- Home
- Skills
- Agents & Orchestration
- codechef-coach
Works with the AI Agents you already use
Codechef Coach
Evidence-based CodeChef coaching that turns profile data into diagnostic reports and structured practice plans.
$2.49
codechef-coach
Example session with this skill installed
Check my CodeChef profile (handle: tourist_fan) and tell me why I'm stuck at 3-stars. I can practice 10 hours a week.
- Read your context and instructions
- Compiled the codechef-coach
I have analyzed the profile for
tourist_fan. Here is the diagnostic report and your 2-week reset plan based on your 10-hour weekly budget.
Performance Audit: tourist_fan
| Metric | Value | Interpretation |
|---|---|---|
| Current Rating | 1642 (3★) | 158 points below peak (1800) |
| Recency | 12 days | Highly active |
| Trend (Last 5) | -12.4 | Moderate downward slide |
| Volatility (σ) | 48.2 | High (Inconsistent performance) |
| Engagement | 0.22 | Active ~1.5 days per week |
| Execution | 1.8 | Solving <2 problems per rated contest |
Primary Bottleneck: Low Practice Volume
Your engagement rate (0.22) is low for a 4-star target. You are currently a "contest-only" participant. Your volatility suggests that when you don't like the problem set, your performance drops sharply because you lack the baseline volume to grind through "off" topics.
2-Week Reset Plan (10 hrs/week)
Week 1: Foundations & Consistency
Contest Block (3 hrs): Participate in the upcoming Rated Division 3 contest. Focus on 100% accuracy on problems A and B before touching C.
Upsolving (3 hrs): Re-solve the first problem you failed in the last two contests. Do not use an editorial for the first 60 minutes.
- Topic Drill (4 hrs): Basic Graph Theory (BFS/DFS). Solve 5 problems in the 1400-1600 difficulty range.
Week 2: Execution Under Pressure
Virtual Contest (3 hrs): Run a past Starters contest. Set a "stop rule": if a submission fails twice, move to the next problem and return later.
- Upsolving (3 hrs): Complete the virtual contest C/D problems with editorials.
- Topic Drill (4 hrs): Dynamic Programming (Linear). Focus on state transitions.
Data Notes
- Handle:
tourist_fan - Fetched: 2023-10-27 14:30 UTC
- Contests Analyzed: 10
- Note: Ratings and trends are based on public contest history.
Next steps
- Confirm if C++ or Python is your primary language for specific recursion advice.
- Complete the Week 1 Graph Theory drill and report your solve rate.
- Share the ID of your next rated contest for a pre-game strategy.
Connects securely to your tools. The creator never sees your data.
About this skill
Your CodeChef rating is a reflection of your habits, not just your knowledge. When your rating plateaus or you struggle to break into a new star category, generic advice like "do more DP" doesn't help. This skill transforms public CodeChef profile data into objective diagnostics and actionable training schedules.
What it does
- Performance auditing calculates recency, volatility, and rating trends over your last 10 contests.
- Practice gap detection measures engagement vs. intensity to see if you are grinding without a feedback loop.
- Execution analysis compares problems solved per contest against targets for your current star rating.
- Structured practice planning generates 2-to-6 week schedules featuring contest blocks, upsolving, and topic-specific drills.
- User comparison provides side-by-side evidence of what separates two coders in terms of consistency and volume.
How it works
- Intake gathers your handle, target rating, and available weekly study hours.
- Data collection fetches profile stats, rating history, contest performance, and submission activity.
- Diagnostic computation runs your data through a playbook to identify bottlenecks like risk management or low volume.
- Report generation delivers a snapshot of your current form followed by a measurable training plan.
Frameworks & tools
This skill uses specialized tools to interface with public CodeChef data, including get_profile, get_rating_history, get_activity, and compare_users.
Why this beats prompting it yourself
Standard LLMs cannot see real-time CodeChef stats and often hallucinate contest history or rating math. This skill enforces evidence-based coaching, ensuring every recommendation is grounded in your actual submission cadence and contest deltas.
Use cases
- Diagnose why a 3-star coder has been stuck at the same rating for six months.
- Create a 4-week re-entry plan for a returning coder who hasn't competed in a year.
- Perform a post-mortem on the last three contests to identify execution errors.
- Compare your activity and solved counts against a higher-rated peer to find gaps.
Known limitations
Does not support live contest standings, source code review, or data from other judges. Results are subject to a 10-minute cache and require public profile accessibility.
Cannot access live contest data, source code, or private profiles. Topic inference is speculative. Minimum 3-5 contests required for trend analysis. 10-minute data caching applies.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 10 days ago
Requires