[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79VB93T67JTVFPCZWS3DX44":3,"skill-same:01M79VB93T67JTVFPCZWS3DX44":77},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M79VB93T67JTVFPCZWS3DX44","inbox-setup",null,"One-time setup skill that builds a personalized inbox triage knowledge base via interactive interview. Interviews the user about their email patterns, business context, reply style, and priorities using grill-me discipline (one question at a time, forcing format where possible, dependency-ordered, each question explains why I'm asking), then generates the knowledge base files that power the companion 'inbox-triage' skill. Run this once before using inbox-triage for the first time. Re-run when business, pricing, or priorities change significantly. Triggers: 'set up my inbox', 'configure inbox triage', 'set up my email system', 'configure email triage', 'build my email knowledge base', 'initialize email management', 'set up inbox triage', 'onboard email triage', or any variation where someone wants to get the email triage system running for the first time.","Heverton-web\u002Fskill-manager","Heverton-web","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F136394064?v=4","01M79STQDWSTA88J5CA9QR184V","Heverton Eduardo Peres","01M79SX01KSKBZ828C257RAC8P",0,"MIT","https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inbox-setup\ndescription: \"One-time setup skill that builds a personalized inbox triage knowledge base via interactive interview. Interviews the user about their email patterns, business context, reply style, and priorities using grill-me discipline (one question at a time, forcing format where possible, dependency-ordered, each question explains why I'm asking), then generates the knowledge base files that power the companion 'inbox-triage' skill. Run this once before using inbox-triage for the first time. Re-run when business, pricing, or priorities change significantly. Triggers: 'set up my inbox', 'configure inbox triage', 'set up my email system', 'configure email triage', 'build my email knowledge base', 'initialize email management', 'set up inbox triage', 'onboard email triage', or any variation where someone wants to get the email triage system running for the first time.\"\nlicense: MIT\nmetadata:\n  source_spec: \"megaprompts\u002F06-inbox-setup-megaprompt.md\"\n  build_pattern: \"Path B (direct conversion)\"\n  paired_with: \"inbox-triage (shared 7-file KB contract)\"\n  version: 1.0.0\n---\n\n# Inbox-Setup — Email Triage Onboarding\n\n> **Paired with `inbox-triage`.** This skill writes the 7-file knowledge base at `${WORKSPACE}\u002FEmail\u002F` that `inbox-triage` reads on every run. The file contracts (names, sections, fields) MUST match between the two skills exactly. See [`references\u002Fkb_file_contract.md`](references\u002Fkb_file_contract.md).\n\nRun once (or re-run when business\u002Fpriorities change). Interview the user about their email patterns, business context, reply style, and priorities. Generate the structured knowledge base in `${WORKSPACE}\u002FEmail\u002F` that captures everything `inbox-triage` needs to process the inbox effectively.\n\n## Invocation Triggers\n\n- \"set up my inbox\"\n- \"configure inbox triage\"\n- \"set up my email system\"\n- \"configure email triage\"\n- \"build my email knowledge base\"\n- \"initialize email management\"\n- \"set up inbox triage\"\n- \"onboard email triage\"\n\n## Conduct Discipline\n\n**Do NOT generate all files at once.** Walk through the 8 sections one at a time. Each section commits its file(s) before moving on. Partial completion (e.g., user drops off mid-interview) still produces a usable partial KB.\n\nGrill-me discipline applies throughout:\n\n- **One question per turn.** Never bundle. Even across section boundaries.\n- **\"Why I'm asking\" on every question** — so users can answer well.\n- **Forcing format where possible.** Multi-choice > open-ended.\n- **Dependency-ordered.** Q2 depends on Q1; downstream sections depend on upstream.\n\nSee [`references\u002Fgrill_me_section_walk.md`](references\u002Fgrill_me_section_walk.md) for the 8-section discipline detail.