CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

imf-data

Retrieve and analyze IMF macroeconomic series, forecasts, and reserve-composition data.

58

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./resources/bundled-skills/imf-data/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is an efficient, well-structured instruction-only skill with a clear sequence and meaningful verification gates, appropriate for its small scope. Its main weakness is actionability: it never names actual IMF endpoints, databases, or API identifiers, leaving the model to discover them at runtime.

Suggestions

Name the concrete IMF access points (e.g., the SDMX/JSON RESTful API, WEO, IFS, and COFER databases, and the DataMapper portal) in the workflow or tool routing table.

Add one short worked example showing an actual request pattern for a common case (e.g., fetching WEO GDP forecasts for a country) so guidance is copy-paste executable.

Turn the completion gates into explicit validate-then-fix steps (e.g., what to do when units or country coverage do not match the request) to add a feedback loop.

DimensionReasoningScore

Conciseness

The ~30-line body is lean with no concept explanations or padding; every section (tool routing, workflow, gates, boundaries, delivery) earns its place, with only a one-line Purpose restating the description, matching the anchor for fully lean and efficient content.

5 / 5

Actionability

Guidance such as "Locate the official public IMF endpoint or release page" remains high-level: no concrete endpoints, API names (e.g., SDMX/JSON RESTful API), database identifiers (WEO, IFS, COFER), or worked examples, so concrete guidance is present but incomplete, fitting anchor 3 rather than the mostly-executable anchor 4.

3 / 5

Workflow Clarity

A clear five-step sequence is paired with explicit completion gates (units, scale, fiscal basis, revision handling, aggregate provenance), providing most checkpoints; it falls short of anchor 5 only because there is no validate-fix-retry feedback loop, and this read-only retrieval skill triggers no destructive-operation cap.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no external bundle files; the well-organized sections (Purpose, Tool routing, Workflow, Completion gates, Boundaries, Delivery) satisfy the rubric's simple-skill exception allowing a score of 5.

5 / 5

Total

17

/

20

Passed

Description

53%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.

The description is concise, specific about the domain, and uses appropriate third-person voice, but it omits any explicit "Use when..." trigger guidance and lacks common user-facing synonyms such as WEO or COFER. Adding a trigger clause and one or two more concrete actions would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks about IMF data, World Economic Outlook (WEO) forecasts, or COFER reserve composition."

Include natural synonyms users say, such as "World Economic Outlook", "WEO", "IFS", and "COFER", to improve trigger term coverage.

Split "analyze" into one or two more concrete actions (e.g., "compare countries, chart indicators, separate observed vs. forecast periods") to lift specificity.

DimensionReasoningScore

Specificity

The description names the domain precisely ("IMF macroeconomic series, forecasts, and reserve-composition data") but offers only two concrete actions ("Retrieve and analyze"), matching the anchor for domain plus 1-2 concrete actions rather than the several actions of level 4.

3 / 5

Completeness

It clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

"IMF", "macroeconomic", "forecasts", and "reserve-composition" are relevant keywords, but common natural variations users would actually say are missing (e.g., "World Economic Outlook", "WEO", "COFER", "IFS", "economic outlook"), fitting the anchor for some relevant keywords with missing synonyms.

3 / 5

Distinctiveness Conflict Risk

"IMF" and "reserve-composition data" carve a distinct niche with minimal conflict risk against unrelated skills, though the broad phrase "macroeconomic series" leaves minor overlap risk with other economic-data skills (e.g., World Bank or OECD), fitting anchor 4 rather than the fully distinct anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

KunAgent/Kun

Path

resources/bundled-skills/imf-data/SKILL.md

Revision

8e16760

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill