SKILLEMALL.ai
GitHub ↗ RU Sign in

DD database-lookup

Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. Use when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.

synthetic-sciences/OpenScience Agent Skills author: synthetic-sciences Apache-2.0 80 files body ≈ 6 719 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Query documented public database APIs with explicit endpoints, filters, pagination, and provenance.

As a process D 49/100 · Unfinished process — References files that are not bundled: references/<database-name>.md, references/zinc.md, references/worldbank.md

ProcedureData and analyticstype 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
68/100
safety, quality, tests
Safety 60%
67
Quality 40%
70
Run on models
none yet
Process rating
D
49/100
Unfinished process
References files that are not bundled: references/<database-name>.md, references/zinc.md, references/worldbank.md
Tools and files w 18
0
Inputs and preconditions w 11
0
When it triggers w 12
20
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  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 · 9

✓ No critical or high findings

Medium and low: 9
  • medium Exfiltration net-credential-use references/noaa.md:47
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Token: $NOAA_TOKEN" \
  • medium Exfiltration net-credential-use references/noaa.md:90
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Token: $NOAA_TOKEN" \
  • medium Exfiltration net-credential-use references/noaa.md:114
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Token: $NOAA_TOKEN" \
  • medium Exfiltration net-credential-use references/noaa.md:144
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Token: $NOAA_TOKEN" \
  • medium Exfiltration net-credential-use references/noaa.md:179
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Token: $NOAA_TOKEN" \
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Bash
  • low Secrets in code secret-password-literal references/brenda.md:54
    Hard-coded password / key literal (may be an example) (placeholder value)
    password = hash…256("your_password".encode()).hexdigest()
    placeholder
  • low Secrets in code secret-high-entropy-token references/datacommons.md:142
    High-entropy token-like string (may be an id, hash or a credential)
    | Coun…ths | Persons in poverty  |
  • low Secrets in code secret-password-literal references/nasa.md:37
    Hard-coded password / key literal (may be an example)
    https://api.nasa.gov/planetary/apod?api_key=…&date=…

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6719 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/<database-name>.md
  • warning missing-ref reference to a missing file: references/zinc.md
  • warning missing-ref reference to a missing file: references/worldbank.md
  • warning missing-ref reference to a missing file: references/who.md

Process rating: all ten parameters 49/100

Will not run. References files that are not bundled: references/<database-name>.md, references/zinc.md, references/worldbank.md
  • 0Tools and files. 4 referenced file(s) missing: references/<database-name>.md, references/zinc.md, references/worldbank.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 6719 tokens
  • 85Steps. 49 steps, 2 vague phrases
  • 100Failures and branches. 4 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

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)
  • +2Single-language instructions
  • +3Description length 271: enough signal without eating the budget
  • +4Structure: 29 headings
  • +3Step-by-step instructions: 49 items
  • +3Output format is stated explicitly
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (79 of 79)
  • +1License stated

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