\n\n## Knowledge Base Contract — Files To Produce\n\nExactly these files at `${WORKSPACE}\u002FEmail\u002F`:\n\n| File | Purpose | Required? |\n|---|---|---|\n| `email-taxonomy.md` | Classification system + report preferences | **Yes** |\n| `email-patterns.md` | Reply voice, tone, templates, hard rules | **Yes** |\n| `evaluation-framework.md` | Decision tree for opportunity emails | Only if user receives pitches\u002Fopportunities |\n| `rate-card.md` | Pricing, terms, negotiation posture | Only if user has pricing |\n| `blocklist.md` | Auto-skip senders + learned decline patterns | **Yes** (seeded, grows over time) |\n| `tracker.md` | Active follow-ups, overdue items, deadlines | **Yes** (starts mostly empty) |\n| `triage-log\u002F` | Directory for per-run logs | **Yes** (created empty) |\n\nThe contract is identical to what `inbox-triage` expects — see [`references\u002Fkb_file_contract.md`](references\u002Fkb_file_contract.md) for the full spec.\n\n## Stop Condition (Full Interview)\n\n~25–31 questions total across the 8 sections (depending on skip-logic). Hard ceiling: 35 questions including all sub-clarifications. Section 4 (Evaluation Framework) is skipped entirely when Section 1 surfaced no opportunity-email category, dropping the total by 6 questions and the rate-card file. After Section 8's confirmation + handoff message, intake is closed — **never re-open it**. To change preferences later, the user re-runs the skill (which detects existing files and asks per-file: replace \u002F merge \u002F skip). The grill-me one-at-a-time rule applies across section boundaries: do NOT batch questions even when moving from S{n} to S{n+1}.\n\n## Section 1: The Big Picture\n\nSix grill-me questions, one at a time:\n\n- **S1.Q1:** \"What do you do? Give me your role and business in 1–2 sentences. *Why I'm asking:* Context shapes what email patterns to expect — a solo creator's inbox looks nothing like an enterprise PM's.\"\n- **S1.Q2:** \"What dominates your inbox? Pick the top 1–2: sales pitches \u002F client work \u002F internal team \u002F newsletters \u002F customer support \u002F financial \u002F other. *Why I'm asking:* Dominant categories drive the taxonomy.\"\n- **S1.Q3:** \"Rough volume split — e.g., '60% business inquiries, 20% ops, 20% noise'. *Why I'm asking:* The split tells me where to focus triage effort.\"\n- **S1.Q4:** \"Which email address(es) should triage cover? *Why I'm asking:* If multiple, I'll set up per-address taxonomies.\"\n- **S1.Q5:** \"Run frequency: once daily \u002F 2x daily \u002F 3x daily \u002F on-demand only? *Why I'm asking:* Drives the default search window in triage (9h overlap for 2x\u002Fday).\"\n- **S1.Q6:** \"Anyone helping manage email — assistant, VA, team — or solo? *Why I'm asking:* Persona handling differs for delegated inboxes.\"\n\n**Action:** Build mental model. Do NOT write files yet. Note whether opportunity emails are a category (drives S4 skip-logic).\n\n## Section 2: Email Categories\n\nPropose 5–7 categories based on Section 1 — pre-recommend a subset, not the whole template menu:\n\n- New Opportunities\n- Active Conversations\n- Action Required\n- Financial\n- Important\u002FPersonal\n- Informational\n- Ignore\u002FLow Priority\n\nThen three forcing questions, one at a time:\n\n- **S2.Q1:** \"Here's my proposed taxonomy: [list]. Does this match your inbox reality — yes \u002F mostly \u002F no? *Why I'm asking:* If 'no', I need to redo the taxonomy before any other section makes sense.\"\n- **S2.Q2:** \"Missing categories? List them. (Skip if none.) *Why I'm asking:* Missing categories produce uncategorized emails downstream, which hurts triage quality.\"\n- **S2.Q3:** \"Which category takes the MOST time per email? *Why I'm asking:* That's where draft-reply effort needs to focus most.\"\n\n**Action:** Generate `email-taxonomy.md` with categories, signals (for each: trigger phrases \u002F sender patterns \u002F subject markers), and default actions per category.\n\n## Section 3: Reply Style & Voice\n\nSix grill-me questions plus the critical sample request:\n\n- **S3.Q1:** \"Register: formal \u002F casual \u002F in-between? *Why I'm asking:* Calibrates default voice; we'll refine from samples next.\"\n- **S3.Q2:** \"Three communication pet peeves — phrases you hate, openings you avoid. *Why I'm asking:* I treat these as forbidden tokens in drafts.\"\n- **S3.Q3:** \"Phrases or sign-offs you always use — list as many as come to mind. *Why I'm asking:* These are your voice fingerprints.\"\n- **S3.Q4:** \"Different persona for different contexts — e.g., assistant replies as you? *Why I'm asking:* Persona context changes pronoun + signature handling.\"\n- **S3.Q5:** \"Typical reply length — one-liner \u002F short paragraph \u002F longer? *Why I'm asking:* Length is the easiest voice signal to get wrong.\"\n- **S3.Q6:** \"Hard rules — never X \u002F always Y? (E.g., never emojis, always reply within 24h, never take calls without context.) *Why I'm asking:* Hard rules are enforced as non-negotiable in every draft.\"\n\n### S3.SAMPLES (the critical highest-quality input)\n\n> **Paste 3–5 real sent emails from your inbox.**\n>\n> *Why I'm asking:* Self-description of voice is unreliable. Real samples are the best signal — I'll analyze them for voice patterns that supplement everything above. Use `scripts\u002Fvoice_sample_analyzer.py` to extract patterns deterministically.\n\nIf user runs a business: also ask about media kits, rate sheets, standard pitches, repeated replies.\n\n**Action:** Generate `email-patterns.md` with tone description (with do\u002Fdon't examples), persona rules, templates, signatures, hard rules. See [`references\u002Fvoice_calibration.md`](references\u002Fvoice_calibration.md) for the sample-extraction discipline.\n\n## Section 4: Evaluation Framework (Conditional)\n\n**Skip-logic:** only run this section if Section 1 surfaced opportunity emails as a meaningful inbox category. Otherwise jump straight to Section 5.\n\nSix grill-me questions, one at a time:\n\n- **S4.Q1:** \"First thing you check when pitched something — give me your gut filter. *Why I'm asking:* That's the top of the decision tree.\"\n- **S4.Q2:** \"Three instant deal-breakers — things that make you decline immediately. *Why I'm asking:* These become PASS-auto signals.\"\n- **S4.Q3:** \"Three things that make you immediately interested. *Why I'm asking:* These become TAKE-IT signals.\"\n- **S4.Q4:** \"Standard pricing \u002F terms — or 'no fixed pricing' if you negotiate every time. *Why I'm asking:* If you have a rate card, I'll generate one; if not, I'll skip.\"\n- **S4.Q5:** \"Negotiation posture: firm \u002F flexible \u002F depends on context? *Why I'm asking:* Drives draft tone on counter-offers.\"\n- **S4.Q6:** \"VIP senders or organizations that always get engagement — list names or domains. *Why I'm asking:* VIP list bypasses normal PASS filters.\"\n\n**Action:** Generate `evaluation-framework.md` (decision tree + recommendation categories + VIP list) AND `rate-card.md` if pricing exists.\n\n## Section 5: Blocklist & Patterns\n\nThree grill-me questions, one at a time:\n\n- **S5.Q1:** \"Senders or domains to always skip — list them. (Skip if none.) *Why I'm asking:* Auto-blocklist saves the most time per run.\"\n- **S5.Q2:** \"Patterns in emails you always delete — e.g., 'unsubscribe' links from specific marketers, recruiter cold outreach, newsletters? *Why I'm asking:* Patterns let triage auto-skip variants without exact-match maintenance.\"\n- **S5.Q3:** \"Specific companies \u002F recruiters \u002F newsletters wasting time — list any. *Why I'm asking:* These seed the blocklist; triage will add more as you override decisions.\"\n\n**Action:** Generate `blocklist.md` (auto-maintained by triage thereafter).\n\n## Section 6: Current State\n\nThree grill-me questions, one at a time:\n\n- **S6.Q1:** \"Active threads you're tracking — list with one-line context each. (Skip if none.) *Why I'm asking:* These become tracker entries so triage knows existing context.\"\n- **S6.Q2:** \"Overdue replies — anything you should have responded to but haven't? *Why I'm asking:* Triage flags these as priority every run until resolved.\"\n- **S6.Q3:** \"Time-sensitive items with deadlines — list with dates. *Why I'm asking:* Tracker enforces deadlines and surfaces them as overdue at the right time.\"\n\n**Action:** Generate `tracker.md` with active follow-ups table, overdue section, resolved section (empty), update log (empty). Also create empty `triage-log\u002F` directory.\n\n## Section 7: Report Preferences\n\nThree grill-me questions, one at a time:\n\n- **S7.Q1:** \"Delivery format — pick one: email draft to self \u002F file in workspace \u002F chat summary only. *Why I'm asking:* The triage report goes here every run.\"\n- **S7.Q2:** \"Detail level — pick one: 30-second scan \u002F detailed breakdown \u002F both (scan first, expand on request). *Why I'm asking:* Affects report length.\"\n- **S7.Q3:** \"Anything always shown first — e.g., overdue payments, VIP messages? *Why I'm asking:* Custom 'top-of-report' rules surface what you care about above standard sections.\"\n\n**Action:** Save these preferences into `email-taxonomy.md` under a \"Report Preferences\" section.\n\n## Section 8: Confirmation & Handoff\n\nList every file created with one-sentence summary. Then:\n\n> Your triage system is ready. Run the **inbox-triage** skill to process your inbox. First runs need oversight — system learns from your edits and overrides.