![\"\u6c42\u804c\u9762\u8bd5\u6559\u7ec3\"](\"https:\/\/ai.jxgzhc.cn\/wp-content\/uploads\/2026\/09\/interview-coach-skill.png\")
<\/p>\n<\/p>\n
\u5e2e\u4f60\u9488\u5bf9\u6027\u5f25\u8865\u9762\u8bd5\u77ed\u677f\uff0c\u6784\u5efa\u8d34\u5408\u76ee\u6807\u804c\u4f4d\u7684\u4e2a\u4eba\u53d9\u4e8b\uff0c\u63d0\u5347\u62ffoffer\u6982\u7387\uff0c\u9ad8\u6548\u89c4\u5212\u5168\u6c42\u804c\u6d41\u7a0b\u3002<\/strong><\/p>\n Interview Coach<\/p>\n A Claude Code-based interview coach that covers the full job search lifecycle \u2014 from JD analysis and resume optimization through mock interviews to post-offer negotiation. 23 commands across application materials, interview prep, practice, analysis, and comp coaching. It scores your answers across five dimensions, diagnoses root causes behind weak spots, builds a storybank you can retrieve under pressure, and adapts its coaching to your specific patterns. Not a generic question bank. An adaptive system that gets sharper the more you use it.<\/p>\n Say kickoff , share your resume, and you're being coached in under 2 minutes.<\/p>\n What It Does<\/p>\n Scoring and diagnosis \u2014 Every answer scored on Substance, Structure, Relevance, Credibility, and Differentiation, calibrated to your seniority. Scores map to root causes (status anxiety, narrative hoarding, conflict avoidance) with targeted fixes, not just "do better."<\/p>\n Adaptive coaching \u2014 After scoring, a decision tree triages your bottleneck and branches to the right drill. If Relevance is your gap, you get question-decoding practice. If Substance, you build raw material. The system doesn't cycle through the same sequence for every candidate.<\/p>\n Multi-format transcript analysis \u2014 Paste raw transcripts from Otter, Zoom, Grain, Google Meet, Teams, Tactiq, Granola, or any other tool. The system auto-detects the format and normalizes it. Analysis adapts to interview type: behavioral interviews get Q&A parsing, system design gets phase-based analysis (scoping, approach, deep-dive, tradeoff, adaptation), panel interviews track cross-interviewer dynamics, and mixed formats handle mode-switching between technical and behavioral segments. Each format gets its own anti-pattern detection and additional scoring dimensions.<\/p>\n Storybank with portfolio optimization \u2014 Structured story management with full STAR text, earned secrets, strength ratings, and rapid-retrieval drills. Story-to-question mapping uses a 4-level fit scoring system (Strong Fit, Workable, Stretch, Gap) with portfolio optimization that resolves conflicts when multiple questions compete for the same story, tracks freshness and overuse, and prioritizes stories with strong earned secrets. Narrative identity extraction finds the 2-3 core themes across your stories so every answer reinforces a coherent thesis about who you are.<\/p>\n Practice and mocks \u2014 8-stage drill progression (constraint ladders, pushback handling, pivot drills, panel simulations, stress tests) plus full 4-6 question mock interviews in behavioral, system design, case study, panel, and technical+behavioral formats. Every round includes the interviewer's perspective \u2014 what they were actually thinking when you spoke. Role-drill scores map to core dimensions so specialized practice feeds into overall trend analysis. At Directness Level 5: expanded interviewer inner monologue, challenge notes on rounds 3+, and optional warmup skip.<\/p>\n Outcome calibration \u2014 The system tracks whether its practice scores actually predict real interview outcomes. After 3+ real interviews, it runs scoring drift detection, identifies when external feedback contradicts coach scoring, and recalibrates. Cross-dimension root causes (like "conflict avoidance" affecting both Substance and Differentiation) get unified treatment instead of separate drills. The system also learns from successes \u2014 tracking which stories, dimensions, and patterns correlate with advancement.