SKILLEMALL.ai
GitHub ↗ RU Sign in

DC native

Implementing production iOS/Android/macOS native features (SwiftUI, Compose) and iterating a screen against a reference design. Not for cross-platform RN/Flutter (Port) or web (Artisan).

Not recommendedcritical or high security findings · low grade D
simota/agent-skills Agent Skills author: simota 35 files body ≈ 5 860 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Implementing production iOS/Android/macOS native features (SwiftUI, Compose) and iterating a screen against a reference design.

As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting

GeneratorSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
D
48/100
safety, quality, tests
Safety 60%
31
Quality 40%
73
Run on models
none yet
Process rating
C
59/100
Has gaps
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

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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

  • high Dangerous commands cmd-persistence reference/macos-modern-stack.md:199
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    | Manual `launchctl` install of LaunchAgents/LaunchDaemons | `SMAppService.agent`/`.daemon` registration |
  • high Dangerous commands cmd-persistence reference/xpc-helpers.md:147
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    │   ├── LaunchAgents/com.example.myapp.agent.plist
  • high Dangerous commands cmd-persistence reference/xpc-helpers.md:148
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    │   └── LaunchDaemons/com.example.myapp.daemon.plist
Medium and low: 3
  • medium Dangerous commands cmd-persistence reference/xpc-helpers.md:117
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    `SMAppService` (macOS 13+) replaces `SMJobBless` and manual `launchctl load` for registering background components. All four registration types are managed through one API surface.
    quoted
  • medium Dangerous commands cmd-persistence reference/xpc-helpers.md:138
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    ### 3.1 Bundled-Plist Layout (Replaces `SMJobBless`/`launchctl load`)
    quoted
  • medium Dangerous commands cmd-persistence reference/xpc-helpers.md:152
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    `SMAppService` reads the plist from this in-bundle location at `register()` time and handles the system-side install/move itself — the app never manually copies plists into `/Library/Launch*` or shell
    quoted

Files scanned: 35. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5860 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 90, 127): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 59/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 18 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 5860 tokens
  • 100Steps. 72 steps
  • 100Consistency. Name and required fields are in place
  • low 19 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
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 186: enough signal without eating the budget
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 72 items
  • +3Output format is stated explicitly
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (34 of 34)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.