SKILLEMALL.ai

BF vibe-coding-learning

Generate structured learning notes from AI coding sessions. Invoke when user completes a coding task with AI and asks to summarize learning, explain code, extract knowledge points, review previous notes, or check learning progress. Also trigger on Chinese phrases: "总结今天学的", "帮我整理学习笔记", "帮我复习", "这段代码讲一下", "我学了多少了", "学习进度怎么样", "准备面试", "模拟面试", "帮我讲一下这段代码", "今天学了什么", "帮我记一下", "这段代码我不太懂"

ClawHub Agent Skills author: lyqqqq66666 v0.1.0 MIT-0 2 files body ≈ 6 219 tokens Open the sourceclawhub.ai analyzed 2 d ago

Generate structured learning notes from AI coding sessions.

As a process F 69/100 · Will not run — References files that are not bundled: references/vibe-coding-origin.md, references/mode-routing.md, templates/daily-learning-note.md

GeneratorSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
B
88/100
safety, quality, tests
Safety 60%
100
Quality 40%
69
Run on models
none yet
Process rating
F
69/100
Will not run
References files that are not bundled: references/vibe-coding-origin.md, references/mode-routing.md, templates/daily-learning-note.md
Tools and files w 18
0
Result and completion w 14
60
Inputs and preconditions w 11
70
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6219 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/vibe-coding-origin.md
  • warning missing-ref reference to a missing file: references/mode-routing.md
  • warning missing-ref reference to a missing file: templates/daily-learning-note.md
  • warning missing-ref reference to a missing file: references/feynman-assessment.md
  • warning missing-ref reference to a missing file: references/connection-review.md
  • warning missing-ref reference to a missing file: references/inbox-triage.md
  • warning missing-ref reference to a missing file: references/weekly-synthesis.md
  • warning missing-ref reference to a missing file: references/health-check.md
  • warning missing-ref reference to a missing file: references/output-routing.md

Process rating: all ten parameters 69/100

Will not run. References files that are not bundled: references/vibe-coding-origin.md, references/mode-routing.md, templates/daily-learning-note.md
  • 0Tools and files. 9 referenced file(s) missing: references/vibe-coding-origin.md, references/mode-routing.md, templates/daily-learning-note.md
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6219 tokens
  • 85Steps. 234 steps, 1 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 14 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • -226 emoji in the instructions: noise for the model
  • +2Single-language instructions
  • +5Description quotes 8 example trigger phrases
  • +3Description length 385: enough signal without eating the budget
  • +4Structure: 63 headings
  • +3Step-by-step instructions: 234 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
This skill is mostly a learning-notes assistant, but it can automatically scan project content, read prior conversation/note data, write many note files, and run a local script without a clear confirmation step.
LLM: suspicious (medium) · 22 Jun 2026