agentleFS
ProjectAJ14ProjectAJ14/eklavya/skills/level/SKILL.md

level

Skill29 starsChanged 22 days agoMITView on GitHub

Show or pin Eklavya's difficulty level for this project — the easy/medium/hard band the questions are drawn from, and how far into it the developer is.

5 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tov-guidelines, icp-research and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • matteotittaSkill

    tov-guidelines

    Analyzes existing client content (website, blog, social, docs) to extract voice patterns, vocabulary preferences,

    Also in 3 projects that use this

  • growthack88Skill

    icp-research

    Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Produces TAM analysis, firmographic segments, champion and economic buyer personas, use case mapping, customer proof points, and voice-of-customer synthesis with normalized attributes. Requires website URL as primary input. Upstream: recommended company-context. Downstream: feeds positioning, product-messaging, landing-page-copy, content-strategy, and outreach-emails.

    Also in 3 projects that use this

  • VercelSkill

    messaging

    Use when turning settled positioning into the lines other people will reuse: the message hierarchy, value propositions per audience, objection handling, and the proof behind each claim.

    Also in 3 projects that use this

  • VercelSkill

    positioning

    Use when working out what a product is, who it's for, and what it competes with: the market alternatives, the ideal customer, the differentiators worth claiming, and the positioning statement that follows.

    Also in 3 projects that use this

  • YepAPISkill

    competitor-research

    Competitive analysis between domains using YepAPI.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    If pinned is set, say where it was pinned (their global config or their settings for this project) and that nothing will promote while it …

    line 32

“Common” is measured: kept by at least 6 in 10 of the 4 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

/eklavya:level [auto|easy|medium|hard]

Difficulty is a band, held per project and normally earned rather than chosen.

LevelTier bandThe questions it asks
easy1–2what a thing is, and what the machine does with it
medium2–4why this choice here, and what breaks it
hard3–5judgement, failure modes, when the architecture is wrong

Everyone starts a codebase at easy. That is the point: the developer has been watching the agent work, and tiers 1–2 are the questions that state can answer honestly. The band moves up on evidence — passing answers, at a real accuracy, spread across enough concepts — so week ten does not feel like week one.

It is per project because "how hard should this be" is a question about a codebase, not about a person. The same developer is a different learner on their fourth Node service and their first Rust one.

No arguments

  1. get_learner_profile — the level block has everything: the band, the next one, passed of needed, the accuracy so far and the concept spread.
  2. get_config if you need to say whether it is pinned, and by which file.

Report it in three lines or fewer:

  • Where they are — the level, and one clause on what that band asks for.
  • The runway — passed/needed passing answers, plus whichever other condition is still short (accuracy, or distinct concepts). Say the number; a progress bar nobody can total is not progress.
  • What is next — the band above, and what changes about the questions when they reach it. If they are on hard, say that this is the top and the tier ladder keeps working inside it.

If pinned is set, say where it was pinned (their global config or their settings for this project) and that nothing will promote while it stands. Do not report a runway toward a level a pin makes unreachable.

With an argument

set_config with difficulty.

  • auto — back to earning it. The project's own record is still there; it resumes where its evidence left it.
  • easy / medium / hard — pins the band and stops progression. A hard set, not a floor.

Scope, and ask when it is ambiguous:

  • global (default) — their own setting on every project. hard here is a senior saying they do not want the runway.
  • project — ~/.eklavya/projects/<checkout>/config.json, and it beats global whenever they work in that codebase. easy here is a codebase they are new to and want kept gentle. It is in their home directory, not the repository, so it reaches nobody else.

Two things to say plainly before writing:

  • Pinning at project scope overrides their own global setting in that codebase, and nobody else's.
  • Pinning hard on a codebase someone has just met is the failure levels exist to prevent. If they are pinning up because the questions feel trivial, check the level first — they may simply be near a promotion.

Confirm

One line: the new setting, the band it means, and what the next question will look like. Then stop — do not run a quiz unless they ask. /eklavya:quiz is for that.

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.

Reviews can't be read right now.

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.