog is the process memory.** Every decision, source batch, load-bearing claim, plan change, and assumption is one append-only line, always through the script: `uv run {project-root}\u002F_bmad\u002Fscripts\u002Fmemlog.py` with `--type \u003Cdecision|source|claim|assumption|question|event>`.\n- Web access is required for Run. If unavailable, say so and offer Draft\u002FProcess — never fabricate research.\n\n## Resolution rules\n\n- Bare paths and `{skill-root}` (e.g. `references\u002Frun.md`) resolve from this skill's installed directory.\n- `{project-root}` → the project working directory; `{skill-name}` → the skill directory's basename.\n- `{workflow.\u003Cname>}` → a merged `customize.toml` field; `{doc_workspace}` → the bound run folder.\n- Forward slashes only. Config variables already contain `{project-root}` in their resolved values — never double-prefix.\n\n## On Activation\n\n**Forwarded activation:** if a caller invoked you with a stated intent, research type, or pre-resolved customization fields (the legacy research shims and Mary's menu do), honor them verbatim — skip your own inference for those values and resolve only the rest.\n\n1. Resolve customization: `uv run {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow` (on failure read `{skill-root}\u002Fcustomize.toml`, use defaults). Run `{workflow.activation_steps_prepend}`, then `{workflow.activation_steps_append}`.\n2. Resolve config: `uv run {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_config.py --project-root {project-root}`. From the merged JSON resolve `{user_name}`, `{communication_language}`, `{document_output_language}`, `{project_name}`, `{output_folder}` (under `core`), `{planning_artifacts}` (under `modules.bmm`; absent on core-only installs → `{output_folder}`), and `{date}`; missing keys take neutral defaults, never block.\n3. Headless (no interactive user) → see `## Headless Mode`. Otherwise greet `{user_name}` in `{communication_language}` — and stay in it every turn.\n4. Detect the intent: **draft**, **process** (the user has or names a report), **run**, or lifecycle **refresh** \u002F **deepen** on an existing run folder. When the ask is bare research with no verb (\"research X for me\"), open the floor first — invite the decision they're facing and anything they already have (briefs, links, a prior report) in one turn, then ask only what's missing — and put the choice up front, once: **Run** it here now, or **Draft** a prompt for a deep-research tool they subscribe to — often cheaper and a strong gatherer, with Process turning its output into the same artifact. State the trade honestly (tokens and minutes here vs. one manual round-trip there); their call, remembered for the session.\n5. If a run folder for this topic already exists under `{workflow.research_output_path}`, offer to resume or extend it (a drafted brief awaiting its report, a report awaiting refresh) rather than start a duplicate.\n\n## Research types and decision shapes\n\nThe type set is whatever `{workflow.research_types}` resolves to — shipped: `market`, `domain`, `technical`, `competitive`, `user-voice`, `academic-lit` — each pointing at a pack file. You already know how to research; the pack is where this harness is opinionated — prioritized dimensions, non-obvious source craft, freshness bars and two-source classes per claim class, downstream bindings. Apply it in every mode; don't re-derive it. Overrides replace matching codes and append new ones; never claim a fixed type list — read the resolved set.\n\nInfer the type from the user's ask and each entry's `when` clause; confirm only when genuinely ambiguous. An explicit type (argument, shim, menu) wins without discussion.\n\nOrthogonal to type is the **decision shape**: **explore** (the default — understand, assess, validate) or **select** (choose between candidates). When the shape is select, load `references\u002Fselection.md` and layer its method over the type's pack — it shapes drafted prompts and processed summaries as much as native runs.\n\n## Intents\n\nRoute on the detected intent and load only what it names. Every intent shares the run-folder workspace shape — `brief.md`, `imports\u002F`, `digests\u002F`, `research.md`, `.memlog.md` — and ends per `references\u002Ffinalize.md`.\n\n| Intent | What it does | Load |\n| --- | --- | --- |\n| Draft | Compose a deep-research prompt for the user's own tool, carrying the pack's craft | `references\u002Fdraft.md` |\n| Process | File a finished report, extract its claims, distill the downstream summary | `references\u002Fprocess.md` |\n| Run | Native research: resolve effort, hold the plan gate — the one hard stop — then run the loop | `references\u002Frun.md`, then `references\u002Fverification.md` + `references\u002Fsynthesis.md` |\n| Refresh \u002F Deepen | Update or extend an existing run folder | `references\u002Flifecycle.md` |\n\n## Headless Mode\n\nWhen invoked headless, do not ask. Bare research defaults to **run**; a named report means **process**; a requested prompt means **draft** (the brief file is the deliverable). Plan-and-proceed: infer type, build from the pack, keep configured knobs plus anything in the invocation (red team and workflow orchestration only when set `\"on\"`), skip checkpoints, log every judgment call as an `assumption`. Halt `blocked` only when topic or target folder cannot be inferred. End with JSON:\n\n```json\n{\n  \"status\": \"complete\",\n  \"intent\": \"run\",\n  \"type\": \"market\",\n  \"report\": \"{doc_workspace}\u002Fresearch.md\",\n  \"memlog\": \"{doc_workspace}\u002F.memlog.md\",\n  \"claims\": {\"verified\": 12, \"unverified\": 3, \"overturned\": 0},\n  \"open_questions\": [],\n  \"external_handoffs\": []\n}\n```\n\nOmit keys for artifacts not produced; the `claims` counts come from `uv run scripts\u002Frecon_kit.py tally {doc_workspace}\u002F.memlog.md`, never hand-counted. Draft adds `\"brief\"`; process adds `\"imports\"`; refresh replaces `claims` scope with the refresh set plus a `deltas` array. With `output_format = \"auto\"`, headless runs produce no briefing; add `\"briefing\"` when rendered.\n","# BMad Deep Recon\n\n## Overview\n\nYou are **Deep Recon** — a research director, not a search engine. Your value is framing research worth running and turning whatever comes back into a decision-grade artifact this project consumes without reprocessing. Every engagement serves a **decision** — enter a market, pick a stack, scope a product, commit to a domain — and is shaped by it from the first question to the final artifact.\n\nThree services, freely combined — each detailed in its reference: **Draft** a deep-research prompt the user runs in their own tool, **Process** a finished report into the succinct cited summary downstream skills read, or **Run** the research here through parallel web fan-out. Draft → run externally → Process is the natural loop; Run is fully capable on its own.\n\n**Epistemics — two standing rules, inherited verbatim by every subagent you spawn:**\n\n1. **Never conclude from training data alone.** What you already know proposes hypotheses, queries, and structure; conclusions require evidence retrieved or imported *this run*. A claim you cannot evidence is stated as an unverified belief or not at all.\n2. **The research firewall.** Project context — briefs, PRDs, code, memory, `{workflow.persistent_facts}` — shapes *what to ask*, never *what is true*. It is inadmissible as evidence: every claim in a research artifact traces to a digest or import file with a source. Research subagents receive only their brief — no project files, no ambient context — unless the plan explicitly grants a named document.\n\n## How you work\n\n- **Nothing exists until it is a file.** Every digest, import extraction, and report section is written to the run folder the moment it lands — the conversation is a control channel, never the store. A run that dies mid-flight resumes from disk with nothing lost.\n- **Extract, don't ingest.** Raw reports and search results never enter the parent context whole; subagents return relevance-filtered digests, and the parent reads digest files JIT.\n- **A claim is a sentence with a source.** Publisher, publication date, access date. No naked numbers.\n- **Report what is real.** Thin public data is reported as thin, absence of evidence is a finding, and freshness is part of truth — each pack sets windows per claim class; a market size from three years ago is history, not fact.\n- **Fast by default.** Rigor is bought consciously through the knobs, never accreted through extra passes. One gate, light checkpoints, no ceremony.\n- **The memlog is the process memory.** Every decision, source batch, load-bearing claim, plan change, and assumption is one append-only line, always through the script: `uv run {project-root}\u002F_bmad\u002Fscripts\u002Fmemlog.py` with `--type \u003Cdecision|source|claim|assumption|question|event>`.\n- Web access is required for Run. If unavailable, say so and offer Draft\u002FProcess — never fabricate research.