FF 赢得目标
在目标平台（goal_web）发布高质量内容的完整技能流程设计。用于：读取任务json与goal_prompt，拆解任务、执行任务引擎、开发与自检、结果回写与评分回写。触发词：修改目标、赢得目标、触发目标实现、触发{网站名称}任务实现。
As a process F 29/100 · Will not run — References files that are not bundled: references/goal_prompt.md, references/prompts/goal_prompt_{goal_web}_v{new_seq}.md, references/prompts/retro_prompt_{goal_web}_v{new_seq}.md
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 4
-
high Dangerous commands
cmd-persistencereferences/cron-design-reference.md:157Persistence mechanism (cron / launchd / scheduled task / autorun registry)~/Library/LaunchAgents/<LAUNCH_AGENT_NAME>.plist
-
high Dangerous commands
cmd-persistencereferences/cron-design-reference.md:216Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/<LAUNCH_AGENT_NAME>.plist
-
high Dangerous commands
cmd-persistencereferences/cron-design-reference.md:219Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl unload ~/Library/LaunchAgents/<LAUNCH_AGENT_NAME>.plist
-
high Dangerous commands
cmd-persistencereferences/cron-design-reference.md:275Persistence mechanism (cron / launchd / scheduled task / autorun registry)7. launchctl load + launchctl start 验证
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 8048 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/goal_prompt.md - warning
missing-refreference to a missing file: references/prompts/goal_prompt_{goal_web}_v{new_seq}.md - warning
missing-refreference to a missing file: references/prompts/retro_prompt_{goal_web}_v{new_seq}.md - warning
missing-refreference to a missing file: references/prompts/{文件名}
Process rating: all ten parameters 29/100
- 0Tools and files. 4 referenced file(s) missing: references/goal_prompt.md, references/prompts/goal_prompt_{goal_web}_v{new_seq}.md, references/prompts/retro_prompt_{goal_web}_v{new_seq}.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (赢得目标) differs from the folder (goal-achiever)
- 40Execution cost. Instruction body is 8048 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 274 steps
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 118: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 55 headings
- +3Step-by-step instructions: 274 items
- +4Has examples (24 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 46.