CtrlK
BlogDocsLog inGet started
Tessl Logo

instantly-local-dev-loop

Configure Instantly.ai local development with mock server and test workflows. Use when setting up a dev environment, testing API calls without sending emails, or building integration tests against Instantly endpoints. Trigger with phrases like "instantly dev setup", "test instantly locally", "instantly mock server", "instantly development environment".

80

Quality

77%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/saas-packs/instantly-pack/skills/instantly-local-dev-loop/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

89%

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

This is a well-structured skill description that clearly identifies its niche (Instantly.ai local development), explains when to use it, and provides explicit trigger phrases. The main weakness is that the specific capabilities could be more granular—listing concrete actions like configuring mock endpoints, stubbing email sends, or setting up test fixtures would strengthen the specificity dimension.

Suggestions

Add more concrete specific actions beyond 'configure' and 'test workflows', e.g., 'stub API responses, configure mock SMTP, generate test fixtures, validate webhook payloads'

DimensionReasoningScore

Specificity

Names the domain (Instantly.ai local development) and some actions (configure, mock server, test workflows), but doesn't list multiple concrete specific actions like 'start mock SMTP server, stub API responses, run integration test suites'. The actions remain somewhat high-level.

2 / 3

Completeness

Clearly answers both 'what' (configure local dev with mock server and test workflows) and 'when' (setting up dev environment, testing API calls without sending emails, building integration tests) with explicit trigger phrases listed.

3 / 3

Trigger Term Quality

Includes natural trigger phrases users would say: 'instantly dev setup', 'test instantly locally', 'instantly mock server', 'instantly development environment', plus terms like 'dev environment', 'testing API calls', 'integration tests', and 'Instantly endpoints'. Good coverage of natural variations.

3 / 3

Distinctiveness Conflict Risk

Very specific niche targeting Instantly.ai local development and mock server setup. The combination of 'Instantly.ai' + 'local development' + 'mock server' creates a distinct trigger profile unlikely to conflict with other skills.

3 / 3

Total

11

/

12

Passed

Implementation

64%

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

This is a solid, highly actionable skill with complete executable code for every step of the Instantly local dev setup. Its main weaknesses are verbosity (the full code listings make it token-heavy) and missing validation checkpoints between steps — there's no explicit verification that the mock server works, that tests pass before proceeding to webhooks, or error recovery guidance within the workflow itself.

Suggestions

Add explicit validation checkpoints between steps, e.g., 'Verify mock server is reachable: curl https://developer.instantly.ai/_mock/api/v2/campaigns' before running tests, and 'Confirm webhook registration succeeded by checking the response' before testing delivery.

Consider moving the full API client and test suite code into referenced files (e.g., See [client.ts](examples/client.ts)) and keeping only the key patterns inline to reduce token usage.

Add a quick smoke test or verification command after Step 1 to confirm the dev environment is correctly configured before building the full client.

DimensionReasoningScore

Conciseness

The skill is mostly efficient with executable code examples, but includes some unnecessary verbosity — the full TypeScript class definitions, complete test suites, and project structure section add bulk that could be trimmed. The error handling table and resources section are useful but the overall length (~150 lines of code) is heavy for what could be more concise.

2 / 3

Actionability

Every step includes fully executable, copy-paste ready code — TypeScript config, API client with error handling and retry logic, Vitest integration tests, bash commands for ngrok setup, and a complete webhook server. The .env file examples and curl commands are concrete and immediately usable.

3 / 3

Workflow Clarity

The 5-step sequence is clearly ordered and logical, but there are no explicit validation checkpoints between steps. For example, there's no step to verify the mock server is reachable before running tests, no verification that the webhook registration succeeded, and no feedback loop for when tests fail against the mock server.

2 / 3

Progressive Disclosure

The skill has good section structure and references external resources and a related skill (`instantly-sdk-patterns`), but the inline content is quite heavy — the full API client, test suite, and webhook server code could be split into referenced files. The project structure section helps navigation but the main body is still monolithic.

2 / 3

Total

9

/

12

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

9

/

11

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.