agentleFS
erikunhaerikunha/vault-of-loci/.agents/skills/new-track/SKILL.md

new-track

Skill0 starsChanged 5 days agoMITView on GitHub

Create a new learning track in this vault (course, book, certification, interview, research, skill, language or other) from the recipe of its kind. Asks for the kind and the horizon. Use when the user starts learning something. Writes files, so only run when asked.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 0 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

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

    Read the recipe for that kind in 90_System/Specs/Track_kinds.md.

    line 10
  2. Very specific:

    Create the folder 10_Tracks/<NN>_<Track_Name>/ with underscores instead of spaces.

    line 11
  3. Very specific:

    Create <Track_Name>.md from 90_System/Templates/Track.md with type: track, kind, horizon, goal, done_criterion, deadline, if_then, status: …

    line 12
  4. Very specific:

    Create sessions/ (sessions come from 90_System/Templates/Session.md, named session-NN-<slug>.md) and practice/.

    line 13
  5. Very specific:

    Every kind also gets Concept_Map.md: the learner orders the concepts by necessity.

    line 20
  6. Very specific:

    When the track has a deadline, also copy Checkpoints.md and Plan_48h.md.

    line 21
  7. Very specific:

    Run the run-checks skill and report each check as passed, failed or not run.

    line 23
  8. Very specific:

    Add one line to 90_System/Agent_Log/YYYY-MM.md.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Tutor mode: the goal, the done criterion and the if-then plan are the learner's words. Ask for them and write what the learner says; do not invent them.

  1. Ask only for what is missing: the track name; the kind (course, book, certification, interview, research, skill, language, other); the horizon (finite ends when the done criterion is met, ongoing has no end); the goal; a done_criterion that can be failed; the deadline (finite only); one if_then plan ("If X, then I do Y").
  2. Read the recipe for that kind in 90_System/Specs/Track_kinds.md.
  3. Create the folder 10_Tracks/<NN>_<Track_Name>/ with underscores instead of spaces; NN is the next free number.
  4. Create <Track_Name>.md from 90_System/Templates/Track.md with type: track, kind, horizon, goal, done_criterion, deadline, if_then, status: active and order. Fill ## Setup and ## Review cadence from the recipe.
  5. Create sessions/ (sessions come from 90_System/Templates/Session.md, named session-NN-<slug>.md) and practice/. Copy the kit for the kind from 90_System/Templates/Practice/ into practice/, setting track: "[[<Track_Name>]]":
    • certification: Blueprint_Map.md.
    • interview: Problem_Log.md.
    • language: Input_Log.md and Output_Sample.md.
    • research: Synthesis_Matrix.md.
    • skill: Attempt_Log.md.
    • course, book, other: Checkpoints.md. Every kind also gets Concept_Map.md: the learner orders the concepts by necessity; you point out missing prerequisites. When the track has a deadline, also copy Checkpoints.md and Plan_48h.md.
  6. The track appears in 00_Home.md through Tracks.base; nothing to add by hand.
  7. Run the run-checks skill and report each check as passed, failed or not run.
  8. Add one line to 90_System/Agent_Log/YYYY-MM.md.

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.