instantly-core-workflow-a
Build and launch an Instantly.ai cold email campaign end-to-end. Use when creating campaigns, adding leads, configuring sequences, and launching outreach via the Instantly API v2. Trigger with phrases like "instantly campaign", "launch instantly campaign", "create instantly outreach", "instantly cold email", "instantly send campaign".
67
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 strong skill description that clearly identifies the platform (Instantly.ai), lists concrete actions (creating campaigns, adding leads, configuring sequences, launching outreach), and provides explicit trigger guidance with natural user phrases. It follows third-person voice correctly and covers all key dimensions well, making it easy for Claude to select this skill appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'build and launch', 'creating campaigns', 'adding leads', 'configuring sequences', 'launching outreach'. These are clear, actionable capabilities tied to a specific platform (Instantly.ai) and API version (v2). | 3 / 3 |
Completeness | Clearly answers both 'what' (build and launch Instantly.ai cold email campaigns end-to-end, including creating campaigns, adding leads, configuring sequences, launching outreach) and 'when' (explicit 'Use when' clause and 'Trigger with phrases like' section with specific triggers). | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger phrases users would actually say: 'instantly campaign', 'launch instantly campaign', 'create instantly outreach', 'instantly cold email', 'instantly send campaign'. These cover multiple natural variations of how a user would request this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific platform name 'Instantly.ai', the API version 'v2', and the niche domain of cold email campaigns. Very unlikely to conflict with other skills unless there were multiple Instantly.ai skills. | 3 / 3 |
Total | 12 / 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, actionable skill with fully executable TypeScript code and a clear 4-step pipeline for launching an Instantly campaign. Its main weaknesses are verbosity (full email body templates, extensive interface definitions) and missing validation checkpoints between pipeline steps — particularly important since lead addition is a batch/loop operation. The error handling table is a nice touch but doesn't compensate for the lack of inline validation logic.
Suggestions
Add validation checkpoints between steps: verify campaign creation returned a valid ID before adding leads, check lead addition results for errors before proceeding, and confirm account assignment before launching.
Trim the email body templates to 1 variant with a comment like '// add A/B variants as needed' — Claude can generate cold email copy without full examples.
Consider extracting the TypeScript interfaces and sample lead data into a separate reference file to keep the SKILL.md focused on the workflow sequence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and the code examples are thorough, but there's significant verbosity — the full 3-step email sequence with complete body text is excessive for a skill file. The interface definitions and sample lead data add bulk that Claude could generate on its own. The error handling and endpoint tables are efficient, but the overall content could be tightened considerably. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript code with concrete API calls, typed interfaces, specific endpoint paths, real payload structures, and sample data. Each step has copy-paste ready code with clear function signatures and return types. | 3 / 3 |
Workflow Clarity | The 4-step sequence is clearly laid out (create → add leads → assign accounts → launch), and there's a verification step after launch (checking sending-status). However, there are no validation checkpoints between steps — no check that campaign creation succeeded before adding leads, no lead verification before assigning accounts, and no error recovery/retry loops for the lead addition loop which is a batch operation. | 2 / 3 |
Progressive Disclosure | The skill references external resources (API docs, related workflow B) and has a useful endpoint summary table. However, the inline content is quite long with full email templates and interface definitions that could be split into separate reference files. With no bundle files provided, there's no supporting structure to offload detail into. | 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.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | |
- Commit
a04d1a2
- 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.