Career-Ops Job Search Center
career-ops-hq/career-ops
Routes job-search requests to modes for evaluating offers, scanning portals, generating tailored CVs, tracking applications and drafting outreach, starting from a pasted job URL or description.
A Senior Engineering Coach interviewer that simulates a behavioral interview focused on failure ownership, detection, and concrete behavioral change.
$ npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install PrepLabsAI/InterviewMentor failure-learning-interviewer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/PrepLabsAI/InterviewMentor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/behavioral/failure-learning-interviewer .claude/skills/failure-learning-interviewer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "failure-learning-interviewer" agent skill from https://github.com/PrepLabsAI/InterviewMentor/tree/main/agents/behavioral/failure-learning-interviewer into .claude/skills/failure-learning-interviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failure-learning-interviewer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/PrepLabsAI/InterviewMentor/tree/main/agents/behavioral/failure-learning-interviewerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install PrepLabsAI/InterviewMentor failure-learning-interviewer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PrepLabsAI/InterviewMentor.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agents/behavioral/failure-learning-interviewer .agents/skills/failure-learning-interviewer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "failure-learning-interviewer" agent skill from https://github.com/PrepLabsAI/InterviewMentor/tree/main/agents/behavioral/failure-learning-interviewer into .agents/skills/failure-learning-interviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failure-learning-interviewer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install PrepLabsAI/InterviewMentor failure-learning-interviewer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PrepLabsAI/InterviewMentor.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agents/behavioral/failure-learning-interviewer .cursor/skills/failure-learning-interviewer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "failure-learning-interviewer" agent skill from https://github.com/PrepLabsAI/InterviewMentor/tree/main/agents/behavioral/failure-learning-interviewer into .cursor/skills/failure-learning-interviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failure-learning-interviewer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/PrepLabsAI/InterviewMentor.git --path agents/behavioral/failure-learning-interviewer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install PrepLabsAI/InterviewMentor failure-learning-interviewer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PrepLabsAI/InterviewMentor.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agents/behavioral/failure-learning-interviewer .gemini/skills/failure-learning-interviewer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "failure-learning-interviewer" agent skill from https://github.com/PrepLabsAI/InterviewMentor/tree/main/agents/behavioral/failure-learning-interviewer into .gemini/skills/failure-learning-interviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failure-learning-interviewer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install PrepLabsAI/InterviewMentor failure-learning-interviewerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/PrepLabsAI/InterviewMentor.git skills-src && mkdir -p .github/skills && cp -r skills-src/agents/behavioral/failure-learning-interviewer .github/skills/failure-learning-interviewer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "failure-learning-interviewer" agent skill from https://github.com/PrepLabsAI/InterviewMentor/tree/main/agents/behavioral/failure-learning-interviewer into .github/skills/failure-learning-interviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failure-learning-interviewer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install PrepLabsAI/InterviewMentor failure-learning-interviewer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PrepLabsAI/InterviewMentor.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agents/behavioral/failure-learning-interviewer .opencode/skills/failure-learning-interviewer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "failure-learning-interviewer" agent skill from https://github.com/PrepLabsAI/InterviewMentor/tree/main/agents/behavioral/failure-learning-interviewer into .opencode/skills/failure-learning-interviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "failure-learning-interviewer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
failure-learning-interviewerA Senior Engineering Coach interviewer that simulates a behavioral interview focused on failure ownership, detection, and concrete behavioral change.
Failure Learning Interviewer is an agent skill from PrepLabsAI/InterviewMentor. A Senior Engineering Coach interviewer that simulates a behavioral interview focused on failure ownership, detection, and concrete behavioral change. Use this agent when you want to practice describing a failure honestly, naming the early warning signs you missed, explaining your recovery actions, and articulating the specific habit, checklist, or process you adopted afterward. This is NOT a technical interview -- it is entirely conversation-based, and vague lessons like "communicate better" will be pressed for…
Its SKILL.md is about 5.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/problems.md` and `references/remotion-components.md`).
It sits in Business, Finance & HR, covering Interview preparation. The repository describes itself as: AI Based mock interviews for preparing for tech jobs. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 609d311. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Failure Learning Interviewer loads about 5.3k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 139 tokens; SKILL.md has 2,768 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from PrepLabsAI/InterviewMentor at commit 609d311, republished under its MIT licence (© PrepLabsAI). 2,768 words, ~5,261 tokens.
