SKILLEMALL.ai
GitHub ↗ RU Sign in

CB nex-changelog

Professional changelog and release notes generator for client-facing software releases and updates. Automatically parse git commit history using conventional commit format (feat:, fix:, security:, etc.) and categorize changes into changelog entries (ADDED, CHANGED, FIXED, REMOVED, SECURITY, DEPRECATED, PERFORMANCE). Organize changes by target audience (internal team, client-facing, public) so you can create separate release notes for different stakeholders. Support multiple output formats including standard Keep a Changelog markdown format, simple text summaries, HTML reports, and JSON structured data. Generate professional client-facing email announcements highlighting new features and improvements while hiding technical details and internal refactoring. Create compact Telegram-friendly release announcements with emoji indicators for easy social media sharing. Track releases with semantic versioning, generate release summaries, and manage unreleased entries. Import git commits automatically from project repositories or manually add changelog entries for documentation or non-code releases. Perfect for web agencies, software companies, and development teams who need to communicate changes professionally with clients and stakeholders.

ClawHub Agent Skills author: Nex AI v1.0.0 MIT-0 11 files · 1 script body ≈ 2 223 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting

GeneratorTelegramWriting and documentsSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
72/100
safety, quality, tests
Safety 60%
80
Quality 40%
60
Run on models
none yet
Process rating
B
75/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
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. Shorten the description to 1024 characters.
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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Dangerous commands cmd-shell-rc setup.sh:116
    Writes to a shell startup file
    echo "  echo 'export PATH=\"\$HOME/.local/bin:\$PATH\"' >> ~/.bashrc"
  • medium Dangerous commands cmd-shell-rc setup.sh:117
    Writes to a shell startup file
    echo "  source ~/.bashrc"
  • medium Dangerous commands cmd-shell-rc setup.sh:119
    Writes to a shell startup file
    echo "  echo 'export PATH=\"\$HOME/.local/bin:\$PATH\"' >> ~/.zshrc"
  • medium Dangerous commands cmd-shell-rc setup.sh:120
    Writes to a shell startup file
    echo "  source ~/.zshrc"

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1252 chars, limit 1024

Process rating: all ten parameters 75/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 25 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 100Tools and files. No external tools needed
  • 100Steps. 40 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2223 tokens
  • low 10 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1252: 120–800 characters recommended
  • +2Single-language instructions
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 40 items
  • +3Output format is stated explicitly
  • +4Has examples (14 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.

External checks

ClawHub: clean
This is a local changelog generator, but users should review client or public drafts because audience filtering is imperfect.
LLM: benign (high) · VirusTotal: · 29 May 2026