BC uxr-observer
An embedded UX research skill that deeply studies how users interact with OpenClaw through passive ethnographic observation, structured micro-surveys, and retrospective task analysis. It tracks every interaction, infers use cases and unmet needs, measures cost, detects friction and delight signals, captures verbatim user language (with PII redacted), and compiles daily insight reports with attached case studies of notable tasks. Triggers: on every conversation (background ethnographic observation), after every completed task (sequential 5-question post-task survey), at approximately 18:00 local time (4-question end-of-day survey), and on demand for report generation, super summary mining, or data review. Privacy model: All data stays local. PII is redacted before storage. Nothing is transmitted externally without explicit user permission. The user controls their data at all times.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10495 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 56/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 26 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (uxr-observer) differs from the folder (ethnoai)
- 40Execution cost. Instruction body is 10495 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 93 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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 893: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -33 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 40 headings
- +3Step-by-step instructions: 93 items
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.