run-learning-retrospective
An agent skill by cursor, from cursor/plugins. Tags: analysis, education, evaluation, planning, review.
What it does
Evaluate learning progress, identify blockers, and adjust the learning plan
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill run-learning-retrospectiveOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/teaching/skills/run-learning-retrospective ~/.claude/skills/run-learning-retrospectiveSafety box score
Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a markdown-only learning-planning prompt. It asks the agent to review progress and produce a retrospective and updated plan, with no scripts, file edits, network calls, or privileged actions.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | `SKILL.md` contains only prose and the instruction `Use Ask user tool`; there are no shell commands, code blocks, or runnable scripts. |
| Network access | 0 (none) | No remote fetches, API calls, uploads, or other network actions are described in `SKILL.md`. |
| Filesystem reach | 0 (none) | The skill does not read, write, or delete files; it only defines a retrospective workflow in markdown. |
| Secrets & credentials | 0 (none) | There is no request for tokens, passwords, `.env` files, or other credentials. |
| Privilege & persistence | 0 (none) | It does not mention sudo, installs, services, shell startup changes, or any OS-level settings. |
| Instruction hijack surface | 0 (none) | The file contains no hidden instructions, prompt-injection content, or directives to ignore safeguards. |
| Irreversible actions | 0 (none) | Its purpose is limited to generating a progress retrospective, updated learning plan, and next milestone; it does not execute actions on the user's behalf. |
| Transparency | 0 (none) | The entire skill is a single readable markdown file; there are no binaries, encoded blobs, or uninspectable components. |
Before installing
- Open `SKILL.md` and confirm it is markdown-only with no bundled scripts or remote content.
Rated 2026-10-21 by an automated review of 1 file from the skill's repository.
Source
- Repository
- cursor/plugins (all skills from this repository)
- Path
- teaching/skills/run-learning-retrospective/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- weekly-review — Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work
- improve-animations — Survey a codebase's animation and motion code as a senior motion advisor.
- advisor — Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done.
- arena — Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
- create-learning-path — Build a personalized learning roadmap with milestones and practice checkpoints
- figure-it-out — Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.