<\/p>\n Role-fit assessment \u2014 Structured evaluation of candidate-role fit across five dimensions (requirement coverage, seniority alignment, domain relevance, competency overlap, trajectory coherence). Distinguishes strong fits from investable stretches and long shots, so candidates focus their energy on roles where they're competitive. Over time, rejection patterns reveal targeting insights that no amount of practice can fix.<\/p>\n Enhanced company intelligence \u2014 Three research depth levels (Quick Scan, Standard, Deep Dive) with a structured search protocol and claim verification. Every company-specific claim maps to a source tier (verified, general knowledge, or unknown). Prep briefs include targeted web research before applying company knowledge, with source attribution for every finding.<\/p>\n Interview lifecycle \u2014 Company research, role-specific prep briefs with interviewer intelligence, same-day post-interview debrief, outcome tracking that correlates practice scores with real results, and post-offer negotiation coaching with exact scripts.<\/p>\n Interview intelligence \u2014 The system learns from your real interview experiences. Every transcript, debrief, and recruiter feedback adds to a personalized knowledge base: question patterns across companies, what works and what doesn't for you specifically, and feedback-outcome correlations. Intelligence data has temporal decay \u2014 stale data is flagged, not silently relied on.<\/p>\n Session continuity \u2014 A persistent coaching_state.md file tracks your storybank, scores, patterns, drill progression, interview loops, interview intelligence, and calibration state across sessions. Pick up where you left off, weeks later. Saves are automatic.<\/p>\n Challenge protocol (Directness Level 5) \u2014 At the highest directness setting, the coach actively challenges you through five lenses: Assumption Audit, Blind Spot Scan, Pre-Mortem, Devil's Advocate, and Strengthening Path. Stories get red-teamed after you add or improve them. Transcripts get challenged. Practice rounds 3+ include a rotating challenge note. Progress reports include a Hard Truth section. Hype includes a pre-mortem before interviews. Rejections get mined for leverage. The system also detects avoidance patterns \u2014 if you keep steering away from a weakness, it names it directly. Every challenge ends with a concrete fix. Levels 1-4 are completely unaffected.<\/p>\n Guided flow \u2014 The coach recommends a specific next step after every command based on your coaching state \u2014 not a generic menu. When you say something like "prepare me for my interview at Google," it detects the multi-step intent and walks you through the full sequence (research, prep, concerns, hype) with natural transitions. Session start greetings include a prescriptive recommendation for the highest-leverage move right now.<\/p>\n LinkedIn profile optimization \u2014 Section-by-section audit of your LinkedIn profile against how the platform actually works: recruiter boolean search mechanics, algorithm distribution, and section-specific impact. Three depth levels from quick audit to deep optimization with content strategy. Not a resume-to-LinkedIn copy \u2014 a platform-native optimization that treats LinkedIn as its own game.<\/p>\n Resume optimization \u2014 Holistic resume audit across every dimension that actually affects outcomes: ATS parsing and ranking, recruiter scan behavior, bullet quality, seniority calibration, keyword coverage, structure, concern management, and cross-surface consistency. Three depth levels from quick audit to deep optimization with full bullet rewrite pipelines. When a storybank exists, the system mines it for quantified outcomes and earned secrets that should appear in resume bullets. When a JD is available, it produces a targeted version optimized for that specific application. Not a grammar check \u2014 a strategic overhaul of the resume as a job-search artifact.<\/p>\n Core positioning \u2014 Builds the atomic unit of self-presentation: a positioning statement that distills who you are into a compelling, memorable core. Uses curiosity gap principles, earned secret anchoring, and the Present-Past-Future formula to produce variants at every duration (10-second elevator, 30-second networking, 60-second recruiter call, 90-second interview TMAY) plus a LinkedIn summary hook. The positioning statement is saved to coaching state and consumed by resume, linkedin, and outreach for cross-surface consistency. Three depth levels from quick draft to deep positioning with a full differentiation audit.<\/p>\n Networking outreach coaching \u2014 Coaches the full outreach lifecycle: cold LinkedIn messages, warm introduction requests, informational interview asks, recruiter replies, follow-up sequences, and referral requests. Three depth levels from quick templates to full networking campaigns with multi-channel strategy. Messages are built on the candidate's Positioning Statement so every outreach is differentiated, not generic. The system knows platform mechanics (LinkedIn's 300-char connection request limit, optimal cold email length of 75-125 words, InMail response rates) and coaches accordingly. Includes a message quality rubric, follow-up cadence guidance, and the research showing that referrals account for 30-50% of hires from only 7% of applicants.<\/p>\n JD decoding and batch triage \u2014 Analyzes job descriptions using six decoding lenses (repetition frequency, order and emphasis, required vs. nice-to-have, verb choices, between-the-lines signals, and what's missing) with confidence labels on every interpretation. Maps extracted competencies against the candidate's profile for a fit verdict. Generates specific questions to ask the recruiter for every uncertain interpretation. Batch triage mode compares 2-5 JDs to find the candidate's market-validated sweet spot and recommend where to invest application effort. Includes a teaching layer so candidates learn to decode JDs themselves over time.<\/p>\n Presentation round coaching \u2014 Fills the prep gap for presentation-format interviews (system design presentations, business cases, portfolio reviews, strategy presentations, technical deep dives). Coaches narrative structure using four arc frameworks, optimizes openings and closings, calibrates content density against time limits (at ~130-150 words per minute), and prepares for Q&A with predicted questions and answer strategies. Three depth levels from quick structural framework to deep preparation with talk track review and constraint versions.<\/p>\n Early-process comp coaching \u2014 Coaches the highest-leverage compensation moments: the recruiter screen "what are your salary expectations?" question, salary history handling, and application form strategy. Guides candidates through comp research (without fabricating data), helps construct a defensible range, and provides stage-specific scripts with backups for pushback. Covers the full pre-offer comp timeline and hands off to the negotiate command when a formal offer arrives. Three depth levels from a quick 30-second script to full career-transition comp positioning.<\/p>\n Differentiation \u2014 Earned secrets and spiky POVs are a first-class dimension, not an afterthought. The system pushes you past "competent" toward "memorable."<\/p>\n Self-awareness \u2014 Tracks the gap between your self-assessment and actual coach scores. Knows if you're an over-rater or under-rater, and adjusts coaching accordingly.<\/p>\n Quick Start<\/p>\n Option 1: Claude Code (recommended)<\/p>\n Clone the repo:<\/p>\n git clone https:\/\/github.com\/noamseg\/interview-coach-skill.git Or download it as a ZIP and unzip.<\/p>\n Activate the coach by renaming the skill file:<\/p>\n mv SKILL.md CLAUDE.md<\/p>\n Open the folder in Claude Code and say kickoff .<\/p>\n Requires any paid Claude plan. Also works with Claude Code (terminal), Cursor, or any environment with file system access.<\/p>\n Option 2: OpenAI Codex<\/p>\n Clone the repo:<\/p>\n git clone https:\/\/github.com\/noamseg\/interview-coach-skill.git Or download it as a ZIP and unzip.<\/p>\n Activate the coach by renaming the skill file:<\/p>\n mv SKILL.md AGENTS.md<\/p>\n Open the folder in Codex and say kickoff .<\/p>\n Requires any paid ChatGPT plan.<\/p>\n For both options, the coach will ask for your resume, target role, and timeline \u2014 then build your profile, assess your starting point, and give you a prioritized action plan. Everything saves automatically to coaching_state.md so you pick up where you left off next session.<\/p>\n Commands<\/p>\n Getting Started<\/p>\n Command kickoff Interview Round Prep<\/p>\n Command research [company] decode prep [company] concerns questions present Application Materials<\/p>\n Command linkedin resume pitch outreach apply [company] Pre-Conversation<\/p>\n Command salary hype Practice and Simulation<\/p>\n Command practice mock [format] stories Analysis, Tracking, and Post-Interview<\/p>\n Command analyze debrief progress feedback thankyou negotiate reflect help Fast Workflow Examples<\/p>\n 1) Initial setup<\/p>\n kickoff<\/p>\n Expected output:<\/p>\n Track selected ( Quick Prep or Full System )<\/p>\n Profile snapshot (strength signals and concern areas)<\/p>\n Interview readiness assessment<\/p>\n Time-aware action plan (adjusted to your interview timeline)<\/p>\n 2) Company research (before committing to prep)<\/p>\n research Notion<\/p>\n Expected output:<\/p>\n Company snapshot (stage, size, culture signals \u2014 claim-verified with source tiers)<\/p>\n Fit assessment against your profile<\/p>\n "If you decide to apply" next steps<\/p>\n For high-priority targets, mention you want a deep dive: "Do a deep dive on Notion" \u2014 gets you employee posts, product reviews, competitor analysis, and leadership profiles on top of the standard research.<\/p>\n 3) Before an interview<\/p>\n prep Stripe<\/p>\n Then provide:<\/p>\n Job description<\/p>\n Role\/seniority<\/p>\n Optional interviewer LinkedIn URLs (for per-interviewer intelligence)<\/p>\n Expected output:<\/p>\n Interview Format (with format-specific coaching boundaries)<\/p>\n Company Culture Read<\/p>\n Interviewer Intelligence (if profile links provided \u2014 per-interviewer lens, focus areas, rapport hooks, story recommendations)<\/p>\n What They Optimize For<\/p>\n Your Best Positioning<\/p>\n Likely Concerns + Counters<\/p>\n Predicted Questions (7-10)<\/p>\n Story Mapping<\/p>\n Questions To Ask Them<\/p>\n Day-Of Cheat Sheet<\/p>\n 4) Right after an interview<\/p>\n debrief<\/p>\n Rapid capture while details are fresh \u2014 works with or without a transcript. Get:<\/p>\n Questions recalled and reconstructed answers<\/p>\n Interviewer signals observed (engagement, skepticism, interest)<\/p>\n Stories used (auto-updates storybank Last Used dates)<\/p>\n Coaching state updated for the next session<\/p>\n 5) Analyzing a transcript<\/p>\n analyze<\/p>\n Then paste raw transcript text from any tool (Otter, Zoom, Grain, Teams, etc.). The system auto-detects the format and normalizes it.<\/p>\n Expected output:<\/p>\n Format detection and normalization<\/p>\n Per-unit score blocks (Q# for behavioral, P# for system design phases, E# for panel exchanges)<\/p>\n Scorecard<\/p>\n Triage Decision (data-driven coaching path based on your patterns)<\/p>\n What Is Working<\/p>\n Top 3 Gaps To Close<\/p>\n Storybank Changes<\/p>\n Priority Move (Next 72 Hours)<\/p>\n 6) Drill practice<\/p>\n practice<\/p>\n Drills (in progression order \u2014 advance when you meet gating thresholds):<\/p>\n practice ladder \u2014 Constraint drills (30s, 60s, 90s, 3min)<\/p>\n practice pushback \u2014 Handle skepticism and interruption<\/p>\n practice