SKILLEMALL.ai
GitHub ↗ RU Sign in

DD skill-manager

打开 SkillDock 本地 GUI，浏览和管理 Codex skills、plugins 与 marketplace 来源；适用于技能库、安装更新、启禁、移除恢复的可视化管理。普通任务只需使用某个 skill 时不触发。

TestAny-io/testany-agent-skills Agent Skills author: TestAny-io MIT 80 files · 45 scripts body ≈ 967 tokens Open the sourcegithub.com↗ analyzed 4 d ago

打开 SkillDock 本地 GUI，浏览和管理 Codex skills、plugins 与 marketplace 来源；适用于技能库、安装更新、启禁、移除恢复的可视化管理。普通任务只需使用某个 skill 时不触发。

As a process D 35/100 · Unfinished process — References files that are not bundled: references/30-native-app.md, references/18-codex-node-runtime.md, references/17-self-update-restart.md

ProcedureSoftware developmentCommercetype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
77/100
safety, quality, tests
Safety 60%
90
Quality 40%
57
Run on models
none yet
Process rating
D
35/100
Unfinished process
References files that are not bundled: references/30-native-app.md, references/18-codex-node-runtime.md, references/17-self-update-restart.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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 Dangerous commands cmd-persistence assets/app/README.md:212
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    启用时注册 `~/Library/LaunchAgents/io.testany.skilldock.update.<实例摘要>.plist`；固定入口、Node/npm/CLI 路径、所选项目与执行状态位于数据目录 `background/`。不写入令牌，不保存临时 SSH agent socket。支持用户已配置的 Git HTTPS/SSH 认证；登录钥匙串或授权不可用时显示原始失败原因，退
    quoted
  • low Secrets in code secret-high-entropy-token assets/app/package-lock.json:55
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…qkQ+BMQq…Lqg==",
    detector
  • low Secrets in code secret-high-entropy-token assets/app/package-lock.json:89
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Lkx+esve…s1Q==",
    detector
  • low Secrets in code secret-high-entropy-token assets/app/package-lock.json:106
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…7xp+Ksxi…Vkw==",
    detector
  • low Secrets in code secret-high-entropy-token assets/app/package-lock.json:310
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…TZM+N3P0…O90+1bZv…F8A/HQ==",
    detector
  • low Secrets in code secret-high-entropy-token assets/app/package-lock.json:412
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…mVs+YKyp…f7g==",
    detector

Files scanned: 78. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: references/30-native-app.md
  • warning missing-ref reference to a missing file: references/18-codex-node-runtime.md
  • warning missing-ref reference to a missing file: references/17-self-update-restart.md
  • warning missing-ref reference to a missing file: references/24-background-updates.md
  • warning missing-ref reference to a missing file: references/19-seed-feedback.md
  • warning missing-ref reference to a missing file: references/03-engineering-design.md
  • warning missing-ref reference to a missing file: references/04-test-plan.md
  • warning missing-ref reference to a missing file: references/01-product-requirements.md
  • warning missing-ref reference to a missing file: references/02-interface-design.md
  • warning missing-ref reference to a missing file: references/07-uat-round1-changes.md
  • warning missing-ref reference to a missing file: references/14-uat-round3-delivery.md
  • warning missing-ref reference to a missing file: LICENSE
  • warning missing-ref reference to a missing file: scripts/launch.sh

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/30-native-app.md, references/18-codex-node-runtime.md, references/17-self-update-restart.md
  • 0Tools and files. 13 referenced file(s) missing: references/30-native-app.md, references/18-codex-node-runtime.md, references/17-self-update-restart.md
  • 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
  • 100Steps. 4 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 967 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)
  • +3Description length 112: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 7 headings
  • +3Step-by-step instructions: 4 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.