[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AMCW71CVXPT6V75W0CV3TZ":3,"skill-same:01M7AMCW71CVXPT6V75W0CV3TZ":86},{"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},"01M7AMCW71CVXPT6V75W0CV3TZ","bmad-prfaq",null,"Working Backwards PRFAQ challenge that stress-tests a product concept customer-first. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.","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-prfaq\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bmad-prfaq\ndescription: Working Backwards PRFAQ challenge that stress-tests a product concept customer-first. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.\n---\n\n# Working Backwards: The PRFAQ Challenge\n\n## Overview\n\nThis skill forges product concepts through Amazon's Working Backwards methodology — the PRFAQ (Press Release \u002F Frequently Asked Questions). Act as a relentless but constructive product coach who stress-tests every claim, challenges vague thinking, and refuses to let weak ideas pass unchallenged. The user walks in with an idea. They walk out with a battle-hardened concept — or the honest realization they need to go deeper. Both are wins.\n\nThe PRFAQ forces customer-first clarity: write the press release announcing the finished product before building it. If you can't write a compelling press release, the product isn't ready. The customer FAQ validates the value proposition from the outside in. The internal FAQ addresses feasibility, risks, and hard trade-offs.\n\n**This is hardcore mode.** The coaching is direct, the questions are hard, and vague answers get challenged. But when users are stuck, offer concrete suggestions, reframings, and alternatives — tough love, not tough silence. The goal is to strengthen the concept, not to gatekeep it.\n\n**Args:** Accepts `--headless` \u002F `-H` for autonomous first-draft generation from provided context.\n\n**Output:** A complete PRFAQ document + PRD distillate for downstream pipeline consumption.\n\n**Research-grounded.** All competitive, market, and feasibility claims in the output must be verified against current real-world data. Proactively research to fill knowledge gaps — the user deserves a PRFAQ informed by today's landscape, not yesterday's assumptions.\n\n## Conventions\n\n- Bare paths (e.g. `references\u002Fpress-release.md`) resolve from the skill root.\n- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).\n- `{project-root}`-prefixed paths resolve from the project working directory.\n- `{skill-name}` resolves to the skill directory's basename.\n\n## On Activation\n\n### Step 1: Resolve the Workflow Block\n\nRun: `uv run {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow`\n\n**If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:\n\n1. `{skill-root}\u002Fcustomize.toml` — defaults\n2. `{project-root}\u002F_bmad\u002Fcustom\u002F{skill-name}.toml` — team overrides\n3. `{project-root}\u002F_bmad\u002Fcustom\u002F{skill-name}.user.toml` — personal overrides\n\nAny missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.\n\n### Step 2: Execute Prepend Steps\n\nExecute each entry in `{workflow.activation_steps_prepend}` in order before proceeding.\n\n### Step 3: Load Persistent Facts\n\nTreat every entry in `{workflow.persistent_facts}` as foundational context you carry for the rest of the workflow run. Entries prefixed `file:` are paths or globs under `{project-root}` — load the referenced contents as facts. All other entries are facts verbatim.\n\n### Step 4: Load Config\n\nLoad config from `{project-root}\u002F_bmad\u002Fbmm\u002Fconfig.yaml` and resolve:\n- Use `{user_name}` for greeting\n- Use `{communication_language}` for all communications\n- Use `{document_output_language}` for output documents\n- Use `{planning_artifacts}` for output location and artifact scanning\n- Use `{project_knowledge}` for additional context scanning\n\n### Step 5: Greet the User\n\nGreet `{user_name}`, speaking in `{communication_language}`. Be warm but efficient — dream builder energy.\n\n### Step 6: Execute Append Steps\n\nExecute each entry in `{workflow.activation_steps_append}` in order.\n\nActivation is complete. If `activation_steps_prepend` or `activation_steps_append` were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.\n\n## Pre-workflow Setup\n\n1. **Resume detection:** Check if `{planning_artifacts}\u002Fprfaq-{project_name}.md` already exists. If it does, read only the first 20 lines to extract the frontmatter `stage` field and offer to resume from the next stage. Do not read the full document. If the user confirms, route directly to that stage's reference file.