CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

firstdata

Find official portals, APIs, and download paths for authoritative primary data sources (governments, international organizations, research institutions, etc.). Use when users need to know "where to find this data from an official source", "which source is more authoritative", or "how to cite primary data". Covers the live FirstData catalog with authority comparison and site navigation guidance.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/firstdata/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Operationally solid content: concrete setup commands, well-documented tool limitations, and a clean reference split. Its main weakness is token efficiency — two sections serve the project's maintainers rather than the agent invoking the skill, and the core tools lack example invocations.

Suggestions

Remove the "Description Quality Guidelines" and "Community" sections — they guide the project's own developers (MCP description authoring, starring/filing issues) and consume context without helping an agent use the skill.

Tighten "What FirstData Is" to a terse factual overview, dropping marketing phrasing like "purpose-built, authoritative collection" and the catalog coverage list that get_status returns live anyway.

Add concrete example invocations (arguments and a representative response) for search_source, get_source, and ask_agent to close the actionability gap, mirroring the existing report_feedback examples.

DimensionReasoningScore

Conciseness

The MCP tool reference is dense and useful, but the "Description Quality Guidelines" section (a 6-dimension authoring checklist for MCP tool descriptions) and the promotional "Community" section are developer-facing padding, and "What FirstData Is" carries marketing phrasing ("purpose-built, authoritative collection") that adds tokens without adding operational value.

3 / 5

Actionability

Provides copy-paste-ready setup (the mcporter command and full MCP JSON config), explicit parameter ranges/defaults, and worked feedback examples; the gap is that search_source, get_source, and ask_agent lack example invocations with actual arguments.

4 / 5

Workflow Clarity

The setup-to-use sequence is present with an explicit validation checkpoint ("call get_status first to verify the MCP connection") and documented error paths (quota check via the token verify API, per-item error fields for invalid IDs), but steps are not consolidated into one numbered flow with error recovery.

4 / 5

Progressive Disclosure

One clearly signaled, one-level-deep reference (references/firstdata-register.md, which exists and holds the registration detail) appropriately splits setup content; the ~75-line MCP Tools Reference is borderline inline-heavy but is the skill's core operational content.

4 / 5

Total

15

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, concrete capabilities, and an explicit "Use when..." clause with realistic user phrasings. It sits just below the top level on specificity and trigger coverage because a few natural terms and core capabilities are not named.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Find official portals, APIs, and download paths", "authority comparison", "site navigation guidance" — but coverage is not comprehensive; core capabilities like keyword search and per-source access guides are absent.

4 / 5

Completeness

Clearly answers both what ("Find official portals, APIs, and download paths for authoritative primary data sources...") and when (an explicit "Use when users need to know..." clause with concrete trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user-voiced trigger phrases ("where to find this data from an official source", "which source is more authoritative", "how to cite primary data") plus domain nouns, but misses common variations such as "official statistics" or "government data".

4 / 5

Distinctiveness Conflict Risk

Clear niche (locating authoritative primary data sources) with mostly distinct triggers; minor overlap risk from "how to cite primary data" pulling in citation-formatting skills.

4 / 5

Total

17

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

MLT-OSS/FirstData

Path

skills/firstdata/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.