\n\nRemind: re-run this setup anytime business\u002Fpricing\u002Fpriorities change.\n\nRun `scripts\u002Fkb_validator.py --workspace ${WORKSPACE}` to confirm the 7-file contract is satisfied before final handoff.\n\n## Privacy Boundary\n\n**Never persist passwords, full account numbers, SSNs, or other sensitive credentials in knowledge base files.** If the user volunteers such info during the interview, acknowledge it but don't store it; the relevant KB file gets `[stored separately by user]` in its place.\n\n## Re-Run Behavior\n\nRe-running on an existing setup:\n\n1. Detect `${WORKSPACE}\u002FEmail\u002F`\n2. For each existing file, ask per-file: **replace \u002F merge \u002F skip**\n3. Walk only the sections whose files the user chose to update\n4. Skip sections whose files the user kept\n\n## Error Handling\n\n| Situation | Behavior |\n|---|---|\n| Workspace inaccessible | Stop. Tell user where files would go and ask for permission\u002Fpath |\n| User refuses to share samples | Use self-description; flag in patterns file that calibration may need iteration |\n| User says \"skip this\" mid-interview | Honor it; flag the gap in the file as `[needs follow-up]` |\n| Sensitive info volunteered | Acknowledge but don't persist; note in file as `[stored separately by user]` |\n| Re-run on existing setup | Detect existing files; ask user per-file: replace, merge, skip |\n| User has no pricing \u002F opportunities | Skip Section 4 entirely; don't create empty files |\n\n## Portability\n\n- **Claude Code CLI:** Native — writes markdown files directly to filesystem.\n- **Claude.ai web:** Works with project files \u002F artifacts. Document the alternate path: generate files as artifacts, instruct user to save to their workspace, or use connected file system if available.\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fkb_validator.py` | Validates the 7-file KB output (required files present, conditional files only if their sections ran, headers + structure correct). |\n| `scripts\u002Fsection_progress_tracker.py` | JSON-backed walk state at `~\u002F.inbox_setup_sessions\u002F\u003Csession>.json`. Tracks active section, answered questions, committed files. |\n| `scripts\u002Fvoice_sample_analyzer.py` | Extracts voice patterns from pasted sent-email samples — opening phrases, sign-offs, length distribution, register markers. |\n\n## References\n\n- [`references\u002Fkb_file_contract.md`](references\u002Fkb_file_contract.md) — the canonical 7-file contract (write perspective; mirror lives in `inbox-triage\u002Freferences\u002F`)\n- [`references\u002Fgrill_me_section_walk.md`](references\u002Fgrill_me_section_walk.md) — 8-section discipline, skip-logic, commit-per-section\n- [`references\u002Fvoice_calibration.md`](references\u002Fvoice_calibration.md) — sample-based voice extraction theory + anti-patterns\n\n## Anti-Patterns To Reject\n\n- Generating all files at once instead of walking through sections\n- Asking all questions in one batch\n- Hardcoded provider references (Gmail-only thinking)\n- Persisting sensitive credentials in knowledge base\n- Skipping the \"why this question matters\" explanation\n- Skipping the sample-emails ask for voice (it's the highest-quality input)\n- Overwriting existing files without consent on re-run\n- Forcing creation of `rate-card.md` or `evaluation-framework.md` when they don't apply\n\n---\n\n**Version:** 1.0.0\n**Source spec:** [`megaprompts\u002F06-inbox-setup-megaprompt.md`](..\u002F..\u002F..\u002F..\u002Fmegaprompts\u002F06-inbox-setup-megaprompt.md)\n**Build pattern:** Path B (direct conversion). Paired with `inbox-triage`.\n","# Inbox-Setup — Email Triage Onboarding\n\n> **Paired with `inbox-triage`.** This skill writes the 7-file knowledge base at `${WORKSPACE}\u002FEmail\u002F` that `inbox-triage` reads on every run. The file contracts (names, sections, fields) MUST match between the two skills exactly. See [`references\u002Fkb_file_contract.md`](references\u002Fkb_file_contract.md).\n\nRun once (or re-run when business\u002Fpriorities change). Interview the user about their email patterns, business context, reply style, and priorities. Generate the structured knowledge base in `${WORKSPACE}\u002FEmail\u002F` that captures everything `inbox-triage` needs to process the inbox effectively.\n\n## Invocation Triggers\n\n- \"set up my inbox\"\n- \"configure inbox triage\"\n- \"set up my email system\"\n- \"configure email triage\"\n- \"build my email knowledge base\"\n- \"initialize email management\"\n- \"set up inbox triage\"\n- \"onboard email triage\"\n\n## Conduct Discipline\n\n**Do NOT generate all files at once.