SKILLEMALL.ai
GitHub ↗ RU Sign in

CF natural-language-planner

Natural language task and project management. Use when the user talks about things they need to do, projects they're working on, tasks, deadlines, or asks for a project overview / dashboard. Captures tasks from conversation, organises them into projects, tracks progress, and serves a local Kanban dashboard.

modbender/skill-library-mcp Agent Skills author: modbender MIT 25 files body ≈ 8 822 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Natural language task and project management.

As a process F 48/100 · Will not run — References files that are not bundled: {rel_path}, templates/dashboard/*.html, scripts/*.py

ProcedureData and analyticstype 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
66/100
safety, quality, tests
Safety 60%
78
Quality 40%
47
Run on models
none yet
Process rating
F
48/100
Will not run
References files that are not bundled: {rel_path}, templates/dashboard/*.html, scripts/*.py
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Dangerous commands cmd-privilege README.md:126
    Privilege escalation / world-writable permissions
    sudo tee /etc/systemd/system/nlplanner-dashboard.service << 'EOF'
  • medium Exfiltration exfil-webhook-url scripts/tunnel.py:89
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    'https://random-name.trycloudflare.com'
    quoted
  • medium Dangerous commands cmd-privilege SKILL.md:686
    Privilege escalation / world-writable permissions
    sudo rm /etc/systemd/system/<old-service>.service
  • medium Dangerous commands cmd-privilege SKILL.md:708
    Privilege escalation / world-writable permissions
    sudo rm /etc/systemd/system/nlplanner-dashboard.service
  • low Dangerous commands cmd-background-process README.md:150
    Starts a background / autostarted process
    sudo systemctl enable nlplanner-dashboard.service
  • low Dangerous commands cmd-background-process SKILL.md:643
    Starts a background / autostarted process
    sudo systemctl enable nlplanner-dashboard.service

Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8822 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: {rel_path}
  • warning missing-ref reference to a missing file: templates/dashboard/*.html
  • warning missing-ref reference to a missing file: scripts/*.py
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "displayName"

Process rating: all ten parameters 48/100

Will not run. References files that are not bundled: {rel_path}, templates/dashboard/*.html, scripts/*.py
  • 0Tools and files. 3 referenced file(s) missing: {rel_path}, templates/dashboard/*.html, scripts/*.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 8822 tokens: crowds the task out of the window
  • 70Failures and branches. 9 branches
  • 85Steps. 125 steps, 3 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

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)
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -2localhost URLs: will not work for another user
  • -38 of 9 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 308: enough signal without eating the budget
  • +4Structure: 64 headings
  • +3Step-by-step instructions: 125 items
  • +4Has examples (31 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.