CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-data-source

Add a new WorldMonitor data source or map layer end to end — Railway seeder, Redis seed-meta and health registration, RPC, service, layer toggle, source attribution, and docs. Use when integrating a new API or dataset, adding a seed-*.mjs worker, or adding a map layer.

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An exemplary project-workflow skill: dense, specific, and verifiable, with concrete commands and file paths at every step. The only improvements are naming the layer-config location in step 6 and adding brief recovery guidance to the Verify section.

Suggestions

In step 6, name the actual layer-config and renderer files (e.g. src/config/layers.ts) the way the other steps name their targets, instead of 'following existing layer patterns'.

Add one line of recovery guidance to the Verify section (e.g. what to check first when typecheck or sources:check fails), which would also lift workflow clarity to the top anchor.

DimensionReasoningScore

Conciseness

A lean checklist where every token earns its place — exact file paths, function signatures ('runSeed(domain, resource, canonicalKey, fetchFn, opts)'), and commands like 'npm run sources:check' with no explanation of concepts Claude already knows.

5 / 5

Actionability

Most steps are directly executable with exact paths and commands, but a few lean on pattern-matching rather than specifics — 'Layer config and renderer following existing layer patterns' does not name the config file, and 'Follow a neighbouring seeder's Railway registration' defers the concrete pattern. Not 5 due to these minor gaps; well above the incomplete-guidance anchor of 3.

4 / 5

Workflow Clarity

A clear numbered 1–8 sequence with a dedicated Verify section of concrete checks ('npm run typecheck', 'npm run lint:boundaries', 'npm run test:related'), so validation checkpoints are explicit. Not 5 because there is no error-recovery guidance for what to do when a verification step fails.

4 / 5

Progressive Disclosure

Well under 50 lines with clean Requirements/Steps/Verify sections and no bundle files; external detail is delegated via clearly signaled one-level-deep links (CONTRIBUTING.md, docs/health-endpoints.mdx, sibling skills add-rpc-endpoint and verify-worldmonitor) rather than inlined.

5 / 5

Total

18

/

20

Passed

Description

88%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, concrete, and comprehensive on the 'what', with an explicit multi-clause 'Use when' trigger. The only weaknesses are a few missing natural synonyms and a slightly generic 'integrating a new API' trigger that could overlap with sibling skills.

DimensionReasoningScore

Specificity

Enumerates seven concrete actions spanning the whole pipeline — 'Railway seeder, Redis seed-meta and health registration, RPC, service, layer toggle, source attribution, and docs' — giving comprehensive end-to-end coverage rather than just several actions with gaps.

5 / 5

Completeness

Explicitly answers both: what ('Add a new WorldMonitor data source or map layer end to end' with a concrete component list) and when ('Use when integrating a new API or dataset, adding a seed-*.mjs worker, or adding a map layer') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'integrating a new API or dataset, adding a seed-*.mjs worker, or adding a map layer' covers natural phrases a user would say, but common synonyms like 'data feed', 'data provider', or 'adding a source' are missing. Not 5 because coverage is good but not comprehensive; not 3 because multiple distinct natural triggers are present.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche ('WorldMonitor data source or map layer'), but 'integrating a new API or dataset' is a fairly generic trigger that could overlap with closely related sibling skills such as add-rpc-endpoint. Not 5 due to this minor overlap risk; well above the broad-anchor 3.

4 / 5

Total

18

/

20

Passed

Validation

75%

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

Validation — 12 / 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

relative_links

Relative link issues: 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

12

/

16

Passed

Repository

koala73/worldmonitor

Path

.agents/skills/add-data-source/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.