BC skill-discovery
Automatically discover, search, and install skills from ClawHub — the public skill registry for OpenClaw — when no locally installed skill can fulfill the user's request. Acts as a "skill gap filler": when the agent encounters a task it cannot handle with existing skills or built-in tools, it searches ClawHub for a matching skill, presents options to the user, and installs their choice with one command. Use when: (1) the user asks for a capability that no installed skill can fulfill, (2) the user explicitly says "find a skill", "search for a skill", "is there a skill for X", "install a skill from ClawHub", or "search ClawHub", (3) the agent determines that a specialized ClawHub skill would handle the task better than general-purpose reasoning or existing tools, (4) the user asks "what skills are available for X" or "can OpenClaw do X". Triggers on phrases like: "find a skill", "search skills", "install a skill", "search ClawHub", "is there a plugin for", "can you do X", "I need a tool for", "有没有能做X的技能", "帮我找个技能", "搜一下技能", "装个技能". Also activates when no available_skills entry matches the user's intent and the task is clearly skill-shaped (domain-specific workflow, specialized integration, or multi-step procedure).
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
The same skill appears in 1 more place: ClawHub
How to improve
- Shorten the description to 1024 characters.
- 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
- error
description-longdescription is 1233 chars, limit 1024
Process rating: all ten parameters 61/100
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-discovery) differs from the folder (clawhub-skill-finder)
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100Execution cost. Instruction body is 515 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 1232: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 17 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.