SKILLEMALL.ai
GitHub ↗ RU Sign in

CD pi-agent

Builds with and operates Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings/environment variables, creating Pi skills/extensions/packages/themes/prompt templates, embedding Pi through the SDK, integrating over RPC or JSON event streams, parsing sessions, running local models through the llama.cpp router, developing custom Pi providers and TUI components, or using ecosystem packages such as pi-subagents (delegation/orchestration), pi-mcp-adapter (MCP servers), pi-interview (interactive forms), and pi-web-access (web search, fetching, video understanding).

Not recommendedcritical or high security findings
K-Dense-AI/claude-scientific-skills Agent Skills author: K-Dense-AI MIT 36 files body ≈ 1 855 tokens Open the sourcegithub.com↗ analyzed 12 h ago

Builds with and operates Pi, the minimal terminal coding harness.

As a process D 46/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions

GeneratorAI and agentstype 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
C
78/100
safety, quality, tests
Safety 60%
72
Quality 40%
86
Run on models
none yet
Process rating
D
46/100
Unfinished process
Steps w 15
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

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.

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. 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.
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 · 3

  • high Dangerous commands cmd-pipe-to-shell references/overview.md:28
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://pi.dev/install.sh | sh
Medium and low: 2
  • medium Exfiltration intent-browser-credential-store references/pi-web-access.md:79
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    "browserCookies": { "browser": "chrome", "profile": "Default" },
    quoted
  • medium Exfiltration intent-browser-credential-store references/pi-web-access.md:104
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    Browser cookies require explicit opt-in (`allowBrowserCookies` or `PI_ALLOW_BROWSER_COOKIES=1`). Use `browserCookies.browser` / `.profile`; the old top-level `chromeProfile` is rejected. Presets inclu
    quoted

Files scanned: 36. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 46/100

  • 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
  • 30Running it twice. 10 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1855 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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)
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 611: enough signal without eating the budget
  • +4Structure: 7 headings
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (35 of 35)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.