** Walk through the 8 sections one at a time. Each section commits its file(s) before moving on. Partial completion (e.g., user drops off mid-interview) still produces a usable partial KB.\n\nGrill-me discipline applies throughout:\n\n- **One question per turn.** Never bundle. Even across section boundaries.\n- **\"Why I'm asking\" on every question** — so users can answer well.\n- **Forcing format where possible.** Multi-choice > open-ended.\n- **Dependency-ordered.** Q2 depends on Q1; downstream sections depend on upstream.\n\nSee [`references\u002Fgrill_me_section_walk.md`](references\u002Fgrill_me_section_walk.md) for the 8-section discipline detail.\n\n## Knowledge Base Contract — Files To Produce\n\nExactly these files at `${WORKSPACE}\u002FEmail\u002F`:\n\n| File | Purpose | Required? |\n|---|---|---|\n| `email-taxonomy.md` | Classification system + report preferences | **Yes** |\n| `email-patterns.md` | Reply voice, tone, templates, hard rules | **Yes** |\n| `evaluation-framework.md` | Decision tree for opportunity emails | Only if user receives pitches\u002Fopportunities |\n| `rate-card.md` | Pricing, terms, negotiation posture | Only if user has pricing |\n| `blocklist.md` | Auto-skip senders + learned decline patterns | **Yes** (seeded, grows over time) |\n| `tracker.md` | Active follow-ups, overdue items, deadlines | **Yes** (starts mostly empty) |\n| `triage-log\u002F` | Directory for per-run logs | **Yes** (created empty) |\n\nThe contract is identical to what `inbox-triage` expects — see [`references\u002Fkb_file_contract.md`](references\u002Fkb_file_contract.md) for the full spec.\n\n## Stop Condition (Full Interview)\n\n~25–31 questions total across the 8 sections (depending on skip-logic). Hard ceiling: 35 questions including all sub-clarifications. Section 4 (Evaluation Framework) is skipped entirely when Section 1 surfaced no opportunity-email category, dropping the total by 6 questions and the rate-card file. After Section 8's confirmation + handoff message, intake is closed — **never re-open it**. To change preferences later, the user re-runs the skill (which detects existing files and asks per-file: replace \u002F merge \u002F skip). The grill-me one-at-a-time rule applies across section boundaries: do NOT batch questions even when moving from S{n} to S{n+1}.\n\n## Section 1: The Big Picture\n\nSix grill-me questions, one at a time:\n\n- **S1.Q1:** \"What do you do? Give me your role and business in 1–2 sentences. *Why I'm asking:* Context shapes what email patterns to expect — a solo creator's inbox looks nothing like an enterprise PM's.\"\n- **S1.Q2:** \"What dominates your inbox? Pick the top 1–2: sales pitches \u002F client work \u002F internal team \u002F newsletters \u002F customer support \u002F financial \u002F other. *Why I'm asking:* Dominant categories drive the taxonomy.\"\n- **S1.Q3:** \"Rough volume split — e.g., '60% business inquiries, 20% ops, 20% noise'. *Why I'm asking:* The split tells me where to focus triage effort.\"\n- **S1.Q4:** \"Which email address(es) should triage cover? *Why I'm asking:* If multiple, I'll set up per-address taxonomies.\"\n- **S1.Q5:** \"Run frequency: once daily \u002F 2x daily \u002F 3x daily \u002F on-demand only? *Why I'm asking:* Drives the default search window in triage (9h overlap for 2x\u002Fday).\"\n- **S1.Q6:** \"Anyone helping manage email — assistant, VA, team — or solo? *Why I'm asking:* Persona handling differs for delegated inboxes.\"\n\n**Action:** Build mental model. Do NOT write files yet. Note whether opportunity emails are a category (drives S4 skip-logic).\n\n## Section 2: Email Categories\n\nPropose 5–7 categories based on Section 1 — pre-recommend a subset, not the whole template menu:\n\n- New Opportunities\n- Active Conversations\n- Action Required\n- Financial\n- Important\u002FPersonal\n- Informational\n- Ignore\u002FLow Priority\n\nThen three forcing questions, one at a time:\n\n- **S2.Q1:** \"Here's my proposed taxonomy: [list]. Does this match your inbox reality — yes \u002F mostly \u002F no? *Why I'm asking:* If 'no', I need to redo the taxonomy before any other section makes sense.\"\n- **S2.Q2:** \"Missing categories? List them. (Skip if none.) *Why I'm asking:* Missing categories produce uncategorized emails downstream, which hurts triage quality.\"\n- **S2.Q3:** \"Which category takes the MOST time per email? *Why I'm asking:* That's where draft-reply effort needs to focus most.\"\n\n**Action:** Generate `email-taxonomy.md` with categories, signals (for each: trigger phrases \u002F sender patterns \u002F subject markers), and default actions per category.\n\n## Section 3: Reply Style & Voice\n\nSix grill-me questions plus the critical sample request:\n\n- **S3.Q1:** \"Register: formal \u002F casual \u002F in-between? *Why I'm asking:* Calibrates default voice; we'll refine from samples next.\"\n- **S3.Q2:** \"Three communication pet peeves — phrases you hate, openings you avoid. *Why I'm asking:* I treat these as forbidden tokens in drafts.\"\n- **S3.Q3:** \"Phrases or sign-offs you always use — list as many as come to mind. *Why I'm asking:* These are your voice fingerprints.\"\n- **S3.Q4:** \"Different persona for different contexts — e.g., assistant replies as you? *Why I'm asking:* Persona context changes pronoun + signature handling.\"\n- **S3.Q5:** \"Typical reply length — one-liner \u002F short paragraph \u002F longer? *Why I'm asking:* Length is the easiest voice signal to get wrong.\"\n- **S3.Q6:** \"Hard rules — never X \u002F always Y? (E.g., never emojis, always reply within 24h, never take calls without context.) *Why I'm asking:* Hard rules are enforced as non-negotiable in every draft.\"\n\n### S3.SAMPLES (the critical highest-quality input)\n\n> **Paste 3–5 real sent emails from your inbox.**\n>\n> *Why I'm asking:* Self-description of voice is unreliable. Real samples are the best signal — I'll analyze them for voice patterns that supplement everything above. Use `scripts\u002Fvoice_sample_analyzer.py` to extract patterns deterministically.\n\nIf user runs a business: also ask about media kits, rate sheets, standard pitches, repeated replies.\n\n**Action:** Generate `email-patterns.md` with tone description (with do\u002Fdon't examples), persona rules, templates, signatures, hard rules. See [`references\u002Fvoice_calibration.md`](references\u002Fvoice_calibration.md) for the sample-extraction discipline.\n\n## Section 4: Evaluation Framework (Conditional)\n\n**Skip-logic:** only run this section if Section 1 surfaced opportunity emails as a meaningful inbox category. Otherwise jump straight to Section 5.\n\nSix grill-me questions, one at a time:\n\n- **S4.Q1:** \"First thing you check when pitched something — give me your gut filter. *Why I'm asking:* That's the top of the decision tree.\"\n- **S4.Q2:** \"Three instant deal-breakers — things that make you decline immediately. *Why I'm asking:* These become PASS-auto signals.\"\n- **S4.Q3:** \"Three things that make you immediately interested. *Why I'm asking:* These become TAKE-IT signals.\"\n- **S4.Q4:** \"Standard pricing \u002F terms — or 'no fixed pricing' if you negotiate every time. *Why I'm asking:* If you have a rate card, I'll generate one; if not, I'll skip.\"\n- **S4.Q5:** \"Negotiation posture: firm \u002F flexible \u002F depends on context? *Why I'm asking:* Drives draft tone on counter-offers.\"\n- **S4.Q6:** \"VIP senders or organizations that always get engagement — list names or domains. *Why I'm asking:* VIP list bypasses normal PASS filters.\"\n\n**Action:** Generate `evaluation-framework.md` (decision tree + recommendation categories + VIP list) AND `rate-card.md` if pricing exists.\n\n## Section 5: Blocklist & Patterns\n\nThree grill-me questions, one at a time:\n\n- **S5.Q1:** \"Senders or domains to always skip — list them. (Skip if none.) *Why I'm asking:* Auto-blocklist saves the most time per run.\"\n- **S5.Q2:** \"Patterns in emails you always delete — e.g., 'unsubscribe' links from specific marketers, recruiter cold outreach, newsletters? *Why I'm asking:* Patterns let triage auto-skip variants without exact-match maintenance.\"\n- **S5.Q3:** \"Specific companies \u002F recruiters \u002F newsletters wasting time — list any. *Why I'm asking:* These seed the blocklist; triage will add more as you override decisions.\"\n\n**Action:** Generate `blocklist.md` (auto-maintained by triage thereafter).\n\n## Section 6: Current State\n\nThree grill-me questions, one at a time:\n\n- **S6.Q1:** \"Active threads you're tracking — list with one-line context each. (Skip if none.) *Why I'm asking:* These become tracker entries so triage knows existing context.\"\n- **S6.Q2:** \"Overdue replies — anything you should have responded to but haven't? *Why I'm asking:* Triage flags these as priority every run until resolved.