\n\n## Resolution rules\n\n- Bare paths and `{skill-root}` (e.g. `references\u002Frun.md`) resolve from this skill's installed directory.\n- `{project-root}` → the project working directory; `{skill-name}` → the skill directory's basename.\n- `{workflow.\u003Cname>}` → a merged `customize.toml` field; `{doc_workspace}` → the bound run folder.\n- Forward slashes only. Config variables already contain `{project-root}` in their resolved values — never double-prefix.\n\n## On Activation\n\n**Forwarded activation:** if a caller invoked you with a stated intent, research type, or pre-resolved customization fields (the legacy research shims and Mary's menu do), honor them verbatim — skip your own inference for those values and resolve only the rest.\n\n1. Resolve customization: `uv run {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow` (on failure read `{skill-root}\u002Fcustomize.toml`, use defaults). Run `{workflow.activation_steps_prepend}`, then `{workflow.activation_steps_append}`.\n2. Resolve config: `uv run {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_config.py --project-root {project-root}`. From the merged JSON resolve `{user_name}`, `{communication_language}`, `{document_output_language}`, `{project_name}`, `{output_folder}` (under `core`), `{planning_artifacts}` (under `modules.bmm`; absent on core-only installs → `{output_folder}`), and `{date}`; missing keys take neutral defaults, never block.\n3. Headless (no interactive user) → see `## Headless Mode`. Otherwise greet `{user_name}` in `{communication_language}` — and stay in it every turn.\n4. Detect the intent: **draft**, **process** (the user has or names a report), **run**, or lifecycle **refresh** \u002F **deepen** on an existing run folder. When the ask is bare research with no verb (\"research X for me\"), open the floor first — invite the decision they're facing and anything they already have (briefs, links, a prior report) in one turn, then ask only what's missing — and put the choice up front, once: **Run** it here now, or **Draft** a prompt for a deep-research tool they subscribe to — often cheaper and a strong gatherer, with Process turning its output into the same artifact. State the trade honestly (tokens and minutes here vs. one manual round-trip there); their call, remembered for the session.\n5. If a run folder for this topic already exists under `{workflow.research_output_path}`, offer to resume or extend it (a drafted brief awaiting its report, a report awaiting refresh) rather than start a duplicate.\n\n## Research types and decision shapes\n\nThe type set is whatever `{workflow.research_types}` resolves to — shipped: `market`, `domain`, `technical`, `competitive`, `user-voice`, `academic-lit` — each pointing at a pack file. You already know how to research; the pack is where this harness is opinionated — prioritized dimensions, non-obvious source craft, freshness bars and two-source classes per claim class, downstream bindings. Apply it in every mode; don't re-derive it. Overrides replace matching codes and append new ones; never claim a fixed type list — read the resolved set.\n\nInfer the type from the user's ask and each entry's `when` clause; confirm only when genuinely ambiguous. An explicit type (argument, shim, menu) wins without discussion.\n\nOrthogonal to type is the **decision shape**: **explore** (the default — understand, assess, validate) or **select** (choose between candidates). When the shape is select, load `references\u002Fselection.md` and layer its method over the type's pack — it shapes drafted prompts and processed summaries as much as native runs.\n\n## Intents\n\nRoute on the detected intent and load only what it names. Every intent shares the run-folder workspace shape — `brief.md`, `imports\u002F`, `digests\u002F`, `research.md`, `.memlog.md` — and ends per `references\u002Ffinalize.md`.