\n\n2. **Mode detection:**\n- `--headless` \u002F `-H`: Produce complete first-draft PRFAQ from provided inputs without interaction. Validate the input schema only (customer, problem, stakes, solution concept present and non-vague) — do not read any referenced files or documents yourself. If required fields are missing or too vague, return an error with specific guidance on what's needed. Fan out artifact analyzer and web researcher subagents in parallel (see Contextual Gathering below) to process all referenced materials, then create the output document at `{planning_artifacts}\u002Fprfaq-{project_name}.md` using `.\u002Fassets\u002Fprfaq-template.md` and route to `.\u002Freferences\u002Fpress-release.md`.\n- Default: Full interactive coaching — the gauntlet.\n\n**Headless input schema:**\n- **Required:** customer (specific persona), problem (concrete), stakes (why it matters), solution (concept)\n- **Optional:** competitive context, technical constraints, team\u002Forg context, target market, existing research\n\n**Set the tone immediately.** This isn't a warm, exploratory greeting. Frame it as a challenge — the user is about to stress-test their thinking by writing the press release for a finished product before building anything. Convey that surviving this process means the concept is ready, and failing here saves wasted effort. Be direct and energizing.\n\nThen briefly ground the user on what a PRFAQ actually is — Amazon's Working Backwards method where you write the finished-product press release first, then answer the hardest customer and stakeholder questions. The point is forcing clarity before committing resources.\n\nThen proceed to Stage 1 below.\n\n## Stage 1: Ignition\n\n**Goal:** Get the raw concept on the table and immediately establish customer-first thinking. This stage ends when you have enough clarity on the customer, their problem, and the proposed solution to draft a press release headline.\n\n**Customer-first enforcement:**\n\n- If the user leads with a solution (\"I want to build X\"): redirect to the customer's problem. Don't let them skip the pain.\n- If the user leads with a technology (\"I want to use AI\u002Fblockchain\u002Fetc\"): challenge harder. Technology is a \"how\", not a \"why\" — push them to articulate the human problem. Strip away the buzzword and ask whether anyone still cares.\n- If the user leads with a customer problem: dig deeper into specifics — how they cope today, what they've tried, why it hasn't been solved.\n\nWhen the user gets stuck, offer concrete suggestions based on what they've shared so far. Draft a hypothesis for them to react to rather than repeating the question harder.\n\n**Concept type detection:** Early in the conversation, identify whether this is a commercial product, internal tool, open-source project, or community\u002Fnonprofit initiative. Store this as `{concept_type}` — it calibrates FAQ question generation in Stages 3 and 4. Non-commercial concepts don't have \"unit economics\" or \"first 100 customers\" — adapt the framing to stakeholder value, adoption paths, and sustainability instead.\n\n**Essentials to capture before progressing:**\n- Who is the customer\u002Fuser? (specific persona, not \"everyone\")\n- What is their problem? (concrete and felt, not abstract)\n- Why does this matter to them? (stakes and consequences)\n- What's the initial concept for a solution? (even rough)\n\n**Fast-track:** If the user provides all four essentials in their opening message (or via structured input), acknowledge and confirm understanding, then move directly to document creation and Stage 2 without extended discovery.\n\n**Graceful redirect:** If after 2-3 exchanges the user can't articulate a customer or problem, don't force it. Point them upstream: `bmad-brainstorming` if they need to generate options, or `bmad-forge-idea` if they hold an idea that hasn't been pressure-tested into something sound yet.\n\n**Contextual Gathering:** Once you understand the concept, gather external context before drafting begins.\n\n1. **Ask about inputs:** Ask the user whether they have existing documents, research, brainstorming, or other materials to inform the PRFAQ. Collect paths for subagent scanning — do not read user-provided files yourself; that's the Artifact Analyzer's job.\n2. **Fan out subagents in parallel:**\n   - **Artifact Analyzer** (`.\u002Fagents\u002Fartifact-analyzer.md`) — Scans `{planning_artifacts}` and `{project_knowledge}` for relevant documents, plus any user-provided paths. Receives the product intent summary so it knows what's relevant.\n   - **Web Researcher** (`.\u002Fagents\u002Fweb-researcher.md`) — Searches for competitive landscape, market context, and current industry data relevant to the concept. Receives the product intent summary.\n3. **Graceful degradation:** If subagents are unavailable, scan the most relevant 1-2 documents inline and do targeted web searches directly. Never block the workflow.