pivot \u2014 Redirect when questions don't match prep<\/p>\n practice gap \u2014 Handle "I don't have an example" moments<\/p>\n practice role \u2014 Role-specific specialist scrutiny<\/p>\n practice panel \u2014 Multiple interviewer personas<\/p>\n practice stress \u2014 High-pressure simulation<\/p>\n practice technical \u2014 Thinking out loud, clarification-seeking, tradeoff articulation (system design \/ case study \/ mixed format only)<\/p>\n Standalone (not gated):<\/p>\n practice retrieval \u2014 Rapid-fire story matching under time pressure<\/p>\n Expected output each round:<\/p>\n Round Debrief<\/p>\n What Worked<\/p>\n Gaps<\/p>\n Scorecard (5 dimensions)<\/p>\n Self-Assessment Delta<\/p>\n Next Round Adjustment<\/p>\n 7) Full mock interview<\/p>\n mock behavioral Stripe<\/p>\n Runs a complete 4-6 question interview simulation. Formats: behavioral screen, deep behavioral, panel, bar raiser, system design\/case study, technical+behavioral mix. Holistic feedback on:<\/p>\n Overall impression and hiring signal<\/p>\n Energy trajectory and pacing across the full arc<\/p>\n Story diversity and selection quality<\/p>\n Signal-reading (did you adapt to interviewer cues?)<\/p>\n Per-question scoring + holistic patterns only visible across the full session<\/p>\n 8) Decode a JD before applying<\/p>\n decode<\/p>\n Then paste the job description. Get:<\/p>\n Competency extraction with confidence labels (HIGH\/MEDIUM\/LOW)<\/p>\n 6-lens analysis (repetition frequency, order, required vs. nice-to-have, verb choices, between-the-lines signals, what's missing)<\/p>\n Fit assessment against your profile (Strong Fit \/ Investable Stretch \/ Long-Shot Stretch \/ Weak Fit)<\/p>\n Recruiter verification questions for uncertain interpretations<\/p>\n Teaching layer so you learn to decode JDs yourself<\/p>\n For multiple JDs: paste 2-5 and get batch triage with ranking, your market-validated sweet spot, and allocation recommendations.<\/p>\n 9) Build your positioning statement<\/p>\n pitch<\/p>\n Get:<\/p>\n Core positioning statement anchored to your strongest earned secret<\/p>\n Context variants: 10-second elevator, 30-second networking, 60-second recruiter, 90-second interview TMAY<\/p>\n Positioning consistency check across resume, LinkedIn, and interview narrative<\/p>\n 10) Coach an outreach message<\/p>\n outreach<\/p>\n Then specify message type (cold LinkedIn, warm intro, recruiter reply, etc.) and target. Get:<\/p>\n Draft critique (if you bring a draft) or guided construction<\/p>\n Rewritten message within platform constraints (300 chars for LinkedIn connection requests)<\/p>\n Follow-up sequence with timing<\/p>\n Earned secret hooks pulled from your storybank<\/p>\n 11) Answer job application screening questions<\/p>\n apply HireRight<\/p>\n Then provide:<\/p>\n List of application questions (paste them directly)<\/p>\n Optional: JD (used for domain matching and "why us" questions)<\/p>\n Optional: word or character limits per question<\/p>\n Expected output:<\/p>\n Per-question story selection menu (2-3 options, with [Domain match] flag when a story comes from the same industry as the company)<\/p>\n Prior answer suggestions when a similar question was answered for another company<\/p>\n Ready-to-paste written answers in written register (150-200 words each, tighter than spoken interview answers)<\/p>\n Flagged gaps where storybank or resume evidence is missing \u2014 no answer gets fabricated<\/p>\n Answers are saved to job-search\/[company]_application.md and reused as a library across future applications.<\/p>\n 12) Post-offer negotiation<\/p>\n negotiate<\/p>\n Then provide offer details, competing offers, and ideal outcome. Get:<\/p>\n Market position analysis<\/p>\n Negotiation strategy with priority ordering<\/p>\n Exact scripts for the conversation<\/p>\n Fallback language for pushback<\/p>\n Tracks<\/p>\n Quick Prep<\/p>\n Best when interview timeline is short.