Skip to content
Agentmart
Submit a tool

learning-path

Use when the user says 'learning path', 'what should I learn next', 'plan my learning', 'learning retro', or 'what did I learn this week'; plans a path or, in…

Skill by courtneyr-dev

IndexedMIT
Write a review

Chalk Labs

Need help deploying learning-path?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/courtneyr-dev-learning-path

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when the user says 'learning path', 'what should I learn next', 'plan my learning', 'learning retro', or 'what did I learn this week'; plans a path or, in retro mode, reviews a finished one.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/learning-path

What's inside

Skill name
learning-path
Description
Use when the user says 'learning path', 'what should I learn next', 'plan my learning', 'learning retro', or 'what did I learn this week'; plans a path or, in retro mode, reviews a finished one.
License
MIT
Instructions
38 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Learning path

One plan note per topic; plan mode writes it, retro mode edits it. No note for the topic (frontmatter `type: learning-path`) → plan. Note exists and the user names a milestone, says "retro", or asks what you learned → retro (no note: say so, then plan). Two or more matching notes → ask which (the one mid-task question).

## Folder

Folder: unset. Agree it with the user in the first intake question and record it here (one-line edit).

## Plan mode

Inputs: topic, baseline (known or built), target outcome (what you will ship or do), hours per week, deadline. Missing ones: one batched question, then finish without further check-ins.

1. Resources: reuse your Reader library (`readwise-mcp`) and `Resources/Readwise/` first; cap at 3 primary. Confirm each by search (URL, edition, version) even when the title is familiar.
2. Sequence fundamentals → applied practice. Each milestone: date, deliverable, pass/fail check, one practice exercise with feedback criteria; `quiz` is the understanding check.
3. Write the note (≤1 page): frontmatter (`type`, `topic`, `status`, `created`, `hours_per_week`, `deadline`), milestone table, one paragraph per milestone, empty `## Retros` section.

Done: note in the agreed folder; every milestone dated with deliverable and check; milestone hours ≤ hours per week × weeks to deadline.

## Retro mode

Inputs: the plan note; evidence since the last retro entry (or `created`): commits, vault notes, quiz results, daily notes, and what the user says you did.

Preconditions — four open blockers from the 2026-08-08 weekly-retro design (`Projects/weekly-learning-retro/`, a separate unbuilt session). Check each; record its state in the entry:

1. chief-of-staff paths unrepaired (no `Review/Weekly/` file in 14 days) → orient from the plan note and evidence only; say so.
3. Things AppleScript write unverified → list next actions in the entry for your to add by hand; create nothing in Things.
4. No session day picked → runs only when asked; no schedule, no cron.

Steps:

1. Score each due milestone pass, partial, or miss against its check, citing the file or commit.
2. Name blockers and weak concepts recurring across 2+ milestones; mark each reinforce or defer.
3. Re-date remaining milestones to the hours left; give the next one a date and a measurable checkpoint.
4. Surgical edit, not a whole-file rewrite: append a dated entry under `## Retros`; update the milestone rows.

Done, all in the plan note: each due milestone scored with evidence; next milestone dated with a checkpoint; four precondition states recorded.

From courtneyr-dev/agent-skills, MIT.

More from courtneyr-dev/agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 20, 2026 (1 month ago)
Last release
Sep 5, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from courtneyr-dev

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get learning-path running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying learning-path?

CallGet help
Cite this page

learning-path skill. Agent Mart. https://agentmart.dev/skills/courtneyr-dev-learning-path (last updated 2026-10-24)