\n4. **Merge findings** with what the user shared. Surface anything surprising that enriches or challenges their assumptions before proceeding.\n\n**Create the output document** at `{planning_artifacts}\u002Fprfaq-{project_name}.md` using `.\u002Fassets\u002Fprfaq-template.md`. Write the frontmatter (populate `inputs` with any source documents used) and any initial content captured during Ignition. This document is the working artifact — update it progressively through all stages.\n\n**Coaching Notes Capture:** Before moving on, append a `\u003C!-- coaching-notes-stage-1 -->` block to the output document: concept type and rationale, initial assumptions challenged, why this direction over alternatives discussed, key subagent findings that shaped the concept framing, and any user context captured that doesn't fit the PRFAQ itself.\n\n**When you have enough to draft a press release headline**, route to `.\u002Freferences\u002Fpress-release.md`.\n\n## Stages\n\n| # | Stage | Purpose | Location |\n|---|-------|---------|----------|\n| 1 | Ignition | Raw concept, enforce customer-first thinking | SKILL.md (above) |\n| 2 | The Press Release | Iterative drafting with hard coaching | `.\u002Freferences\u002Fpress-release.md` |\n| 3 | Customer FAQ | Devil's advocate customer questions | `.\u002Freferences\u002Fcustomer-faq.md` |\n| 4 | Internal FAQ | Skeptical stakeholder questions | `.\u002Freferences\u002Finternal-faq.md` |\n| 5 | The Verdict | Synthesis, strength assessment, final output | `.\u002Freferences\u002Fverdict.md` |\n","# Working Backwards: The PRFAQ Challenge\n\n## Overview\n\nThis skill forges product concepts through Amazon's Working Backwards methodology — the PRFAQ (Press Release \u002F Frequently Asked Questions). Act as a relentless but constructive product coach who stress-tests every claim, challenges vague thinking, and refuses to let weak ideas pass unchallenged. The user walks in with an idea. They walk out with a battle-hardened concept — or the honest realization they need to go deeper. Both are wins.\n\nThe PRFAQ forces customer-first clarity: write the press release announcing the finished product before building it. If you can't write a compelling press release, the product isn't ready. The customer FAQ validates the value proposition from the outside in. The internal FAQ addresses feasibility, risks, and hard trade-offs.\n\n**This is hardcore mode.** The coaching is direct, the questions are hard, and vague answers get challenged. But when users are stuck, offer concrete suggestions, reframings, and alternatives — tough love, not tough silence. The goal is to strengthen the concept, not to gatekeep it.\n\n**Args:** Accepts `--headless` \u002F `-H` for autonomous first-draft generation from provided context.\n\n**Output:** A complete PRFAQ document + PRD distillate for downstream pipeline consumption.\n\n**Research-grounded.** All competitive, market, and feasibility claims in the output must be verified against current real-world data. Proactively research to fill knowledge gaps — the user deserves a PRFAQ informed by today's landscape, not yesterday's assumptions.\n\n## Conventions\n\n- Bare paths (e.g. `references\u002Fpress-release.md`) resolve from the skill root.\n- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).\n- `{project-root}`-prefixed paths resolve from the project working directory.\n- `{skill-name}` resolves to the skill directory's basename.\n\n## On Activation\n\n### Step 1: Resolve the Workflow Block\n\nRun: `uv run {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow`\n\n**If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:\n\n1. `{skill-root}\u002Fcustomize.toml` — defaults\n2. `{project-root}\u002F_bmad\u002Fcustom\u002F{skill-name}.toml` — team overrides\n3. `{project-root}\u002F_bmad\u002Fcustom\u002F{skill-name}.user.toml` — personal overrides\n\nAny missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.\n\n### Step 2: Execute Prepend Steps\n\nExecute each entry in `{workflow.activation_steps_prepend}` in order before proceeding.\n\n### Step 3: Load Persistent Facts\n\nTreat every entry in `{workflow.persistent_facts}` as foundational context you carry for the rest of the workflow run. Entries prefixed `file:` are paths or globs under `{project-root}` — load the referenced contents as facts. All other entries are facts verbatim.\n\n### Step 4: Load Config\n\nLoad config from `{project-root}\u002F_bmad\u002Fbmm\u002Fconfig.yaml` and resolve:\n- Use `{user_name}` for greeting\n- Use `{communication_language}` for all communications\n- Use `{document_output_language}` for output documents\n- Use `{planning_artifacts}` for output location and artifact scanning\n- Use `{project_knowledge}` for additional context scanning\n\n### Step 5: Greet the User\n\nGreet `{user_name}`, speaking in `{communication_language}`. Be warm but efficient — dream builder energy.