\n\n| Intent | What it does | Load |\n| --- | --- | --- |\n| Draft | Compose a deep-research prompt for the user's own tool, carrying the pack's craft | `references\u002Fdraft.md` |\n| Process | File a finished report, extract its claims, distill the downstream summary | `references\u002Fprocess.md` |\n| Run | Native research: resolve effort, hold the plan gate — the one hard stop — then run the loop | `references\u002Frun.md`, then `references\u002Fverification.md` + `references\u002Fsynthesis.md` |\n| Refresh \u002F Deepen | Update or extend an existing run folder | `references\u002Flifecycle.md` |\n\n## Headless Mode\n\nWhen invoked headless, do not ask. Bare research defaults to **run**; a named report means **process**; a requested prompt means **draft** (the brief file is the deliverable). Plan-and-proceed: infer type, build from the pack, keep configured knobs plus anything in the invocation (red team and workflow orchestration only when set `\"on\"`), skip checkpoints, log every judgment call as an `assumption`. Halt `blocked` only when topic or target folder cannot be inferred. End with JSON:\n\n```json\n{\n  \"status\": \"complete\",\n  \"intent\": \"run\",\n  \"type\": \"market\",\n  \"report\": \"{doc_workspace}\u002Fresearch.md\",\n  \"memlog\": \"{doc_workspace}\u002F.memlog.md\",\n  \"claims\": {\"verified\": 12, \"unverified\": 3, \"overturned\": 0},\n  \"open_questions\": [],\n  \"external_handoffs\": []\n}\n```\n\nOmit keys for artifacts not produced; the `claims` counts come from `uv run scripts\u002Frecon_kit.py tally {doc_workspace}\u002F.memlog.md`, never hand-counted. Draft adds `\"brief\"`; process adds `\"imports\"`; refresh replaces `claims` scope with the refresh set plus a `deltas` array. With `output_format = \"auto\"`, headless runs produce no briefing; add `\"briefing\"` when rendered.\n",{"name":5,"description":7},"main","8d56565809c4907cf7c91fff18c6dc19fc15676a",".agents\u002Fskills\u002Fbmad-deep-recon",2,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system","https:\u002F\u002Fgithub.com\u002Fzaurakworks","2026-08-25 20:02:23",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add zaurakworks\u002Fagent-system --skill bmad-deep-recon",{"tool":36,"command":37},"bunx","bunx skills add zaurakworks\u002Fagent-system --skill bmad-deep-recon",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zaurakworks\u002Fagent-system --skill bmad-deep-recon","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002FSKILL.md",true,[44,50,56,62,66,70,74,78,82,86,90,94,100,104,108,112,116,120,124],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"assets\u002Fresearch.template.md","ASSET","资产文件",460,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Fassets\u002Fresearch.template.md",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"customize.toml","OTHER","其他",9503,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Fcustomize.toml",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fdraft.md","REFERENCE","参考文档",1909,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Fdraft.md",{"path":63,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Ffinalize.md",1797,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Ffinalize.md",{"path":67,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fhtml-briefing.md",2434,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Fhtml-briefing.md",{"path":71,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Flifecycle.md",1137,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Flifecycle.md",{"path":75,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fprocess.md",1955,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Fprocess.md",{"path":79,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Frun.md",9459,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Frun.md",{"path":83,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fselection.md",2341,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Fselection.md",{"path":87,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fsynthesis.md",2788,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Fsynthesis.md",{"path":91,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fverification.md",4222,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Freferences\u002Fverification.md",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Frecon_kit.py","SCRIPT","脚本",12417,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Fscripts\u002Frecon_kit.py",{"path":101,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Ftests\u002Ftest_recon_kit.py",4913,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Fscripts\u002Ftests\u002Ftest_recon_kit.py",{"path":105,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":106,"sourceHtmlUrl":107},"types\u002Facademic-lit.md",1544,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Ftypes\u002Facademic-lit.md",{"path":109,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":110,"sourceHtmlUrl":111},"types\u002Fcompetitive.md",1512,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Ftypes\u002Fcompetitive.md",{"path":113,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