SKILLEMALL.ai
GitHub ↗ RU Sign in

DF install

Fresh-machine bootstrap of the ralphy CLI binary. Read .agents/skills/install/references/ralphy-install.md FIRST via the Read tool — every time, no exceptions. USE WHEN the ralphy binary is NOT yet on PATH and the user needs to get it onto their machine — install the standalone binary from GitHub Releases, ensure bun + ffmpeg are present, run the interactive setup wizard, link to the user's checkout of ugc-cli. Once `ralphy --version` works and the project is linked, hand off to ralph-core for in-tree dev tasks. TRIGGER (EN): "install ralphy", "set up from scratch", "fresh machine", "first run", "bootstrap the CLI", "I just cloned the repo", "I don't have ralphy yet", "ralphy not found", "/install". ALSO FIRE if `which ralphy` returns nothing in a session about to use ralphy commands, OR `ralphy status` errors with "Could not locate the ugc-cli project". DO NOT FIRE if ralphy is already installed and the user just wants `ralphy doctor` / env check (that is ralph-core), or wants to install template assets from the companion repo (that is `ralphy assets`). KEYWORDS: install, bootstrap, fresh machine, ralphy binary, GitHub Releases, install.sh, bun, ffmpeg, ralphy setup, setup wizard, PATH, ~/.local/bin/ralphy, link project.

alecs5am/ralphy Agent Skills author: alecs5am 2 files body ≈ 105 tokens Open the sourcegithub.com↗ analyzed 11 h ago

Fresh-machine bootstrap of the ralphy CLI binary.

As a process F 25/100 · No process to follow — References files that are not bundled: ../../../.agents/skills/install/references/ralphy-install.md

IntegrationGitHubAI and agentsCommercetype 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
75/100
safety, quality, tests
Safety 60%
94
Quality 40%
47
Run on models
none yet
Process rating
F
25/100
No process to follow
References files that are not bundled: ../../../.agents/skills/install/references/ralphy-install.md
Tools and files w 18
0
Steps w 15
0
Result and completion w 14
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. Shorten the description to 1024 characters.
  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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Dangerous commands cmd-pipe-to-shell-known-host references/ralphy-install.md:37
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://raw.githubusercontent.com/aleksei-oleinik/ugc-cli/main/install.sh | sh
  • low Dangerous commands cmd-pipe-to-shell-known-host references/ralphy-install.md:28
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    - `bun` missing → run `curl -fsSL https://bun.sh/install | bash` (in current shell so the user keeps running). Source the shell rc afterward.
    quoted

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

Against the Agent Skills spec

  • error description-long description is 1241 chars, limit 1024
  • warning missing-ref reference to a missing file: ../../../.agents/skills/install/references/ralphy-install.md
  • note frontmatter-key unknown frontmatter key "namespace"

Process rating: all ten parameters 25/100

Will not run. References files that are not bundled: ../../../.agents/skills/install/references/ralphy-install.md
  • 0Tools and files. 1 referenced file(s) missing: ../../../.agents/skills/install/references/ralphy-install.md
  • 0Steps. Prose only: no discrete steps
  • 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
  • 20When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 105 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)
  • +3Description length 1241: 120–800 characters recommended
  • +4Structure: 1 headings, hard to scan
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 10 example trigger phrases
  • +4Reference files are cited in the instructions (1 of 1)

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