\"\n- **S6.Q3:** \"Time-sensitive items with deadlines — list with dates. *Why I'm asking:* Tracker enforces deadlines and surfaces them as overdue at the right time.\"\n\n**Action:** Generate `tracker.md` with active follow-ups table, overdue section, resolved section (empty), update log (empty). Also create empty `triage-log\u002F` directory.\n\n## Section 7: Report Preferences\n\nThree grill-me questions, one at a time:\n\n- **S7.Q1:** \"Delivery format — pick one: email draft to self \u002F file in workspace \u002F chat summary only. *Why I'm asking:* The triage report goes here every run.\"\n- **S7.Q2:** \"Detail level — pick one: 30-second scan \u002F detailed breakdown \u002F both (scan first, expand on request). *Why I'm asking:* Affects report length.\"\n- **S7.Q3:** \"Anything always shown first — e.g., overdue payments, VIP messages? *Why I'm asking:* Custom 'top-of-report' rules surface what you care about above standard sections.\"\n\n**Action:** Save these preferences into `email-taxonomy.md` under a \"Report Preferences\" section.\n\n## Section 8: Confirmation & Handoff\n\nList every file created with one-sentence summary. Then:\n\n> Your triage system is ready. Run the **inbox-triage** skill to process your inbox. First runs need oversight — system learns from your edits and overrides.\n\nRemind: re-run this setup anytime business\u002Fpricing\u002Fpriorities change.\n\nRun `scripts\u002Fkb_validator.py --workspace ${WORKSPACE}` to confirm the 7-file contract is satisfied before final handoff.\n\n## Privacy Boundary\n\n**Never persist passwords, full account numbers, SSNs, or other sensitive credentials in knowledge base files.** If the user volunteers such info during the interview, acknowledge it but don't store it; the relevant KB file gets `[stored separately by user]` in its place.\n\n## Re-Run Behavior\n\nRe-running on an existing setup:\n\n1. Detect `${WORKSPACE}\u002FEmail\u002F`\n2. For each existing file, ask per-file: **replace \u002F merge \u002F skip**\n3. Walk only the sections whose files the user chose to update\n4. Skip sections whose files the user kept\n\n## Error Handling\n\n| Situation | Behavior |\n|---|---|\n| Workspace inaccessible | Stop. Tell user where files would go and ask for permission\u002Fpath |\n| User refuses to share samples | Use self-description; flag in patterns file that calibration may need iteration |\n| User says \"skip this\" mid-interview | Honor it; flag the gap in the file as `[needs follow-up]` |\n| Sensitive info volunteered | Acknowledge but don't persist; note in file as `[stored separately by user]` |\n| Re-run on existing setup | Detect existing files; ask user per-file: replace, merge, skip |\n| User has no pricing \u002F opportunities | Skip Section 4 entirely; don't create empty files |\n\n## Portability\n\n- **Claude Code CLI:** Native — writes markdown files directly to filesystem.\n- **Claude.ai web:** Works with project files \u002F artifacts. Document the alternate path: generate files as artifacts, instruct user to save to their workspace, or use connected file system if available.\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fkb_validator.py` | Validates the 7-file KB output (required files present, conditional files only if their sections ran, headers + structure correct). |\n| `scripts\u002Fsection_progress_tracker.py` | JSON-backed walk state at `~\u002F.inbox_setup_sessions\u002F\u003Csession>.json`. Tracks active section, answered questions, committed files. |\n| `scripts\u002Fvoice_sample_analyzer.py` | Extracts voice patterns from pasted sent-email samples — opening phrases, sign-offs, length distribution, register markers. |\n\n## References\n\n- [`references\u002Fkb_file_contract.md`](references\u002Fkb_file_contract.md) — the canonical 7-file contract (write perspective; mirror lives in `inbox-triage\u002Freferences\u002F`)\n- [`references\u002Fgrill_me_section_walk.md`](references\u002Fgrill_me_section_walk.md) — 8-section discipline, skip-logic, commit-per-section\n- [`references\u002Fvoice_calibration.md`](references\u002Fvoice_calibration.md) — sample-based voice extraction theory + anti-patterns\n\n## Anti-Patterns To Reject\n\n- Generating all files at once instead of walking through sections\n- Asking all questions in one batch\n- Hardcoded provider references (Gmail-only thinking)\n- Persisting sensitive credentials in knowledge base\n- Skipping the \"why this question matters\" explanation\n- Skipping the sample-emails ask for voice (it's the highest-quality input)\n- Overwriting existing files without consent on re-run\n- Forcing creation of `rate-card.md` or `evaluation-framework.md` when they don't apply\n\n---\n\n**Version:** 1.0.0\n**Source spec:** [`megaprompts\u002F06-inbox-setup-megaprompt.md`](..