CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-provider

Add an AI provider to ClaudeBar as a JSON definition run by the one generic Provider and DataSource. Use this skill when: (1) Adding a new AI assistant provider (like Antigravity, Cursor, etc.) (2) A provider needs a setting, an added account, or an old saved key kept working (3) A provider's CLI, API or file format changed and its definition must follow (4) User asks "how do I add a new provider" or "create a provider for X"

Quality

92%

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

88%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.

A strong, highly actionable skill body: executable test-first workflow with explicit validation gates and a checklist, and reference-manual density with essentially no wasted tokens. The main weakness is that the exhaustive definition-language and mapping schema material lives inline in SKILL.md rather than in a reference file, which affects both conciseness and progressive disclosure at the margin.

Suggestions

Move the exhaustive per-case option lists (the credential/fetch/mapping sums table and the per-data-source options like errors, fallbackOn, cache.ttl) into a references/definition-language.md file, keeping only the shape overview and one worked example in SKILL.md.

Move the full JSON mapping grammar section (quotas/notes/cost/whenEmpty path rules) to a references/json-mapping.md and keep a single compact example inline, shortening the body by ~80 lines.

Trim inline decoration detail such as the full look color/gradient arrays in the profile example to placeholder values, since the icon guide reference already covers visual specifics.

DimensionReasoningScore

Conciseness

The body is extremely dense with no padding and no explanations of concepts Claude already knows ("A provider is data: one file... There is no registration step and no Swift line that names it"), consistently assuming competence. Not 5 because minor detail could be trimmed or moved (full look color/gradient arrays, exhaustive per-case option lists packed into table cells such as the credential/fetch/mapping sums). Not 3 because there is no unnecessary explanation anywhere.

4 / 5

Actionability

Fully executable throughout: copy-paste-ready Swift golden-test code (StubbedProvider, #expect assertions), concrete JSON definition examples, exact file paths, and exact commands ("tuist test", "python3 scripts/gen-docs.py && python3 scripts/check-docs.py --strict", "npm test in website/"). Not 4 because there are no gaps in executable coverage of the common cases.

5 / 5

Workflow Clarity

A six-step numbered TDD workflow with explicit red-green sequencing ("Golden tests first (red)... They fail first because <id>.json doesn't exist"), explicit validation checkpoints (ProviderFactory.builtIn validates, "tuist test green", docs check passes, npm test fails until counts match), a feedback loop in step 4 for when the language can't say something, and a final checklist. Not 4 because checkpoints are explicit and complete, not implicit.

5 / 5

Progressive Disclosure

One real, well-signaled one-level-deep bundle reference (references/provider-icon-guide.md, verified present) plus clearly flagged repo docs ("Read first: TARGET_ARCHITECTURE.md, MODULAR_DESIGN.md, CANONICAL_MODEL.md") and good section structure. Not 5 because substantial reference material — the full definition-language spec, settings/accounts schemas, and the complete JSON mapping grammar — is inlined, making the body ~340 lines; not 3 because references are clearly signaled and content is well organized, not buried.

4 / 5

Total

18

/

20

Passed

Description

95%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: a concrete what, an explicit four-scenario when clause with verbatim user phrasings, and a distinct niche anchored by named vendors. Voice is appropriately third-person/imperative with no fluff or over-claims.

DimensionReasoningScore

Specificity

"Add an AI provider to ClaudeBar as a JSON definition run by the one generic Provider and DataSource" names the domain and concrete mechanism, and the trigger clauses enumerate specific sub-actions ("A provider needs a setting, an added account, or an old saved key kept working", "A provider's CLI, API or file format changed"). Not 5 because the core capability is a single action with variants rather than a comprehensive list of multiple distinct operations; not 3 because it goes well beyond naming 1-2 actions.

4 / 5

Completeness

Explicitly answers both what ("Add an AI provider to ClaudeBar as a JSON definition...") and when ("Use this skill when:" followed by four numbered scenarios with concrete trigger phrases). Not 4 because the 'when' clause is fully explicit with quoted user asks rather than merely present or generic.

5 / 5

Trigger Term Quality

Includes verbatim natural user phrasings ("how do I add a new provider", "create a provider for X") plus synonyms across add/change scenarios and concrete vendor names users would mention ("like Antigravity, Cursor, etc."), matching the comprehensive anchor. A score of 4 would require natural terms actually missing, which is not the case.

5 / 5

Distinctiveness Conflict Risk

Clear niche (adding AI providers to ClaudeBar as JSON definitions) with distinct triggers and named example vendors; no plausible overlap with unrelated skills. Not 4 because there is no meaningful overlap risk with closely related skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 9 suspicious

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

tddworks/ClaudeBar

Path

.claude/skills/add-provider/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.