<\/p>\n Company research<\/p>\n Prep brief<\/p>\n Focused transcript analysis<\/p>\n Immediate next actions<\/p>\n Full System<\/p>\n Best when running a multi-week search.<\/p>\n Storybank management with rapid-retrieval drills and portfolio-optimized story mapping<\/p>\n Multi-format transcript analysis (behavioral, system design, panel, mixed) with decision tree triage<\/p>\n Pattern and trend tracking with self-assessment calibration<\/p>\n Differentiation coaching integrated into all workflows<\/p>\n Full mock interview simulations (behavioral, system design, case study, panel, technical+behavioral mix)<\/p>\n Drill progression with gating thresholds (8 stages + standalone retrieval)<\/p>\n Post-interview debrief and rapid capture<\/p>\n Outcome tracking (correlate practice with real results) with scoring calibration (drift detection, recalibration)<\/p>\n Interview intelligence \u2014 learns question patterns, what works\/doesn't, and company-specific insights from your real interviews, with temporal decay on stale data<\/p>\n Interview loop awareness across company rounds<\/p>\n Post-offer negotiation coaching<\/p>\n Post-search retrospective and archiving<\/p>\n Choose during kickoff . You can switch later.<\/p>\n Repository Structure<\/p>\n interview-coach-skill\/ Best Results<\/p>\n Share a real resume (not a high-level summary).<\/p>\n Include a full job description for prep \u2014 and the interview format if you know it.<\/p>\n Use real transcripts for analyze . The more you give it, the better the triage.<\/p>\n Keep a living storybank with stories . Extract earned secrets for every story.<\/p>\n Run progress weekly \u2014 it tracks your self-assessment accuracy, not just scores.<\/p>\n After real interviews, log outcomes. The system correlates practice scores with real results.<\/p>\n When you hear back from a recruiter \u2014 good or bad \u2014 run feedback to capture it. The system learns from your real experiences over time.<\/p>\n Run mock before important interviews. Individual drills build skills; mocks test the full arc.<\/p>\n Use debrief the same day as a real interview \u2014 capture signals while they're fresh.<\/p>\n Run decode before applying \u2014 analyze the JD's language, assess your fit, and decide if the role is worth your time. Use batch triage to compare multiple JDs at once.<\/p>\n Run salary before your first recruiter call \u2014 the recruiter screen is the highest-leverage comp moment, not the offer negotiation.<\/p>\n Run present before a presentation round \u2014 structure your content and prepare for Q&A before you ever open PowerPoint.<\/p>\n Run apply when a job application includes screening questions \u2014 it surfaces domain-relevant stories, checks your storybank for evidence before drafting, and builds a reusable answer library across applications.<\/p>\n FAQ<\/p>\n How is this different from asking ChatGPT for interview help? Does this only work for tech roles? Why is the feedback direct? How does it work across multiple sessions? Contributing<\/p>\n Open an issue or PR with:<\/p>\n Repro steps<\/p>\n Current behavior<\/p>\n Expected behavior<\/p>\n Suggested fix (optional)<\/p>\n Credits<\/p>\n Created by Noam Segal .<\/p>\n License<\/p>\n MIT<\/p>\n \u4f5c\u8005\uff1anoamseg \u00e8\u0081\u008c\u00e5\u009c\u00ba\u00e4\u00ba\u00ba \/ \u00e5\u00ad\u00a6\u00e7\u0094\u009f\u00e7\u00a0\u0094\u00e7\u00a9\u00b6\u00e8\u0080 \uff5c GitHub Stars 2K \uff5c \u6807\u7b7e\uff1a\u5199\u4f5c\u6587\u6848 \u77e5\u8bc6\u7ba1\u7406 \u5df2\u8ba4\u8bc1 \u5f00\u6e90\u8bb8\u53ef: MIT<\/p>\n\u8be6\u7ec6\u4ecb\u7ecd<\/h2>\n
cd interview-coach-skill<\/p>\n
cd interview-coach-skill<\/p>\n
Purpose
Typical Output<\/p>\n
Setup profile, track, and preferences
Kickoff summary + time-aware action plan<\/p>\n
Purpose
Typical Output<\/p>\n
Company research + structured fit assessment (3 depth levels)
Company snapshot, culture signals, fit assessment, claim-verified findings<\/p>\n
JD analysis + batch triage (3 depth levels, 6 lenses)
Confidence-labeled decoding, competency extraction, fit assessment, recruiter verification questions, batch comparison, teaching layer<\/p>\n
Build role-specific prep brief (format-aware, culture-aware, role-fit assessment)
Format guidance, culture read, role-fit assessment, interviewer intelligence, competencies, predicted Qs, story mapping<\/p>\n
Anticipate interviewer concerns
Concern-counter-evidence map<\/p>\n
Generate interviewer questions
5 tailored, non-generic questions<\/p>\n
Presentation round coaching (3 depth levels)
Narrative arc selection, content structuring, timing calibration, opening\/closing optimization, Q&A preparation, constraint versions<\/p>\n
Purpose
Typical Output<\/p>\n
LinkedIn profile optimization (3 depth levels)
Section-by-section audit, rewritten sections, content strategy<\/p>\n
Resume optimization (3 depth levels, JD-targeted when available)
ATS audit, section-by-section assessment, bullet rewrites, seniority calibration, keyword analysis, storybank-to-bullet pipeline<\/p>\n
Core positioning statement + context variants
Core statement, constraint ladder, context-specific pitches, positioning consistency check<\/p>\n
Networking outreach coaching (3 depth levels, 9 message types)
Message frameworks, draft critique + rewrite, follow-up sequences, multi-channel campaign strategy<\/p>\n
Draft written answers to job application screening questions
Story selection menu per question (with domain match flagging), ready-to-paste answers, prior answer reuse, flagged gaps<\/p>\n
Purpose
Typical Output<\/p>\n
Early\/mid-process comp coaching (3 depth levels)
Comp research guidance, range construction, stage-specific scripts, total comp education, salary history handling<\/p>\n
Pre-interview confidence + psychological warmup. At Level 5: includes a pre-mortem with failure prevention
60-second reel + 3×3 sheet + focus cue + recovery playbook<\/p>\n
Purpose
Typical Output<\/p>\n
Run drill rounds (with progression gating). At Level 5: challenge notes, expanded interviewer read, optional warmup skip
Round debrief + self-assessment delta + targeted adjustment<\/p>\n
Full simulated interview (4-6 Qs) \u2014 behavioral screen, deep behavioral, panel, bar raiser, system design\/case study, technical+behavioral mix
Holistic arc feedback, signal-reading notes, energy trajectory<\/p>\n
Build\/manage storybank + rapid-retrieval drill. At Level 5: stories get red-teamed with 5 challenge lenses
Story table + earned secrets + gap analysis + retrieval drill<\/p>\n
Purpose
Typical Output<\/p>\n
Analyze transcript with format-aware parsing, triage-based coaching, and interviewer's inner monologue. At Level 5: includes structured challenge
Auto-detected format, per-unit scoring (Q&A\/phases\/exchanges), format-specific dimensions, decision tree + interview delta<\/p>\n
Post-interview rapid capture (same day)
Questions recalled, interviewer signals, stories used, coaching state updates<\/p>\n
Trends, self-calibration, outcome tracking, scoring calibration. At Level 5: includes a Hard Truth section
Self-assessment delta + outcome correlation + scoring drift detection + root cause tracking + coaching meta-check<\/p>\n
Capture recruiter feedback, outcomes, corrections, context, or coaching meta-feedback. At Level 5: rejections include structured leverage extraction
State updates + next step suggestion<\/p>\n
Post-interview follow-up drafts
Thank-you note + variants<\/p>\n
Post-offer negotiation coaching
Offer analysis + strategy + scripts + specific language<\/p>\n
Post-search retrospective + archive
Journey arc, breakthroughs, transferable skills, archived state<\/p>\n
Show command menu (context-aware)
Full command list + recommended next based on coaching state<\/p>\n
\u251c\u2500\u2500 SKILL.md # Core skill \u2014 rename to CLAUDE.md to activate
\u251c\u2500\u2500 README.md # This file