\u002F..\u002F..\u002F..\u002Fmegaprompts\u002F06-inbox-setup-megaprompt.md)\n**Build pattern:** Path B (direct conversion). Paired with `inbox-triage`.\n",{"name":5,"license":15,"metadata":24,"description":7},{"version":25,"paired_with":26,"source_spec":27,"build_pattern":28},"1.0.0","inbox-triage (shared 7-file KB contract)","megaprompts\u002F06-inbox-setup-megaprompt.md","Path B (direct conversion)","main","4c9acccad4644b62896dcb63e794f0d936b35d94","fabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup","https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager","https:\u002F\u002Fgithub.com\u002FHeverton-web","2026-08-06 09:12:45",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Heverton-web\u002Fskill-manager --skill inbox-setup",{"tool":41,"command":42},"bunx","bunx skills add Heverton-web\u002Fskill-manager --skill inbox-setup",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Heverton-web\u002Fskill-manager --skill inbox-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup\u002FSKILL.md",true,[49,55,59,63,69,73],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fgrill_me_section_walk.md","REFERENCE","参考文档",7259,"https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup\u002Freferences\u002Fgrill_me_section_walk.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fkb_file_contract.md",6185,"https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup\u002Freferences\u002Fkb_file_contract.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fvoice_calibration.md",8352,"https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup\u002Freferences\u002Fvoice_calibration.md",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002Fkb_validator.py","SCRIPT","脚本",10710,"https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup\u002Fscripts\u002Fkb_validator.py",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fsection_progress_tracker.py",10221,"https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup\u002Fscripts\u002Fsection_progress_tracker.py",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fvoice_sample_analyzer.py",11390,"https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002F.claude\u002Fskills\u002Finbox-setup\u002Fscripts\u002Fvoice_sample_analyzer.py",[78,85,92,99,106,113],{"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},"01M79ZW1HMA4KQ5NQKBNATQWYD","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002Fagentic\u002Fskills\u002Fyoutube-full\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},"01M79ZVENME42XFYS7F7W7TQYF","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002Fagentic\u002Fskills\u002Fx-twitter-growth\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},"01M79ZTQW25Y85KSE58B8YTDR4","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002Fagentic\u002Fskills\u002Fwrite-a-skill\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},"01M79ZTJ181TCYK8K995E26VDZ","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002Fagentic\u002Fskills\u002Fworkflow-builder\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},"01M79ZT5Q0B9WNWNQFZRFMK197","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002Fagentic\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M79ZSS3DTNNTAZYD2CZ9C4Z5","webinar-marketing","When the user wants to plan, promote, run, or improve a webinar or virtual event to generate and convert demand. Use when the user mentions 'webinar,' 'virtual event,' 'online event,' 'live demo,' 'virtual summit,' 'workshop,' 'masterclass,' 'fireside chat,' 'roundtable,' 'registration funnel,' 'show-up rate,' 'attendance rate,' 'webinar promotion,' 'webinar follow-up,' or 'on-demand webinar.' Also use when they have a webinar that isn't converting — low registrations, low show-up, or attendees who don't buy — and want to diagnose and fix it. Covers the full funnel: registration, promotion, show-up, live engagement, live-to-close, and post-event nurture. Distinct from launch-strategy (full product launches) and email-sequence (lifecycle nurture) — this is the end-to-end webinar\u002Fevent motion. NOT for in-person field events logistics, and NOT for generic lifecycle email (use email-sequence).","https:\u002F\u002Fgithub.com\u002FHeverton-web\u002Fskill-manager\u002Fblob\u002Fmain\u002Ffabrica-de-livros\u002Fagentic\u002Fskills\u002Fwebinar-marketing\u002FSKILL.md",[],[]]