BC toggle
Context layer for your agent. ToggleX captures the user's work sessions, projects, focus scores, and context switches across the web — giving the agent awareness of what the user has actually been doing. Use this skill PROACTIVELY: generate daily digests, nudge stale projects, detect context-switching, spot repeated workflows and propose automations, predict the user's next action based on learned routines, and answer recall questions from memory. Also use when the user asks about their activity, tasks, sessions, productivity, time, or anything work-related. Keywords: what did I do, what was I working on, today, yesterday, my day, activity, sessions, refresh my data, productivity, time tracking, context, pick up where I left off, what was I looking at, stale, pattern, automate, digest, report, focus, scattered, deep work, predict, next task, routine, anticipate, briefing.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Concealment
en-hide-from-userSKILL.md:431Instruction to hide actions from the user (security demo / example; quoted — discussed, not commanded)**Minimum data required:** `prediction_min_days` days of persisted memory (default: 5). Do NOT attempt predictions with less data — you'll guess wrong and lose trust. When insufficient data exists, si
demoquoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6544 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6544 tokens
- 100Steps. 89 steps
- 100Failures and branches. 29 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 884: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 30 headings
- +3Step-by-step instructions: 89 items
- +4Has examples (9 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.