AC skill-installer
Install or remove third-party openscience skills from a public git repository. Use when the user says "add this skill <url>", "install skill <url>", or "remove skill <namespace>". The skill runs locally via `openscience skill add|list|remove`, fetches the repo, runs a 6-layer safety gate (regex + server-side Haiku classifier), prompts the user to confirm, then writes the skills to ~/.openscience/installed-skills/ and uploads to the dashboard for cross-machine sync.
Install or remove third-party openscience skills from a public git repository.
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 1. 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 63/100
- 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
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 23 steps
- 100When it triggers. States when to use and 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 989 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (23 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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 469: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.