agentleFS
Sign inStart free
HolojermHolojerm/drawthesystem/skills/critique/SKILL.md

critique

Skill0 starsChanged 2 months agoMITView on GitHub

Async review of your Excalidraw diagram (+ notes) for a session against the scenario and rubric; writes feedback.md. Usage — /critique [session-dir] [path/to/other.excalidraw]

80 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use delight, teach-impeccable 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.
  • HK-hubSkill

    delight

    Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

    Also in 33 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • owshq-mecSkill

    layout

    Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

    Also in 8 projects that use this

  • +8 more from HK-hub

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 73 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Read prompt.md, interviewer.md, notes.md (if the user filled it), rubric/rubric.md.

    line 13
  2. Very specific:

    Run bun scripts/read-excalidraw.mjs <diagram> and read the summary.

    line 14

“Common” is measured: kept by at least 6 in 10 of the 73 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

/critique [session-dir] [diagram-path]

Grade a diagram you drew on your own time. Same rubric as /mock, but diagram-centred and with more teaching.

Steps

  1. Resolve session dir (arg, else most recent). Diagram = explicit path arg, else <session>/canvas.excalidraw. If the file is missing or only contains the starter title/legend, tell the user to draw in the workbench (http://localhost:7788/sessions/<dir>, autosaves) or save from excalidraw.com to that path, and stop.
  2. Read prompt.md, interviewer.md, notes.md (if the user filled it), rubric/rubric.md.
  3. Run bun scripts/read-excalidraw.mjs <diagram> and read the summary. If it looks mis-parsed (many <unlabelled> or ? endpoints), also run with --json and reason from coordinates. Never guess at what an unlabelled box "probably" is — call it out.
  4. Reconstruct the design from the diagram + notes: components, read path, write path, sync/async, storage choices, partitioning, caching, failure handling. State explicitly what is inferable from the artefact vs. absent. In a real interview, absent from the whiteboard ≈ absent unless spoken.
  5. Compare against interviewer.md's crux and expected deep dives.
  6. Write <session>/feedback.md:
# Critique — <title> (<date>)
Diagram: <path> · Notes: yes/no

## What I see (neutral reconstruction, 5–10 bullets)
## Diagram hygiene  (each rubric diagram check: ✅/⚠️/❌ + fix)
## Design review
### Meets the requirements? (walk read path & write path; name any request that can't be served)
### Scale & bottlenecks (use the scenario's numbers)
### Failure & consistency
### The crux — found / partially / missed, and why it matters here
## Rubric scores (only dimensions assessable from a diagram+notes: 3,4,6,7, and 10-diagram-legibility; others "n/a — needs a live session")
## Three highest-leverage changes (concrete: "add X between A and B labelled Y because Z")
## Questions an interviewer would ask next (5, escalating)
  1. Append the progress.md row (mode = async). Offer /solution for a reference diagram, and /mock on the same session to practise defending it live.

Tone

Direct, specific, senior-peer. Praise only what's actually good. Every criticism paired with what a strong answer does instead.

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