AF ros1-noetic-general
General bilingual ROS1 Noetic skill for ROS questions and ROS project operations across robot dogs, mobile robots, manipulators, perception pipelines, simulation, and OpenClaw integrations. Trigger whenever the user mentions ROS, ROS1, Noetic, catkin, roslaunch, rosrun, roscore, rostopic, rosservice, rospy, roscpp, tf, tf2, rosbag, launch files, workspace, package.xml, CMakeLists.txt, rosbridge, or asks in Chinese or English to start/build/check/debug/stop a ROS project or robot, such as "启动 ROS", "启动机器狗", "编译 ROS 项目", "检查 catkin 工作区", "run roslaunch", "build this ROS package", or "debug this ROS node". For general ROS knowledge questions, provide broad ROS guidance first; for requests involving local files, local workspaces, commands, builds, launch/run actions, monitoring, health checks, or stopping runtime targets, use this skill's local scripts and workflows. If the user explicitly says "使用 rosskill", "用 ros skill", or "use rosskill", treat that as a strong signal to use this skill.
As a process F 45/100 · Will not run — References files that are not bundled: scripts/..., references/...
How to improve
- The text references files that are not there: add them or drop the references.
- 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 Dangerous commands
cmd-background-processscripts/ros1_start_target.sh:259Starts a background / autostarted processnohup "$launcher_file" >"$log_file" 2>&1 < /dev/null &
Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/... - warning
missing-refreference to a missing file: references/...
Process rating: all ten parameters 45/100
- 0Tools and files. 2 referenced file(s) missing: scripts/..., references/...
- 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. 2 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 8 branches
- 85Steps. 76 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2006 tokens
- 100Progress reporting. Reports progress
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1001: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 11 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 15 headings
- +3Step-by-step instructions: 76 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.