\u251c\u2500\u2500 LICENSE # MIT License
\u251c\u2500\u2500 coaching_state.md # Created on first kickoff (persistent memory, auto-saved)
\u2514\u2500\u2500 references\/
\u251c\u2500\u2500 commands\/ # Per-command workflows (loaded on demand)
\u2502 \u251c\u2500\u2500 kickoff.md
\u2502 \u251c\u2500\u2500 research.md
\u2502 \u251c\u2500\u2500 prep.md
\u2502 \u251c\u2500\u2500 analyze.md
\u2502 \u251c\u2500\u2500 debrief.md
\u2502 \u251c\u2500\u2500 practice.md
\u2502 \u251c\u2500\u2500 mock.md
\u2502 \u251c\u2500\u2500 stories.md
\u2502 \u251c\u2500\u2500 concerns.md
\u2502 \u251c\u2500\u2500 questions.md
\u2502 \u251c\u2500\u2500 linkedin.md
\u2502 \u251c\u2500\u2500 resume.md
\u2502 \u251c\u2500\u2500 pitch.md
\u2502 \u251c\u2500\u2500 outreach.md
\u2502 \u251c\u2500\u2500 decode.md
\u2502 \u251c\u2500\u2500 present.md
\u2502 \u251c\u2500\u2500 salary.md
\u2502 \u251c\u2500\u2500 hype.md
\u2502 \u251c\u2500\u2500 thankyou.md
\u2502 \u251c\u2500\u2500 progress.md
\u2502 \u251c\u2500\u2500 negotiate.md
\u2502 \u251c\u2500\u2500 feedback.md
\u2502 \u251c\u2500\u2500 apply.md
\u2502 \u251c\u2500\u2500 reflect.md
\u2502 \u2514\u2500\u2500 help.md
\u251c\u2500\u2500 cross-cutting.md # Shared modules: gap-handling, signal-reading, differentiation, cultural awareness, psychological readiness, cross-command dependencies
\u251c\u2500\u2500 rubrics-detailed.md # Scoring anchors, root causes, seniority calibration
\u251c\u2500\u2500 role-drills.md # Role-specific drills + interviewer archetypes
\u251c\u2500\u2500 differentiation.md # Earned secrets, spiky POVs, clarity under pressure
\u251c\u2500\u2500 transcript-processing.md # Step-by-step transcript analysis guide (format-aware parsing)
\u251c\u2500\u2500 transcript-formats.md # Format detection + per-format normalization (Otter, Zoom, Grain, etc.)
\u251c\u2500\u2500 storybank-guide.md # Story management + rapid-retrieval drill
\u251c\u2500\u2500 story-mapping-engine.md # Portfolio-optimized story mapping with fit scoring
\u251c\u2500\u2500 calibration-engine.md # Scoring drift detection, root cause tracking, success patterns
\u251c\u2500\u2500 challenge-protocol.md # Five-lens challenge framework (Level 5 only): assumption audit, blind spot scan, pre-mortem, devil's advocate, strengthening path
\u2514\u2500\u2500 examples.md # Worked examples: scored answers, triage, rewrites, system design analysis<\/p>\n
Generic LLM interview help gives you the same advice regardless of your patterns. This system scores you on five dimensions, tracks your scores over time, diagnoses root causes behind weak spots, builds a storybank with retrieval drills, and adapts its coaching based on what the data reveals. It remembers your previous sessions, knows which stories you've already used at a company, and changes its approach when something isn't working. It's the difference between a textbook and a coach.<\/p>\n
No. Core workflows are role-agnostic; role drills include PM, Engineering, Design, Data Science, Research, Operations, and Marketing.<\/p>\n
The skill is intentionally high-candor and evidence-based. It uses strengths-first delivery and self-reflection before critique. It also periodically checks whether the coaching is landing and adapts if not. You can set your feedback directness level (1-5) during kickoff. At Level 5, the Challenge Protocol activates: stories get red-teamed, progress includes a Hard Truth, rejections get mined for leverage, and avoidance patterns are named directly. Levels 1-4 are gentler \u2014 same rigor, softer delivery.<\/p>\n
The skill writes a coaching_state.md file that tracks your storybank, scores, patterns, drill progression, interview outcomes, interview loops, and more. At the start of each session, it reads this file and picks up where you left off. Saves happen automatically after every major workflow \u2014 not just at session end.<\/p>\n\u8bd5\u8bd5\u8fd9\u6837\u505a<\/h2>\n
\n
\n