CB trip-planner
Plan trips and build day-by-day travel itineraries, delivered as one polished, standalone HTML page. Use this skill PROACTIVELY for any travel-planning request — trigger on "帮我规划行程 / 旅游攻略 / X日游 / 安排去XX玩 / 做旅行计划 / 行程安排 / 帮我排个行程", on "plan a trip / make an itinerary / X-day trip to a city / things to do in a place", and whenever the user gives a destination plus dates or a duration (e.g. "6月去东京玩5天", "国庆想去成都4天", "trip to Kyoto next month", "下周末杭州两日游"). Always gather requirements first (never jump straight to an itinerary), research transport/weather/opening-hours via web search (query-only — it never books or pays), then output ONE self-contained HTML file with an embedded Leaflet + OpenStreetMap map, per-day timeline cards, transport-segment cards, a budget table, a pre-departure checklist, collapsible sections, hierarchical navigation, scroll-memory, and 注意/必订/避雷 callouts. Do NOT use for academic study notes (use study-notes) or generic business reports (use visual-report).
As a process B 77/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 7
-
high Obfuscation
uni-zero-widthreferences/scraping-method.md:181Zero-width / invisible characters (possible hidden text) (10 occurrences)- **坑**：① 用户名里被插入**零宽字符**（`␀`/`␀` 等），需 strip；② 轮播 + 列表有重复，需**去重**；③ 长评论尾部有「全文」按钮，需展开取全文
-
high Obfuscation
uni-bidi-overridereferences/scraping-method.md:186Bidirectional override characters (Trojan Source) (4 occurrences)const strip = s => (s || '').replace(/[␀-␀␀-␀␀␀]/g, '').trim();
Medium and low: 5
-
low Obfuscation
obf-hex-escape-chainexamples/成都4日游行程.html:578Escaped/char-code string obfuscation (security demo / example; test fixture / example file; quoted — discussed, not commanded)<div class="pc-row cheapest"><span class="pc-plat"><a class="btn-link" style="padding:1px 8px" href="https://hotels.ctrip.com/hotels/list?cityId=28&searchWord=…
demofixturequoted -
low Obfuscation
obf-hex-escape-chainexamples/成都4日游行程.html:601Escaped/char-code string obfuscation (security demo / example; test fixture / example file; quoted — discussed, not commanded)<div class="pc-row cheapest"><span class="pc-plat"><a class="btn-link" style="padding:1px 8px" href="https://hotels.ctrip.com/hotels/list?cityId=28&searchWord=…
demofixturequoted -
low Secrets in code
secret-high-entropy-tokenREADME.md:7High-entropy token-like string (may be an id, hash or a credential)[](SKILL.md)
-
low Secrets in code
secret-high-entropy-tokenreferences/scraping-method.md:87High-entropy token-like string (may be an id, hash or a credential)Revi…37n 高德
-
low Secrets in code
secret-high-entropy-tokenreferences/scraping-method.md:88High-entropy token-like string (may be an id, hash or a credential)revi…2hC 携程
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5909 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 77/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 4 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5909 tokens
- 85Steps. 80 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- medium 2 test cases, all positive: not one "should refuse" or "should ask first"
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
- +3Description length 987: 120–800 characters recommended
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 80 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.