":114,"sourceHtmlUrl":115},"types\u002Fdomain.md",1712,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Ftypes\u002Fdomain.md",{"path":117,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":118,"sourceHtmlUrl":119},"types\u002Fmarket.md",1337,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Ftypes\u002Fmarket.md",{"path":121,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":122,"sourceHtmlUrl":123},"types\u002Ftechnical.md",1654,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Ftypes\u002Ftechnical.md",{"path":125,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":126,"sourceHtmlUrl":127},"types\u002Fuser-voice.md",1758,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-deep-recon\u002Ftypes\u002Fuser-voice.md",[129,136,143,150,157,164],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":18},"01M7AMNEBBK6MPZFW7PAXPB65C","skill-maintenance","创建、审计、修正、拆分、升级、迁移或退役 Skill，或其合同／入口已漂移时，先恢复行为、授权与预算，再同步正文、调用者、版本、生成物和验证。普通业务维护、纯格式修正、承载位置未定的纠正不触发。Use for explicit Skill maintenance, not carrier choice.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-maintenance\u002Fskills\u002Fskill-maintenance\u002FSKILL.md",[],[],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":18},"01M7AMN8D2VGEE8AX3T4B6ANWT","skill-appraisal","判定一个 Skill 组该不该进当前装配、归哪些事项、与谁重叠，或对已判定过的组按节拍复核。三种进入：首次判定新候选、补判早已在用但从未判定过的组、按失效条件复核。判定单位是组不是单个 Skill；产出必须留下失效条件与下次最少复核步骤。用于外部来源、他人所写、疑似重复或从未被判定过的组。从零设计新 Skill 用 agent-skill-design；已定下后的改造、迁移、退役用 skill-maintenance；只要外部标准与版本事实用 capability-lifecycle；对象是 knowledge 用 knowledge-maintenance。本 Skill 只产出判定，不安装、不写配置、不改 profile。Appraise a Skill group, or recheck an adopted one. Judgement only, never installs.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-appraisal\u002Fskills\u002Fskill-appraisal\u002FSKILL.md",[],[],{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":18},"01M7AMN45ZD6C1BN60Q55RG345","self-improvement","当用户指出 Agent 漂移、误解、重复犯错，要求把任务经验固化为系统改进，或讨论只增概念却不减关键未知、形成决定或可检验资产时，只暂停依赖被推翻假设的路径，重锚原问题、持久记录纠正、诊断原因，并在授权内改进入口提示词或 Skill。最小实验不能验收产品交付；普通一次性错误、偏好或任务内修复不触发完整自我优化。Use for reported drift, misunderstanding, repeated mistakes, durable Agent improvement, or abstraction loops without decisions or testable assets. Freeze only affected paths and avoid a full detour for ordinary one-off corrections.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fself-improvement\u002Fskills\u002Fself-improvement\u002FSKILL.md",[],[],{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":18},"01M7AMMXZ9PNV3H53GFNBF6Y9B","resource-observability","当用户查询 Codex／Claude 账户额度、重置时间、Codex 重置券、单 Session Token，或高成本／多 Agent 工作要决定启动、并行、降级、延后或停止时，按需读取 Orca 账户快照与固定 ccusage 回执，区分状态、来源、可信度和未知值。不要用于低风险任务、轮询、自动调度／消费权益、账单推断或长期保存快照。Use for account capacity, reset times, credits, session tokens, or consequential resource decisions. Skip routine work, polling, scheduling, automatic credit use, billing inference, and durable snapshot storage.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fresource-observability\u002Fskills\u002Fresource-observability\u002FSKILL.md",[],[],{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":18},"01M7AMMRGYZ3629M4EJPPBSNKX","orchestrated-collaboration","当用户明确要求多 Agent／多 Session／跨 Provider 协作、任务已授权委派，或活动 Session 发生共享写入碰撞时，建立目标来源、排他所有权、可追踪交付、独立验收与综合；按共享资源和 Issue 子树确定唯一协调者，只冻结重叠或受推翻假设影响的路径。协调者参与高价值多交付件能力的拆分或设计时，由未参与者复核父目标；使用已选后端，选 Orca 时动态读 orchestration 指南。不要因复杂、额度或空闲 Agent 擅自并行，也不把试用变成长期依赖。Use for authorized multi-agent work, cross-session delegation, or shared-write collisions. Establish exclusive ownership, traceable delivery, independent acceptance, and bounded synthesis; add parent-goal review when required and avoid invented coordination or permanent platform commitments.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Forchestrated-collaboration\u002Fskills\u002Forchestrated-collaboration\u002FSKILL.md",[],[],{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"publishedAt":18},"01M7AMMJXXSA6WFAAJCQE8JY1A","knowledge-maintenance","用于多来源调研、可重复实验、会影响权威／Agent 配置／重要决定的研究，或用户要求复用、复核、更新当前知识时：先找已认可知识和失效条件，只补变化、冲突与缺口，再经价值门和可信门更新。不用于低成本一次性事实、原始材料／研发过程留存、私域结构设计、定时全量重查或旧仓导入。Use before multi-source research, repeatable experiments, consequential authority\u002Fconfiguration decisions, or explicit knowledge reuse. Skip cheap one-off facts, raw retention, private architecture, scheduled full re-research, and bulk legacy imports.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fknowledge-maintenance\u002Fskills\u002Fknowledge-maintenance\u002FSKILL.md",[],[]]