Write a hello file to the workspace output directory.
44
45%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/hello/SKILL.mdQuality
Discovery
17%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is extremely minimal and appears to describe a trivial or demo skill. It lacks a 'Use when...' clause, contains no natural trigger terms a user would employ, and the single action described ('write a hello file') is too narrow and unclear to be useful for skill selection among multiple options.
Suggestions
Add a 'Use when...' clause that specifies the conditions under which Claude should select this skill, e.g., 'Use when the user asks to test workspace output or create a sample file.'
Include natural trigger terms users might say, such as 'test file', 'sample output', 'hello world', or 'workspace test'.
Clarify what a 'hello file' actually is (e.g., a hello world text file, a greeting template) to improve specificity and help distinguish this skill from other file-writing skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a specific action ('write a hello file') and a specific location ('workspace output directory'), but describes only a single narrow action without listing multiple concrete capabilities. | 2 / 3 |
Completeness | It partially answers 'what' (write a hello file) but has no 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill, which caps completeness at a maximum of 2, and the 'what' itself is also quite weak. | 1 / 3 |
Trigger Term Quality | The description lacks natural keywords a user would say. 'Hello file' and 'workspace output directory' are not terms users would naturally use in requests; there are no common variations or recognizable trigger terms. | 1 / 3 |
Distinctiveness Conflict Risk | The description is narrow enough ('hello file' to 'workspace output directory') that it's unlikely to conflict with many other skills, but the vague nature of 'hello file' could cause confusion about whether this is a test/demo skill or something more specific. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a minimal, well-structured skill for a very simple task. Its brevity is appropriate, but it lacks verification steps (confirming file creation/content) and the referenced script `scripts/hello.sh` is not provided in the bundle, making the command's executability uncertain. Adding a brief validation step and ensuring the script exists would strengthen it.
Suggestions
Add a brief validation step after the command, e.g., `cat out/hello.txt` to confirm expected output.
Either include the `scripts/hello.sh` script in the bundle or inline the command (e.g., `echo 'Hello' > out/hello.txt`) so the skill is self-contained and executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is very lean—no unnecessary explanations, no padding. Every line serves a purpose for a simple task. | 3 / 3 |
Actionability | It provides a concrete command to run, but there's no indication of what the script does, what the expected file content is, or whether the script actually exists. Without the bundle providing `scripts/hello.sh`, the command isn't truly executable or verifiable. | 2 / 3 |
Workflow Clarity | For a simple single-step task this is mostly adequate, but there's no validation step (e.g., confirming the file was created or checking its contents), and no mention of prerequisites like ensuring the `out/` directory exists or that the script is executable. | 2 / 3 |
Progressive Disclosure | For a simple skill under 50 lines with a single task, the content is well-organized into clear sections (Overview, Command, Output Files) with no need for external references. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
9f4b734
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.