CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-resend

Add Resend (email) channel integration via Chat SDK.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

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 well-engineered, fully executable setup skill: idempotent directives, explicit validation checkpoints with feedback loops, and concrete recovery paths. The only notable improvements are trimming minor duplicated notes and splitting the long Channel Info/Troubleshooting tail into a reference file.

DimensionReasoningScore

Conciseness

The body is dense and almost entirely project-specific (idempotent directives, NanoClaw wiring, test-file rationale), with no explanation of concepts Claude already knows. It is not a 5 because of minor redundancy — e.g. the WEBHOOK_HOST=0.0.0.0 note appears both inside the webhook_secret prompt and again in Troubleshooting, and a few asides could be tightened.

4 / 5

Actionability

Every step is executable as written: shell guards in nc:run fences, a pinned exact dependency (@resend/chat-sdk-adapter@0.3.0), an idempotent barrel append, concrete ncl CLI commands with placeholders, and named vitest runs. Copy-paste ready guidance covers the common cases end to end.

5 / 5

Workflow Clarity

Four clearly sequenced Apply steps each carry explicit validation (build, then per-file test runs with the rationale for splitting them), a failure-recovery fallback restores resend.ts if the branch copy fails, and Troubleshooting closes the loop ("red means ... re-run the Apply steps"). This matches the anchor with explicit checkpoints and feedback loops for error recovery.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), so the single SKILL.md is the whole skill; its sections (Apply, Credentials, Connect yourself, Channel Info, Troubleshooting) are clearly headed, ordered, and nothing is buried. It is not a 5 because at ~185 lines, reference material like Channel Info and Troubleshooting could plausibly live in one-level-deep reference files, keeping the main file closer to an overview.

4 / 5

Total

18

/

20

Passed

Description

65%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.

A terse, third-person description that clearly states a specific, distinctive capability but completely omits any trigger guidance. Adding a "Use when..." clause (and a couple of natural phrasings like "connect email" or "set up Resend") would raise completeness and trigger-term quality substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up email for NanoClaw, when the user mentions Resend, email channels, or connecting the bot to email."

Broaden trigger-term coverage with natural synonyms users would say — "connect email", "email channel setup", "Resend integration" — since only "Resend" and "email" currently appear.

Optionally enumerate 1-2 more concrete actions (e.g., wiring the webhook and registering the owner address) to lift specificity beyond a single stated action.

DimensionReasoningScore

Specificity

"Add Resend (email) channel integration via Chat SDK" names a specific domain and one concrete action (adding the channel adapter via the Chat SDK), but offers no broader action coverage. It is above anchor 2 because the action is concrete rather than generic, and below anchor 4 because only a single action is described.

3 / 5

Completeness

The "what" is clear (add the Resend email channel integration via Chat SDK), but there is no "Use when..." clause or any equivalent explicit trigger guidance, which caps this dimension at 3. Not 4 because the "when" is entirely missing rather than merely implicit-but-present.

3 / 5

Trigger Term Quality

The description carries natural terms a user would say — "Resend", "email", "channel", "integration" — giving good keyword coverage. It falls short of anchor 5 because common phrasings like "connect email", "set up Resend", or "email bot" are absent.

4 / 5

Distinctiveness Conflict Risk

"Resend" is a specific named email service, giving the description a clear niche with distinct triggers and minimal risk of firing for an unrelated skill. The generic word "email" alone would create overlap risk, but the Resend qualifier pins it down.

5 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

nanocoai/nanoclaw

Path

.claude/skills/add-resend/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.