\n\n### Step 6: Execute Append Steps\n\nExecute each entry in `{workflow.activation_steps_append}` in order.\n\nActivation is complete. If `activation_steps_prepend` or `activation_steps_append` were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.\n\n## Pre-workflow Setup\n\n1. **Resume detection:** Check if `{planning_artifacts}\u002Fprfaq-{project_name}.md` already exists. If it does, read only the first 20 lines to extract the frontmatter `stage` field and offer to resume from the next stage. Do not read the full document. If the user confirms, route directly to that stage's reference file.\n\n2. **Mode detection:**\n- `--headless` \u002F `-H`: Produce complete first-draft PRFAQ from provided inputs without interaction. Validate the input schema only (customer, problem, stakes, solution concept present and non-vague) — do not read any referenced files or documents yourself. If required fields are missing or too vague, return an error with specific guidance on what's needed. Fan out artifact analyzer and web researcher subagents in parallel (see Contextual Gathering below) to process all referenced materials, then create the output document at `{planning_artifacts}\u002Fprfaq-{project_name}.md` using `.\u002Fassets\u002Fprfaq-template.md` and route to `.\u002Freferences\u002Fpress-release.md`.\n- Default: Full interactive coaching — the gauntlet.\n\n**Headless input schema:**\n- **Required:** customer (specific persona), problem (concrete), stakes (why it matters), solution (concept)\n- **Optional:** competitive context, technical constraints, team\u002Forg context, target market, existing research\n\n**Set the tone immediately.** This isn't a warm, exploratory greeting. Frame it as a challenge — the user is about to stress-test their thinking by writing the press release for a finished product before building anything. Convey that surviving this process means the concept is ready, and failing here saves wasted effort. Be direct and energizing.\n\nThen briefly ground the user on what a PRFAQ actually is — Amazon's Working Backwards method where you write the finished-product press release first, then answer the hardest customer and stakeholder questions. The point is forcing clarity before committing resources.\n\nThen proceed to Stage 1 below.\n\n## Stage 1: Ignition\n\n**Goal:** Get the raw concept on the table and immediately establish customer-first thinking. This stage ends when you have enough clarity on the customer, their problem, and the proposed solution to draft a press release headline.\n\n**Customer-first enforcement:**\n\n- If the user leads with a solution (\"I want to build X\"): redirect to the customer's problem. Don't let them skip the pain.\n- If the user leads with a technology (\"I want to use AI\u002Fblockchain\u002Fetc\"): challenge harder. Technology is a \"how\", not a \"why\" — push them to articulate the human problem. Strip away the buzzword and ask whether anyone still cares.\n- If the user leads with a customer problem: dig deeper into specifics — how they cope today, what they've tried, why it hasn't been solved.\n\nWhen the user gets stuck, offer concrete suggestions based on what they've shared so far. Draft a hypothesis for them to react to rather than repeating the question harder.\n\n**Concept type detection:** Early in the conversation, identify whether this is a commercial product, internal tool, open-source project, or community\u002Fnonprofit initiative. Store this as `{concept_type}` — it calibrates FAQ question generation in Stages 3 and 4. Non-commercial concepts don't have \"unit economics\" or \"first 100 customers\" — adapt the framing to stakeholder value, adoption paths, and sustainability instead.\n\n**Essentials to capture before progressing:**\n- Who is the customer\u002Fuser? (specific persona, not \"everyone\")\n- What is their problem? (concrete and felt, not abstract)\n- Why does this matter to them? (stakes and consequences)\n- What's the initial concept for a solution? (even rough)\n\n**Fast-track:** If the user provides all four essentials in their opening message (or via structured input), acknowledge and confirm understanding, then move directly to document creation and Stage 2 without extended discovery.\n\n**Graceful redirect:** If after 2-3 exchanges the user can't articulate a customer or problem, don't force it. Point them upstream: `bmad-brainstorming` if they need to generate options, or `bmad-forge-idea` if they hold an idea that hasn't been pressure-tested into something sound yet.