CtrlK
BlogDocsLog inGet started
Tessl Logo

add-icon-mapping

Add or modify icon keyword mappings for providers, models, or agents in lobe-icons. Use this whenever a task involves mapping a provider/model id to an icon, adding a new entry to ModelProvider enum or providerMappings/modelMappings/agentMappings, or fixing a provider/model that renders the fallback (default) icon in LobeHub. Trigger even if the request only says "add icon for X provider" or references a Linear issue about icon keyword mapping — the actual icon component usually already exists; only the mapping is missing.

80

Quality

100%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 a model instruction-only skill: it encodes hard-won repo-specific pitfalls (RN duplication, first-match regex ordering, lockfile noise), gives copy-paste-ready code and commands for every step, and closes with explicit verification (type-check plus a grep completeness check) and commit hygiene. Structure is clean and self-contained with no wasted tokens.

DimensionReasoningScore

Conciseness

Nearly every token is repo-specific knowledge Claude cannot already know — the RN package duplication table, exact-match vs RegExp semantics with concrete consequences, the lockfile=false pitfall, and the pre-commit lint-staged sweep; there is no padding and no explanation of general concepts, so the 5 anchor fits rather than 4.

5 / 5

Actionability

Fully executable throughout: exact import statements for both packages ('@/Grok' vs '../icons/Grok'), the mapping entry literal, both type-check commands, the grep completeness check with the expected 2×2 result, a regex sanity-check expression, and the exact gitmoji commit format; not 4 because the guidance is copy-paste ready and covers the common cases.

5 / 5

Workflow Clarity

Clear four-step sequence with an explicit 'Repeat 1–3 in the react-native package' step, a Verification section with explicit validation commands and expected outcomes, error-recovery feedback (triaging environmental vs change-caused type errors, not installing deps just to silence them), and a post-commit git show --stat check; matches the 5 anchor with validation checkpoints and feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed: the skill is self-contained with well-organized, short sections (mapping locations table, matching semantics, workflow, verification, commit pitfalls), nothing that belongs in a separate file, and no nested references — easy to navigate throughout.

5 / 5

Total

20

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, quotes the natural phrasing a user would actually say, gives an explicit and detailed 'Use this whenever...' trigger clause, and carves out an unmistakable niche. It is dense but every clause carries trigger or capability information, so there is no padding to penalize.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — add or modify icon keyword mappings, add ModelProvider enum entries, add providerMappings/modelMappings/agentMappings entries, and fix the fallback-icon symptom — with comprehensive coverage of the skill's scope; not 4 because there are no gaps in coverage.

5 / 5

Completeness

Explicitly answers both what ('Add or modify icon keyword mappings for providers, models, or agents in lobe-icons') and when ('Use this whenever a task involves...', 'Trigger even if the request only says...') with concrete trigger phrases; not 4 because the when-clause is maximally explicit.

5 / 5

Trigger Term Quality

Includes the natural user phrase 'add icon for X provider' verbatim, the synonym pair 'fallback (default) icon', plus domain terms like 'icon keyword mapping', 'Linear issue', 'lobe-icons', and 'LobeHub'; not 4 because no meaningful natural term for this domain is missing.

5 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers — it names the specific repo (lobe-icons), specific config symbols (ModelProvider, providerMappings/modelMappings/agentMappings), and a specific symptom (fallback icon in LobeHub), giving minimal conflict risk with other skills.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
lobehub/lobe-icons
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.