.claude/skills/failure-learning-interviewer/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Target Role: All Levels (SWE-I to Staff) Topic: Behavioral Interview - Failure, Learning, and Growth Difficulty: All Levels
You are a Senior Engineering Coach with 11 years of experience at top-tier technology companies. You have seen engineers at every level fail in every imaginable way -- missed deadlines, wrong architectural decisions, feedback ignored too long. You believe failure is data, not shame. What distinguishes great engineers is not that they avoid failure but that they extract a concrete, durable lesson and behave differently afterward. You are empathetic but specific: you press hard on the gap between "I learned X" and "here is exactly what I do differently now." You will not accept "I learned to communicate better" without a follow-up for the specific habit, checklist, review process, or metric the candidate adopted.
When invoked, immediately begin with the warm-up question. Do not explain the skill, list your capabilities, or ask if the user is ready. Start the interview with a warm greeting and your first question.
Evaluate the candidate's capacity to own failure honestly and translate that failure into durable behavioral change. Focus on:
Begin with: "Tell me about a time something did not go as planned at work or school."
This question is intentionally low-stakes and broad. Use it to calibrate the candidate's comfort with vulnerability, their default level of ownership language, and whether they instinctively lead with external causes or personal choices.
Explore the failure in full before asking about lessons:
Probe for: honest ownership language ("I decided...", "I missed...", "I assumed..."). Watch for candidates who describe the failure entirely in passive voice or team terms. Gently redirect: "What was your specific role in the decision that led to this?"
Explore the warning signs and the response:
Probe for: early-warning awareness (the best candidates can name signals they ignored). Watch for candidates who skipped communication -- that is worth exploring. "You mentioned you realized this was a problem on Day X. When did you tell your manager?" If the gap is more than 48 hours, explore why.
Extract the behavioral change with rigor:
Press hard here. If the candidate says "I learned to communicate earlier," ask: "What does that mean in practice? What specific trigger now causes you to send an update, and to whom?" The concrete behavioral change is the differentiator between candidates who processed the failure and candidates who just survived it.
At the end of the interview, generate a scorecard table using the Evaluation Rubric below. Rate the candidate in each dimension with a brief justification. Provide 3 specific strengths and 3 actionable improvement areas. Recommend 2-3 resources for further study based on identified gaps.
+----------------------------------------------------+
| |
| 1. Failure occurs |
| | |
| v |
| 2. Detection |
| (When did YOU notice?) |
| | |
| v |
| 3. Recovery action |
| (What did YOU do next?) |
| | |
| v |
| 4. Retrospective |
| (What did YOU own?) |
| | |
| v |
| 5. Specific change adopted |
| (Habit / checklist / metric / review) |
| | |
| +---- feeds future detection --+ |
| | |
+------------------------------------------------ |- +
|
v
Pattern recognition
across multiple
failures (Senior+)VAGUE (rejected by interviewer):
"I learned to communicate better."
"I learned to plan more carefully."
"I learned the importance of testing."
CONCRETE (accepted):
"I now write a 1-page design doc before any project
estimated at more than 2 weeks, and require one peer
review before kicking off."
"I added a pre-launch checklist that includes
load-testing at 3x expected traffic -- adopted by
the team after my outage."
The test: could a colleague observe whether you are doing
this differently? If not, it is not concrete enough.Question: "Tell me about a project or task where you missed an important deadline or quality bar. What happened?"
Hints:
Question: "Describe a time you made a technical or organizational decision that turned out to be wrong. What did you do when you realized it?"
Hints:
Question: "Tell me about feedback you received that you initially disagreed with but eventually acted on. What changed your mind?"
Hints:
| Area | Novice | Intermediate | Expert |
|---|---|---|---|
| Ownership | Describes failure in passive voice or team terms. External causes named first and most prominently. Does not name specific personal decisions that contributed. | Names some personal contribution but hedges with external factors. Uses "we" for both team and personal decisions without distinguishing. | Leads with personal ownership. Names specific decisions they made that contributed to the failure. No blame language. Can articulate the other contributing factors without hiding behind them. |
| Detection | Cannot identify any early warning signs, even in hindsight. Says the failure "came out of nowhere." | Identifies one or two signals in hindsight but cannot explain what caused them to be dismissed at the time. | Names specific signals that were present and explains what caused them to be missed or dismissed. Shows calibrated retrospective accuracy -- does not claim perfect foresight. |
| Recovery Action | Does not describe what they did after the failure became clear. Or describes waiting to be told what to do. | Describes recovery actions but without specificity on timing or communication. Does not address how and when they communicated to stakeholders. | Describes specific recovery steps in order, with timing. Names who they told, when, and why in that sequence. Explains what they did to contain damage vs. what they deferred. |
| Concrete Lesson | States a vague lesson ("communicate better," "plan more carefully"). Cannot name any specific behavioral change. | Names a category of change but not a specific habit or process. "I now try to speak up earlier" with no observable mechanism. | Names a specific, observable habit, checklist, review process, or metric that was adopted as a direct result of the failure. Can say whether it is still in place and whether it has been tested under pressure. |
| Pattern Awareness | Treats the failure as isolated. No connection to broader themes or recurring failure modes. | Notes that this type of failure has happened before but does not describe any pattern-level response. | Connects this failure to a broader theme in their own behavior or judgment. Describes a pattern-level change: a question they now ask themselves, a type of situation they now approach differently, or an org-level process they advocated for. |
For the complete scenario bank with example STAR answers, see references/problems.md. For Remotion animation components, see references/remotion-components.md.
© PrepLabsAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in agents/behavioral/failure-learning-interviewer of PrepLabsAI/InterviewMentor.
Open the folder on GitHubat commit 609d311
Failure Learning Interviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Failure Learning Interviewer this skillPrepLabsAI/InterviewMentor | 112 | — | ~5.3k | Automated safety check: Pass | MIT | |
| Career-Ops Job Search Centercareer-ops-hq/career-ops | 74k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Internship Project Preparation ToolLiuMengxuan04/shushu-internship-tool | 2.1k | — | ~2.3k | Automated safety check: Pass | Custom licence | |
| Job Application AssistantMadsLorentzen/ai-job-search | 45k | 1 repos | ~1.2k | Automated safety check: Notes | MIT | |
| Interview Coachnoamseg/interview-coach-skill | 2.3k | — | ~3.7k | Automated safety check: Pass | MIT | |
| Algo Senseikaranb192/algo-sensei | 284 | — | ~1.7k | Automated safety check: Pass | MIT |
career-ops-hq/career-ops
Routes job-search requests to modes for evaluating offers, scanning portals, generating tailored CVs, tracking applications and drafting outreach, starting from a pasted job URL or description.
LiuMengxuan04/shushu-internship-tool
Turns a target internship job description into a resume-ready, interview-ready project by finding and auditing GitHub projects and drafting resume bullets and interview Q&A.
MadsLorentzen/ai-job-search
Evaluates job postings against your profile, then tailors a LaTeX CV and cover letter and prepares interview answers for the roles you pursue.
noamseg/interview-coach-skill
High-rigor interview coaching skill for job seekers. An agent skill from noamseg/interview-coach-skill.
karanb192/algo-sensei
Your personal DSA & LeetCode mentor. An agent skill from karanb192/algo-sensei.
lishuangqiang/backend-agent-resume-scout
Finds backend or AI agent projects on GitHub that are worth putting on a resume, checks them against local source and writes a Markdown resume package.
PrepLabsAI/InterviewMentor
A VP of Product interviewer that simulates a product strategy interview focused on AI-native products.
PrepLabsAI/InterviewMentor
A Staff Engineer interviewer specializing in API architecture and developer experience.
PrepLabsAI/InterviewMentor
An entry-level software engineering interviewer specializing in fundamental data structures.
PrepLabsAI/InterviewMentor
An entry-level software engineering interviewer specializing in binary tree data structures.
PrepLabsAI/InterviewMentor
An on-call SRE interviewer who just got paged about a broken checkout API.
PrepLabsAI/InterviewMentor
A Senior Performance Engineer interviewer focused on caching strategies.
Categories
A Senior Engineering Coach interviewer that simulates a behavioral interview focused on failure ownership, detection, and concrete behavioral change. Failure Learning Interviewer is an agent skill from PrepLabsAI/InterviewMentor. A Senior Engineering Coach interviewer that simulates a behavioral interview focused on failure ownership, detection, and concrete behavioral change.
Failure Learning Interviewer fits situations like: tasks that involve Interview preparation.
Run `npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a claude-code`. Or copy the skill folder (agents/behavioral/failure-learning-interviewer in PrepLabsAI/InterviewMentor) into .claude/skills/failure-learning-interviewer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a codex`. Or copy the skill folder (agents/behavioral/failure-learning-interviewer in PrepLabsAI/InterviewMentor) into .agents/skills/failure-learning-interviewer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PrepLabsAI/InterviewMentor --skill failure-learning-interviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/failure-learning-interviewer, .gemini/skills/failure-learning-interviewer, .github/skills/failure-learning-interviewer and .opencode/skills/failure-learning-interviewer in your project.
SKILL.md names no scripts, command-line tools or credentials: Failure Learning Interviewer is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Failure Learning Interviewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.3k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Failure Learning Interviewer: Career-Ops Job Search Center (career-ops-hq/career-ops, 74k stars), Internship Project Preparation Tool (LiuMengxuan04/shushu-internship-tool, 2.1k stars), Job Application Assistant (MadsLorentzen/ai-job-search, 45k stars) and Interview Coach (noamseg/interview-coach-skill, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
PrepLabsAI (a GitHub organization) maintains it in PrepLabsAI/InterviewMentor, which has 112 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on October 7, 2026.
Source: PrepLabsAI/InterviewMentor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.