agentleFS
mtibebumtibebu/technical-learning-lab/.claude/skills/quick-recap/SKILL.md

quick-recap

Skill0 starsChanged 3 months agoMITView on GitHub

Give a fast, read-only condensed recap of a topic, book chapter, or company/role already tracked in this project — for interview day, a work meeting, or any moment you need a refresher, not a re-teach. Use when the user asks to be "reminded," "refreshed," wants a "quick recap"/"cheat sheet"/"summary" of something already studied, or needs an interview-day briefing.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. BuilderIO/skills★ 4.7ksame name
    2. CodeCaroS/MythOs_Aegis★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read-only and fast. Don't run train-topic's 5 stages, book-study's code-along flow, spaced-review's active-recall quiz, or mock-interview's …

    line 8
  2. Very specific:

    If it doesn't exist or the topic is not started in TRAINING.md, say so plainly — don't fabricate a recap.

    line 19
  3. Distinctive:

    Don't write the recap to a file by default.

    line 29
  4. Distinctive:

    When the user asks for an interview-day recap for a specific company/role, combine, in order:

    line 34
  5. Very specific:

    If none of these exist yet, say so and suggest running interview-prep-kit and/or mock-interview first rather than generating generic …

    line 43
  6. Distinctive:

    Keep the whole briefing short enough to read in the elevator — this is not the moment for a full study session.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Quick Recap

Read-only and fast. Don't run train-topic's 5 stages, book-study's code-along flow, spaced-review's active-recall quiz, or mock-interview's live round here — this skill only condenses what's already written down. If it isn't written down yet, say so and offer to run the matching skill instead of improvising a recap from general knowledge as if it were the user's own notes.

Single-topic/chapter recap

  1. Locate the source: topics/<slug>/README.md for a topic, books/<slug>/notes.md + books/<slug>/progress.md for a book chapter, or topics/interview-prep/<company-slug>.md for a company.
  2. If it doesn't exist or the topic is not started in TRAINING.md, say so plainly — don't fabricate a recap. Offer to run train-topic/book-study instead.
  3. Condense into a skimmable format, roughly a 60-90 second read:
    • Core idea — 1-3 sentences, the thing you'd say if someone asked "what is this" cold.
    • Key facts/terms — a short bullet list of the things most likely to get asked about or that are easy to blank on (numbers, API names, trade-offs, gotchas already noted).
    • Watch-outs — anything flagged in the original notes as a common mistake, a fast-moving/uncertain fact, or something the user previously got wrong (check REVIEW.md history / past miss notes if referenced).
    • Skip anything not already in the notes — this is compression, not new research.
  4. Don't write the recap to a file by default; it's meant to be read once, now. Only save it if the user asks.

Interview-day briefing

When the user asks for an interview-day recap for a specific company/role, combine, in order:

  1. The one-page summary from topics/interview-prep/<company-role-slug>-prep-kit.md if it exists (from interview-prep-kit).
  2. The mistakes checklist from topics/interview-prep/<company-slug>-mistakes.md if it exists (from mock-interview) — this is the highest-value thing to review right before walking in, since it's your own documented failure modes, not generic advice.
  3. A one-line takeaway from the most recent mock-interview log (topics/interview-prep/<company-slug>.md) if one exists.
  4. If none of these exist yet, say so and suggest running interview-prep-kit and/or mock-interview first rather than generating generic interview advice — a recap of nothing isn't useful.

Keep the whole briefing short enough to read in the elevator — this is not the moment for a full study session.

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.