analyze
01Command Claude Code
Use references/transcript-processing.md as execution guide.
Interview Coach is a Claude Code-based coaching system for the full job-search process, including job-description analysis, application materials, interview practice, answer evaluation, and offer negotiation. It is intended for job seekers who want tailored feedback and structured preparation based on their own experience and interview transcripts. Its catalogue entry consists of commands, a setting, and a skill that provide the coaching workflows.
This repository also configures its own agents. See what interview-coach-skill tells them →
Command Claude Code
Use references/transcript-processing.md as execution guide.
Command Claude Code
Command "apply" from noamseg/interview-coach-skill, covering apply — job application question drafting, inputs, sequence, q1 [behavioral] — story used: [story title] and q2 [process/method] — story used: [story title].
Command Claude Code
Executive coach Alisa Cohn (top 50 coaches in the world per Thinkers50, via Lenny's Podcast) emphasizes that the key to handling difficult interview moments is preparation — not just knowing the strategy but wrapping your mouth around the actual words beforehand. Her framework for difficult conversations.
Command Claude Code
Captures what happened in a real interview while it's still fresh. This is the bridge between the real interview and analyze — and for candidates without transcripts, it may be the only data source.
Command Claude Code
JD Structure Patterns: JDs follow predictable structures — company intro, role summary, responsibilities, requirements, nice-to-haves, benefits. But the signal isn't in the structure, it's in the language.
Command Claude Code
A lightweight command for capturing information that arrives between structured workflows. Feedback does capture, not analysis. Analysis happens in analyze, progress, and prep when the data becomes relevant.
Command Claude Code
When the user types help, generate a context-aware command guide — not just a static list.
Command Claude Code
The hype reel should be built from real coaching data, not generic encouragement.
Command Claude Code
Command "kickoff" from noamseg/interview-coach-skill, covering kickoff — setup workflow, step 1: coaching configuration, step 2: candidate context, step 2.5: resume analysis and step 2.55: career transition detection.
Command Claude Code
Optimize the candidate's LinkedIn profile as a search-discoverable, credibility-building, job-landing surface. LinkedIn is its own platform with its own rules — not a resume mirror. The profile needs to be optimized for how LinkedIn actually works: recruiter boolean search, algorithm distribution, section-specific…
Command Claude Code
A complete simulated interview (4-6 questions in sequence) with holistic feedback on the full arc — not just individual answers.
Command Claude Code
This workflow involves financial and legal-adjacent advice. Be explicit about boundaries.
Command Claude Code
Coach the candidate through the full outreach lifecycle: cold LinkedIn messages, warm introduction requests, informational interview asks, recruiter replies, follow-up sequences, and referral requests. Messages are built on the candidate's Positioning Statement so every outreach is differentiated, not generic.
Command Claude Code
Build the candidate's atomic unit of self-presentation: a positioning statement that distills who they are into a compelling, memorable core. The positioning statement is saved to coaching state and consumed by resume, linkedin, and outreach for cross-surface consistency.
Command Claude Code
Command "practice" from noamseg/interview-coach-skill, covering practice — practice system, drill progression ladder, revisit queue, question tailoring and warmup round.
Command Claude Code
6.5. Role-Fit Assessment — With the JD parsed and candidate profile available, run the full 5-dimension fit assessment from the Role-Fit Assessment Module (references/cross-cutting.md). See Step 6.5 below.
Command Claude Code
Format Prevalence: Presentation rounds appear across seniority levels and functions.
Command Claude Code
The value of progress scales with the data available. Before running the full protocol, assess what's in coachingstate.md and adapt.
Command Claude Code
Generate 5 questions with clear intent, interviewer fit, and follow-up preparation. Questions are strategic tools, not afterthoughts. Each question should serve at least one purpose.
Command Claude Code
Closes the loop on a coaching engagement. Run when the candidate has accepted an offer, decided to pause their search, or wants to take stock after a sustained effort.
Command Claude Code
A lightweight alternative to prep for when the candidate wants to understand a company before committing to a full prep cycle. Use when they're evaluating whether to apply, building a target list, or doing early-stage reconnaissance.
Command Claude Code
Optimize the candidate's resume across every dimension that actually affects whether they get interviews: ATS parsing and ranking, recruiter scan behavior, bullet quality, seniority calibration, keyword coverage, structure, concern management, and cross-surface consistency. This is NOT a duplicate of kickoff's Step…
Command Claude Code
The Anchoring Effect: The first number mentioned in a compensation conversation becomes the anchor. If a candidate says "$120K" in a recruiter screen, the final offer will orbit $120K — regardless of market rate. This makes the recruiter screen the highest-leverage comp moment. By the time negotiate fires…
Command Claude Code
Command "stories" from noamseg/interview-coach-skill, covering stories — storybank workflow, adding stories — guided discovery, improving stories — structured upgrade protocol, story strength audit and story versioning.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: