BF opencode-api
透過 HTTP API 呼叫 OpenCode Server 進行 code review、程式碼分析與編碼任務。 涵蓋：Agents（4種模式+自訂代理）、Custom Tools（TypeScript）、Formatters（ruff/biome）、 Skills（載入技能）、SDK（完整 API，含結構化輸出/noReply/事件監聽）、Plugins（事件鉤子）、 Config（完整 schema）、Permissions（細粒度規則）、Commands（自訂指令）、Providers（MCP/LM Studio/Ollama）、 MCP（Model Context Protocol）、LSP（語言伺服器整合）、Server（HTTP 部署）。 適用於 OpenClaw 派工給 OpenCode 執行的場景。
As a process F 31/100 · Will not run — weak spots: steps, result and completion, when it triggers
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 Broad scope
meta-dynamic-shellreferences/commands.md:71Shell command executed automatically when the skill loads (Claude Code !`cmd` preamble)!`npm test`
Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 364 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "clawhub" - note
frontmatter-keyunknown frontmatter key "department" - note
frontmatter-keyunknown frontmatter key "languages" - note
frontmatter-keyunknown frontmatter key "models"
Process rating: all ten parameters 31/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1414 tokens
- 100Running it twice. No mutating operations
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +3Description length 363: enough signal without eating the budget
- +4Structure: 15 headings
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (12 of 18)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.