BC screenpipe
Search screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem. Use when the user asks to recall desktop activity, a meeting, or something seen in another app through Screenpipe.
Promises to search screen and audio history from Screenpipe and save context to claude-mem. Grade B, quality score 79—solid for a reference tool. No critical issues found, but process score of 58 suggests some logic lag. Two files and one script run without broken links. In practice, it lets your AI assistant recall what you did in other apps or said in meetings if Screenpipe recorded it.
Catch: the skill depends on Screenpipe already running and having built up history. Without recordings, it's dead weight. Worth installing if you already run Screenpipe and want Claude to reference it—saves time rehashing context.
Search screen and audio history recorded by Screenpipe and optionally save selected context into claude-mem.
As a process C 58/100 · Has gaps — weak spots: steps, result and completion, inputs and preconditions
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: 2. 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 58/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 929 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
- +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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 223: enough signal without eating the budget
- +4Structure: 4 headings
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 1 скрипт; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
screenpipe.mjs | ничего за пределами своей папки |
16 Oct 2026