BF meta-analysis
Comprehensive R-based meta-analysis skill covering RevMan 5.x + Stata equivalents (metareg/mvmeta) + esc + RVE + Bayesian NMA (Stan/JAGS) + survival meta + TSA + single-group meta + diagnostic meta + systematic review workflow; produces forest plots, funnel plots, heterogeneity (I²), publication bias, subgroup analysis, meta-regression, network meta, for a total of 23 analysis figures. Auto-switches language (defaults to English, switches to Chinese in zh-* environments). All analyses ship reproducible R code. / 基于 R 的全方位 Meta 分析技能，覆盖 RevMan 全部功能 + Stata 等价（metareg/mvmeta）+ esc + RVE + 贝叶斯 NMA（Stan/JAGS）+ 生存 Meta + TSA + 单组率 Meta + 诊断 Meta + 系统评价流程；输出森林图、漏斗图、异质性(I²)、发表偏倚、亚组分析、元回归、网络 Meta等共 23 种分析图形。中英双语自动切换（默认英文/中文环境切中文），所有分析提供可复现 R 代码。
Comprehensive R-based meta-analysis skill covering RevMan 5.x + Stata equivalents (metareg/mvmeta) + esc + RVE + Bayesian NMA (Stan/JAGS) + survival meta +…
As a process F 43/100 · Will not run — References files that are not bundled: assets/icon.svg
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Obfuscation
obf-base64-blobCHANGELOG.md:1152Long base64-looking blob- **R 包清单瘦身**（单一可信源 `docker/r_packages.txt`）：核心 14（metafor/meta/netmeta/bayesmeta/dosresmeta/mada/robumeta/clubSandwich/ggplot2/svglite/forestploter/jsonlite/dplyr/scales）+ 可选 2（ggrepel/robvis）。移除：`es
-
low Obfuscation
obf-base64-blobadapters/bug_report.py:75Long base64-looking blob (detector / deny-list definition)"Bg1n…XQs
detector -
low Obfuscation
obf-base64-blobadapters/coze_token.py:30Long base64-looking blob (quoted — discussed, not commanded)"CBw-…LAc
quoted -
low Obfuscation
obf-base64-blobadapters/coze_token.py:35Long base64-looking blob (quoted — discussed, not commanded)"CBw-…LHQ
quoted -
low Secrets in code
secret-high-entropy-tokenCHANGELOG.md:571High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **主工作流端点切换为 ct-meta2、回退 ct-meta**：`DEFAULT_ENDPOINT=https://ct-m…ite/run`（用户新 token，aud=`5v9H…Xny`）；`FALLBACK_ENDPOINT=https://ct-meta.coze.site/run`（旧端点，保留旧 token，
quoted -
low Secrets in code
secret-high-entropy-tokenCHANGELOG.md:580High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- 模块编译；`get_token_for("ct-meta2")`→aud=`5v9H…Xny`、`get_token_for("ct-meta")`→aud=`oxwS…EjO`（二者不同）；线上探测两端点均 HTTP 200 + `unknown_task`（token 被接受）。quoted
Files scanned: 77. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: assets/icon.svg - note
frontmatter-keyunknown frontmatter key "cn_name" - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "required_commands" - note
frontmatter-keyunknown frontmatter key "invocable" - note
frontmatter-keyunknown frontmatter key "triggers" - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 43/100
- 0Tools and files. 1 referenced file(s) missing: assets/icon.svg
- 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. 16 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3973 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- -213 emoji in the instructions: noise for the model
- -36 of 12 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 746: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (17 of 39)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.