agentleFS
Sign inStart free
tydev-newtydev-new/10xjobs-careercoach/skills/learn/SKILL.md

learn

Skill3 starsChanged 53 days agoMITView on GitHub

Use this skill when the candidate wants to build domain or technical knowledge for their target roles — e.g. "what should I study for FDE roles?", "do I know enough about payments to interview at Mesh?", "teach me system design interviews", "build me a course on X", "quiz me on Y", "where are my knowledge gaps?". Identifies the knowledge the target roles demand, assesses the candidate's level honestly, and builds researched courses to close the gaps.

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-anydoc, add-clidash and 10 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.
  • TomGranotSkill

    add-anydoc

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    Also in 5 projects that use this

  • TomGranotSkill

    add-clidash

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    Also in 5 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 11 projects that use this

  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • MicrosoftSkill

    add-codex

    Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

    Also in 6 projects that use this

  • MicrosoftSkill

    add-deltachat

    Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

    Also in 6 projects that use this

  • +5 more from TomGranot
  • +1 more from microsoft

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 170 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:

    Session close: Run ../profile/scripts/check_files.mjs --workspace .

    line 47

“Common” is measured: kept by at least 6 in 10 of the 170 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

Learn — know what the target roles demand

Goal

Map the domain and technical knowledge demanded by target roles, assess candidate proficiency honestly, and build researched courses to bridge critical gaps. Scored by references/eval.md.

Must be trueWhere
Every topic has Map row with valid scope, source, sighting count, and depthknowledge.md § Map
Assessments logged and stamped on Map row in same turn§ Assessment log + Map row
Live gaps have researched, cited course files (courses/<slug>.md)courses/
Status advances (gap → studying → credible) only on logged assessment evidenceknowledge.md
Never certify unearned credentials (clarify what candidate can honestly claim)reply

Prerequisites

  • Required: Workspace CLAUDE.md (none → profile's Setup); criteria.md § Targets (target roles and seniority band).
  • Optional: jd-analysis/ (demand-side competency sightings), profile.md.

The loop

Curriculum research, quiz formats, and topic depth standards live in references/patterns.md.

A topic (the loop)

Runs when candidate asks what to study, requests a quiz/course, or prep/practice identifies an unaddressed domain gap.

  • Standard: The course checklist at the row's seniority depth (references/eval.md § Quiz scoring).
  • Budget: 1 quiz round per assessment; reps stated up front. Read knowledge.md before starting.
  • Each pass: Map $\rightarrow$ Assess (short quiz + candidate self-rating $\rightarrow$ log + stamp row) $\rightarrow$ Course (research tiered sources, create courses/<slug>.md) $\rightarrow$ Train (reps against checklist).
  • Obligations:
    1. Track vs Role scope: Two independent JD sightings required to promote a topic to track scope (otherwise role: scoped).
    2. Honest calibration: State exact score and depth; never claim generic mastery.
    3. Dual write: Update § Assessment log and stamp the row in knowledge.md in the same turn.
  • Exits: Row reaches credible on a dated rep; budget expires; or the ceiling: two reps with the same coverage count → stop and adjust approach. Never relax the checklist.

State

Owned: knowledge.md and courses/ (shapes in references/schema.md).

  • Hands back: Format courses and frameable gaps → interview (scored reps & concern counters).
  • Session close: Run ../profile/scripts/check_files.mjs --workspace . and scripts/check_knowledge.py --workspace .. No checker-subagent is spawned (coach voice). Report outcomes, never narration (clean is 1 line; fix FAILs before reply ends).

Guardrails

  • Curricula must be researched with tiered sources (verified, general knowledge, unknown) and research dates, never hallucinated.

Every reply ends with ONE contextual next step — a sentence with its why, not a menu.

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.

Check your setup, free