clay-sdk-patterns

Apply production-ready patterns for integrating with Clay via webhooks and HTTP API. Use when building Clay integrations, implementing webhook handlers, or establishing team coding standards for Clay data pipelines. Trigger with phrases like "clay SDK patterns", "clay best practices", "clay code patterns", "clay integration patterns", "clay webhook patterns".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is highly actionable with complete, executable TypeScript and Python clients, but it is token-heavy from duplicating the client across two languages and lacks validation checkpoints for its batch operations. With no bundle files, all of this large code surface lives inline rather than being progressively disclosed.

Suggestions

Move the full client implementations and type definitions into reference files (e.g. references/client.ts.md, references/clay_client.py.md) and keep SKILL.md as an overview with one minimal example per language.

Add an explicit validation/verification checkpoint to the batch send workflow (e.g. confirm sent count, surface and retry failed rows) to satisfy the batch-operation feedback-loop requirement.

Pick one primary language inline and reference the other to cut the duplicated client boilerplate and improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Prose is lean and mostly code, but the body ships two full client implementations (TypeScript ~100 lines and Python ~55 lines) plus type definitions and a singleton, much of which duplicates concepts across languages and could be tightened or offloaded. This matches "mostly efficient but includes some unnecessary explanation or could be tightened" rather than the every-token-earns-its-place score-3 anchor.	2 / 3
Actionability	Provides fully executable, copy-paste-ready TypeScript and Python clients, concrete type definitions, a singleton factory, and a working Express callback handler. This matches the score-3 anchor for executable code and specific examples, not the score-2 pseudocode anchor.	3 / 3
Workflow Clarity	Sections are sequenced (Step 1–4) and an error-handling table exists, but the batch send operation has no validation/verification checkpoint or feedback loop, and the per-step "validation -> fix -> retry" pattern is absent. Per the rubric, missing validation for batch operations caps workflow clarity at 2 rather than 3.	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so all content is inline in a ~270-line SKILL.md; the heavy client code and type definitions could be split into referenced files. Sectioning and headings give it some structure, matching "some structure but content that should be separate is inline" rather than the monolithic score-1 anchor or the well-split score-3 anchor.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 clearly states both what the skill does and when to use it with explicit triggers, and is well-scoped to a Clay-specific niche. Its main weakness is repetitive, formulaic trigger phrases that miss natural variations users would actually say.

Suggestions

Vary trigger phrases beyond the repeated "clay ___ patterns" template to include natural phrasings like "integrate with Clay", "clay webhook handler", and "clay API client".

Drop the generic "clay best practices" trigger, which is broad enough to risk firing for unrelated Clay questions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "Apply production-ready patterns for integrating with Clay via webhooks and HTTP API", "building Clay integrations", "implementing webhook handlers", and "establishing team coding standards". This matches the anchor for naming multiple specific concrete actions rather than the score-2 anchor that names only a domain and some actions.	3 / 3
Completeness	Explicitly answers both "what" ("Apply production-ready patterns for integrating with Clay via webhooks and HTTP API") and "when" ("Use when building Clay integrations, implementing webhook handlers...") with explicit trigger guidance, matching the score-3 anchor. It is not score 2 because the "when" is explicit, not merely implied.	3 / 3
Trigger Term Quality	Provides trigger phrases ("clay SDK patterns", "clay best practices", "clay code patterns", "clay integration patterns", "clay webhook patterns") but they are formulaically repetitive — all suffixed with "patterns" — and miss common natural variations a user would actually say like "integrate with Clay", "clay webhook handler", or "clay API". This fits "some relevant keywords but missing common variations" rather than the full-coverage score-3 anchor.	2 / 3
Distinctiveness Conflict Risk	Clay-specific niche with distinct Clay-prefixed triggers (webhook patterns, integration patterns) makes it unlikely to fire for unrelated skills, matching the clear-niche score-3 anchor. It is not score 2 because the domain and triggers are tightly scoped to Clay rather than overlapping with generic integration skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

Warnings & errors only

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

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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

Reviewed: about 1 hour ago

Table of Contents

Discovery Implementation Validation

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.