跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
其他技能

setup-cracked

One-time setup for cracked. Creates your prep profile, builds briefs for your target companies, and suggests your first three sessions. Run once before using the other skills, and again whenever your targets change.

nishant-Tiwari24 · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add nishant-Tiwari24/cracked --skill setup-cracked

技能说明


name: setup-cracked description: One-time setup for cracked. Creates your prep profile, builds briefs for your target companies, and suggests your first three sessions. Run once before using the other skills, and again whenever your targets change. disable-model-invocation: true

Setup cracked

Get the candidate from zero to their first useful session in about two minutes.

  1. Call the Skill tool with "cracked-profile". Let it infer what it can, then ask its single round of questions. If a profile already exists, show it and ask what changed.

  2. For each company in target_companies (max 3), call the Skill tool with "company-intel". Skip this if they have no specific companies.

  3. Check the environment once and report it in a short table:

    • python3 available (needed for company questions, OA grading and the portable timeout runner)
    • the profile language's toolchain: g++/clang++ (C++), javac and java (Java), node (JavaScript), go (Go), python3 (Python). Without it, /oa-sim and /mock-interview fall back to hand-tracing, so say so.
    • timeout or gtimeout (optional: the Python runner in skills/interview/oa-sim/RUNNER.md replaces it, which matters on macOS and Windows)
    • on Windows: note that date +%s and mktemp aren't available. The skills use the Python fallbacks in RUNNER.md.
    • sqlite3 or Python's sqlite3 module (for SQL in /core-viva)
    • gh installed and authenticated (for /github-glowup)
    • a text-to-speech command (say, spd-say or espeak) and the agent's voice dictation, for voice mode in /mock-interview

    Missing tools are fine. Just say which skills lose which feature.

  4. Recommend the first three sessions for their situation, e.g. /roast-my-resume → /mock-interview <company> → /prep-plan. Then stop and let them pick.


Skill calls: if your agent has no Skill tool, open the named skill's SKILL.md in the cracked skills folder (core/, interview/, profile/, strategy/) and follow it instead.

Delegated implementation: cracked-profile

Source: https://github.com/nishant-Tiwari24/cracked/tree/3fc457cf4fb0ffc214ba97e9ef26d23dbc16b028/skills/core/cracked-profile


name: cracked-profile description: Load, create, or update the candidate's cracked profile and journal (target roles, companies, language, level, resume, deadline), and log scorecards. Every other cracked skill calls this first. Use when the user wants to set up or edit their placement/job-prep profile, see their progress history, or when another cracked skill needs the profile.

cracked profile

The shared memory layer for every cracked skill. It owns three things: the data directory, the profile, and the journal. Other skills call this skill first, then carry on with their own work.

Calling other skills

cracked skills call each other with lines like Call the Skill tool with "company-intel". If your agent has no Skill tool, open that skill's SKILL.md and follow it, then come back. The skills live side by side in the cracked folder: core/cracked-profile, core/company-intel, interview/<name>, profile/<name>, strategy/<name>. Never skip the profile step: the journal, company mode and scorecards depend on it.

Data directory

All cracked data lives in one directory, outside any project, so it follows the candidate across repos:

CRACKED_DIR="${CRACKED_HOME:-$HOME/.cracked}"

Resolve it with the shell once per session (echo "${CRACKED_HOME:-$HOME/.cracked}") and use the absolute path from then on. Create it if missing. Layout:

PathOwnerContents
profile.mdthis skillWho the candidate is and what they are aiming for
journal.mdthis skill (append-only)One scorecard per session, newest last
plan.mdprep-planThe current prep plan
stories.mdhr-roundThe candidate's behavioral story bank
companies/company-intelCached company prep briefs
cache/company-intelCached company-wise question data
oa/, defense/, resume/, offers/, jd/the skill of the same nameSession artifacts

If there is no shell or file access, keep the profile in the conversation and tell the user once that progress will not persist.

Loading the profile

  1. Read profile.md. If it exists and the calling skill has what it needs, do not ask any questions. Say one line, for example Loaded profile: <graduation year> grad · SDE-1 · product companies · C++ · placements in 9 weeks, and hand back.
  2. If it is missing, or a field the calling skill needs is empty, run Creating the profile below, asking only for the missing fields.
  3. If a deadline in the profile has passed, ask once whether to update it. Get today's date from the shell (date +%F); never assume it.

Creating the profile

Before asking anything, infer what you can:

  • git config user.name → name
  • gh api user --jq .login (if gh is installed and authed) → GitHub username
  • A file named like *resume* or *cv* (.pdf, .docx, .md, .tex) in the current directory or ~/Downloads, ~/Documents, ~/Desktop → resume path (confirm it, don't assume)

Then ask one round of at most six numbered questions, each with a suggested default so the user can reply in a few words:

1. Status: final-year student, pre-final year, recent grad, or working (how many years)?
2. Target roles: e.g. SDE / backend / frontend / full-stack / data / ML / DevOps.
3. Target companies: specific names, or a tier (service-based, product-based, big tech, startups, remote/international).
4. Main interview language: C++ / Java / Python / JavaScript / Go?
5. Honest DSA level: beginner (<100 problems), intermediate (100–300), strong (300+)? Any contest rating?
6. When do interviews/placements start, and which country are you hiring in?

Write profile.md in exactly this shape (leave unknown fields as -):

# cracked
阅读完整来源 ↗