Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Improve

ASecurity

Use to log, prioritize, move, or review COURSE IMPROVEMENTS — the local kanban backlog in the course's `IMPROVEMENTS.md`. Load whenever an audit surfaces findings, the user notes something to fix / try / revisit, a handoff lands action items, or you're asked "what's on the board / what's next / show the backlog / log this". Each improvement is a card that moves Backlog → Ready → In Progress → In Review → Done. This is CONTINUOUS IMPROVEMENT (kaizen) for the course — NOT continuous integration...

5 stars
0 votes
0 copies
0 views
Added 9/24/2026
educationgogit

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add chaz-clark/canvas-toolbox --skill improve --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Improve?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Improve
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/chaz-clark-improve/badge)](https://www.skillsdirectory.com/skills/chaz-clark-improve)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: improve
description: Use to log, prioritize, move, or review COURSE IMPROVEMENTS — the local kanban backlog in the course's `IMPROVEMENTS.md`. Load whenever an audit surfaces findings, the user notes something to fix / try / revisit, a handoff lands action items, or you're asked "what's on the board / what's next / show the backlog / log this". Each improvement is a card that moves Backlog → Ready → In Progress → In Review → Done. This is CONTINUOUS IMPROVEMENT (kaizen) for the course — NOT continuous integration / CI pipelines / GitHub Actions.
---

# Improve — the course continuous-improvement board

Every course accumulates "should fix / should try" items — from audits, from teaching
a term, from the instructor noticing something. Left in chat or one-off letters, they're
lost by the next session. This skill keeps them in **one local, git-tracked kanban
board** so improvements are tracked to *done*, not rediscovered every term.

## The board

**`IMPROVEMENTS.md` at the course root.** Git-tracked (travels with the repo), plain
markdown (the instructor can edit it directly), no external service. If it doesn't
exist yet, copy `IMPROVEMENTS.template.md` from this skill to create it — confirm with
the instructor the first time.

## The one rule

**When an improvement is found — by an audit, by the instructor, by a handoff — it
becomes a card on the board. When it's worked, it moves through the columns. Nothing
that matters gets left only in chat.**

## Columns (the lifecycle)

`🗄 Backlog` (unordered ideas) → `🔴 Ready` (prioritized; top = next) →
`🟡 In Progress` (being worked) → `🔵 In Review` (done but unverified — awaiting the
instructor) → `✅ Done` (verified, linked to the PR/commit that closed it).

## Card schema

One line per card, compact:

```
- **[C-###] Short title** — src: <audit YYYY-MM-DD | user | handoff | session> · size <S/M/L> · risk <low/med/high> · <link when it moves>
```

- **id** `C-###` — stable, monotonic; never reused. Assign the next free number.
- **src** — where it came from + date, so provenance survives.
- **size / risk** — rough, for ordering. No story points.
- **link** — the PR/commit/handoff, added as the card moves to In Review / Done.

## How to work it (lightweight agile — solo-instructor scale)

- **Log**: new find → a `Backlog` card (or straight to `Ready` if it's clearly next).
  Audits write their findings here **as cards**, not as a separate lost letter.
- **Prioritize**: order `Ready` so the **top is the next thing** to pull. Tag size/risk.
- **Pull, don't push**: start work by pulling the top of `Ready` into `In Progress`.
  **WIP limit: keep `In Progress` small (≈2).** Finish before starting.
- **Review gate**: work lands in `In Review`, not `Done`, until the instructor has
  seen/verified it. Nothing self-marks Done.
- **Close**: move to `Done` with the PR/commit link and the date. Keep Done as the
  record (prune only when it's long).
- **Age**: flag a card that's sat in `In Progress`/`In Review` too long — surface it.

## Phrases that load this

"log this / add to the board", "what's on the board / show the backlog", "what's next /
what should I work on", "move C-012 to in progress / done", "prioritize the board",
"turn the audit into cards".

## Where it plugs in

- **`audit`** — an audit's output is a set of `IMPROVEMENTS.md` cards (with `src: audit
  <date>`), so findings are tracked to closure instead of filed and forgotten.
- **Handoffs** — a received handoff's action items become cards.
- The board is course context (no student PII) — **Zone-1**, safe to read and commit.

<!-- GENERATED by lib/tools/generate_adapters.py from skills/improve/SKILL.md — do not edit this copy directly; edit the canonical file and regenerate. schema_version: 1 -->

Attribution

chaz-clarkchaz-clark
View sourceSee grades on GitHubMore from chaz-clark →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Math Olympiad

1. **Strip thinking before verifying** — a verifier that sees the reasoning is biased toward agreement. Fresh context, cleaned proof only. 2. **"Does this prove RH?"** — if your theorem's specialization to ζ is a famous open problem, you have a gap. Most reliable red flag. 3. **Short proof → extract the general lemma** — try 2×2 counterexamples. If general form is false, find what's special about THIS instance. 4. **Same gap twice → step back** — the case split may be obscuring a unifie

374330 votes

Manim

Comprehensive guide for Manim Community - Python framework for creating mathematical animations and educational videos with programmatic control

304950 votes

Mcore Onboard Gb200 1node Tests

Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.

180410 votes

Mcore Split Pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

180410 votes

Read Sensor

Listens to a CARLA sensor and either saves its data to files, shows it live in a window, prints a one-shot summary, or (ros-info) reports the native ROS 2 topics, QoS and enabled-for-ROS state so you can echo it from ROS instead. Cameras save as PNG (depth/semantic auto-colourised) and display in a pygame window; lidar saves as .ply and shows as a top-down scatter; IMU/GNSS/radar/collision stream to JSONL or the console. Use when the user asks to "show/view the camera", "display the lidar", "...

144610 votes
View all in education →