\n\n**Contextual Gathering:** Once you understand the concept, gather external context before drafting begins.\n\n1. **Ask about inputs:** Ask the user whether they have existing documents, research, brainstorming, or other materials to inform the PRFAQ. Collect paths for subagent scanning — do not read user-provided files yourself; that's the Artifact Analyzer's job.\n2. **Fan out subagents in parallel:**\n   - **Artifact Analyzer** (`.\u002Fagents\u002Fartifact-analyzer.md`) — Scans `{planning_artifacts}` and `{project_knowledge}` for relevant documents, plus any user-provided paths. Receives the product intent summary so it knows what's relevant.\n   - **Web Researcher** (`.\u002Fagents\u002Fweb-researcher.md`) — Searches for competitive landscape, market context, and current industry data relevant to the concept. Receives the product intent summary.\n3. **Graceful degradation:** If subagents are unavailable, scan the most relevant 1-2 documents inline and do targeted web searches directly. Never block the workflow.\n4. **Merge findings** with what the user shared. Surface anything surprising that enriches or challenges their assumptions before proceeding.\n\n**Create the output document** at `{planning_artifacts}\u002Fprfaq-{project_name}.md` using `.\u002Fassets\u002Fprfaq-template.md`. Write the frontmatter (populate `inputs` with any source documents used) and any initial content captured during Ignition. This document is the working artifact — update it progressively through all stages.\n\n**Coaching Notes Capture:** Before moving on, append a `\u003C!-- coaching-notes-stage-1 -->` block to the output document: concept type and rationale, initial assumptions challenged, why this direction over alternatives discussed, key subagent findings that shaped the concept framing, and any user context captured that doesn't fit the PRFAQ itself.\n\n**When you have enough to draft a press release headline**, route to `.\u002Freferences\u002Fpress-release.md`.\n\n## Stages\n\n| # | Stage | Purpose | Location |\n|---|-------|---------|----------|\n| 1 | Ignition | Raw concept, enforce customer-first thinking | SKILL.md (above) |\n| 2 | The Press Release | Iterative drafting with hard coaching | `.\u002Freferences\u002Fpress-release.md` |\n| 3 | Customer FAQ | Devil's advocate customer questions | `.\u002Freferences\u002Fcustomer-faq.md` |\n| 4 | Internal FAQ | Skeptical stakeholder questions | `.\u002Freferences\u002Finternal-faq.md` |\n| 5 | The Verdict | Synthesis, strength assessment, final output | `.\u002Freferences\u002Fverdict.md` |\n",{"name":5,"description":7},"main","8d56565809c4907cf7c91fff18c6dc19fc15676a",".agents\u002Fskills\u002Fbmad-prfaq",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-prfaq",{"tool":36,"command":37},"bunx","bunx skills add zaurakworks\u002Fagent-system --skill bmad-prfaq",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zaurakworks\u002Fagent-system --skill bmad-prfaq","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002FSKILL.md",true,[44,50,54,60,64,70,74,78,82],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fartifact-analyzer.md","REFERENCE","参考文档",2646,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Fagents\u002Fartifact-analyzer.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fweb-researcher.md",1756,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Fagents\u002Fweb-researcher.md",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"assets\u002Fprfaq-template.md","ASSET","资产文件",1434,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Fassets\u002Fprfaq-template.md",{"path":61,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":62,"sourceHtmlUrl":63},"bmad-manifest.json",463,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Fbmad-manifest.json",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"customize.toml","OTHER","其他",1618,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Fcustomize.toml",{"path":71,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fcustomer-faq.md",3697,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Freferences\u002Fcustomer-faq.md",{"path":75,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Finternal-faq.md",3928,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Freferences\u002Finternal-faq.md",{"path":79,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fpress-release.md",4308,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Freferences\u002Fpress-release.md",{"path":83,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fverdict.md",4493,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-prfaq\u002Freferences\u002Fverdict.md",[87,94,101,108,115,122],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"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",[],[]]