SKILLEMALL.ai

AF readme-writer

Expert README writing skill for open source projects. Use this skill whenever the user wants to write, improve, or review a README for any open source repository. Triggers include: "write a README", "help me with my README", "README template", "improve my README", "review my README", "open source documentation", "GitHub README", "project documentation". Also use when the user is creating a new project and needs documentation, or asks "how do I document my project", "what should my README include", or "make my README better". This skill covers tool-type software, AI/ML projects, and code frameworks based on patterns distilled from 20 high-star GitHub repositories.

ClawHub Agent Skills author: Pu Cao v1.0.0 MIT-0 5 files body ≈ 1 769 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 40/100 · Will not run — References files that are not bundled: CONTRIBUTING.md, LICENSE

GeneratorGitHubWriting and documentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
95
Quality 40%
84
Run on models
none yet
Process rating
F
40/100
Will not run
References files that are not bundled: CONTRIBUTING.md, LICENSE
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. 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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:131
    Downloads and executes remote code from an unrecognised host (pipe to shell) (security demo / example)
    curl -fsSL https://get.example.com | sh  # Universal: curl-pipe-sh
    demo

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: CONTRIBUTING.md
  • warning missing-ref reference to a missing file: LICENSE

Process rating: all ten parameters 40/100

Will not run. References files that are not bundled: CONTRIBUTING.md, LICENSE
  • 0Tools and files. 2 referenced file(s) missing: CONTRIBUTING.md, LICENSE
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (readme-writer) differs from the folder (readme-writer-skill)
  • 55Failures and branches. 1 branches
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 46 steps, 1 vague phrases
  • 100Execution cost. Instruction body is 1769 tokens
  • 100Running it twice. No mutating operations

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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 11 example trigger phrases
  • +3Description length 671: enough signal without eating the budget
  • +4Structure: 17 headings
  • +3Step-by-step instructions: 46 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

External checks

ClawHub: clean
This skill is a README-writing aid made only of Markdown guidance and reference files, with no executable code or hidden access.
LLM: benign (high) · VirusTotal: · 29 May 2026