agentleFS
SirjanSinghSirjanSingh/oahelper-mcp/skills/study-plan/SKILL.md

study-plan

Skill2 starsChanged 25 days agoMITView on GitHub

Build a day-by-day study plan to the user's OA or interview dates from the company patterns saved by the oahelper MCP server and their past practice results. Use when the user says "make me a study plan", "I have X's OA on <date>", "how should I prepare in N days", "schedule my prep", or lists upcoming OA and interview dates.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask only for what is missing, in one message:

    line 12
  2. Distinctive:

    Use today's date from the environment, not a guess.

    line 17
  3. Very specific:

    Read the newest sets to get the format and topic mix (follow oa-compare if there are several companies).

    line 22
  4. Very specific:

    Read library/_progress.md if it exists: topics with misses or solved-with-hints get extra time, topics solved cleanly get less.

    line 24
  5. Very specific:

    Every day has: one focused topic block, practice from that company's real questions in the library, and 10 to 15 minutes of mcq-drill if …

    line 31
  6. Very specific:

    Put a full oa-mock roughly every 3 to 4 days.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Study plan to the OA date

Part of oahelper-mcp by Sirjan Singh.

1. Inputs

Ask only for what is missing, in one message:

  • Companies and their OA or interview dates (and time zone if close).
  • Hours available per day.
  • Weak areas the user already knows about (optional).

Use today's date from the environment, not a guess.

2. Evidence

  1. For each company, oahelper_offline(company); sync only if nothing is saved.
  2. Read the newest sets to get the format and topic mix (follow oa-compare if there are several companies).
  3. Read library/_progress.md if it exists: topics with misses or solved-with-hints get extra time, topics solved cleanly get less.

3. Plan rules

  • Earliest deadline first. The day before each OA is a light day: one timed oa-mock and a review, nothing new.
  • Every day has: one focused topic block, practice from that company's real questions in the library, and 10 to 15 minutes of mcq-drill if the company's OAs include MCQs.
  • Put a full oa-mock roughly every 3 to 4 days.
  • Each item names a concrete question file or a known LeetCode problem, not just a topic.
  • Fit the user's hours. If everything does not fit, cut the lowest-frequency topics and say what was cut.

4. Output

# Prep plan: <companies>, <today> to <last date>

| Date | Focus | Practice (links) | Time |

Cut for time: ...

Save it as prep/study-plan-<today>.md (or where the user keeps notes) and offer to update it after each mock.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.