add-resend

Add Resend (email) channel integration via Chat SDK.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-resend/SKILL.md

Quality

Content

100%Weight 40%Scale 1-3

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

The body is a strong, lean, fully-executable recipe: exact commands and pinned versions, a clearly sequenced Apply workflow with explicit build/test validation and error-recovery guidance, and clean single-file section organization requiring no external references.

Dimension	Reasoning	Score
Conciseness	The body is dense and task-focused with directive fences, exact pinned versions, and full commands; it avoids explaining concepts Claude already knows and the explanatory prose (e.g., why nc:append is the only reach-in, why the test covers the dependency) earns its place for the dual agent/parser audience, matching the score-3 anchor 'Lean and efficient; every token earns its place'; not 2 because there is no padding or unnecessary explanation.	3 / 3
Actionability	Provides fully executable, copy-paste-ready guidance — exact paths in nc:copy, pinned '@resend/chat-sdk-adapter@0.1.1', and complete 'pnpm run build' / 'pnpm exec vitest run ...' / 'ncl ...' commands with all flags — matching the score-3 anchor; not 2 because there is no pseudocode and no missing key details.	3 / 3
Workflow Clarity	Apply steps are numbered 1–4 with explicit validation checkpoints (build guards the typed call; the registration test verifies the barrel import and dependency) and a documented feedback loop in Troubleshooting ('red means ... re-run the Apply steps; if green, restart the service'), matching the score-3 anchor with explicit validation and error recovery; not 2 because checkpoints are explicit rather than merely listed.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the skill is self-contained in a single well-organized file with clearly headed sections (Apply, Credentials, Connect yourself, Next Steps, Channel Info, Troubleshooting) and no nested references; per the scoring notes a skill with no need for external references scores 3 with well-organized sections; not 2 because organization is clean and there is no content that should be split out.	3 / 3
	Total	12 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 specific and distinctive, clearly naming the Resend email channel niche, but it is terse and omits any explicit 'Use when' trigger guidance and broader natural-language keywords, which caps completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' clause naming the triggering situations (e.g., 'Use when adding email to NanoClaw via Resend, or when the user asks to send or receive email through the bot').

Broaden natural trigger terms to include common phrasings a user would say, such as 'email channel', 'sending/receiving email', or 'inbox'.

List a second concrete action beyond 'add integration' (e.g., wiring the sending identity and webhook) to lift specificity toward 3.

Dimension	Reasoning	Score
Specificity	Quotes 'Add Resend (email) channel integration via Chat SDK' — it names the domain (Resend email channel) and one concrete action (add integration), matching the score-2 anchor 'Names domain and some actions, but not comprehensive'; not 3 because only a single action is named rather than multiple specific concrete actions.	2 / 3
Completeness	Clearly states what the skill does ('Add Resend (email) channel integration') but provides no 'Use when...' or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2; not 1 because 'what' is clear, not 3 because 'when' is entirely absent.	2 / 3
Trigger Term Quality	Contains natural terms like 'Resend' and 'email', but the phrasing 'channel integration via Chat SDK' leans technical and omits common user variations, matching the score-2 anchor 'Some relevant keywords but missing common variations'; not 3 due to narrow coverage, not 1 because real natural keywords are present.	2 / 3
Distinctiveness Conflict Risk	Scoped to a single named vendor/channel ('Resend (email) channel integration'), a clear niche with distinct triggers unlikely to conflict with other channel skills, matching the score-3 anchor; not 2 because it is not a generic overlap-prone description.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nanocoai/nanoclaw
Path: .claude/skills/add-resend/SKILL.md
Commit: 641963c

Reviewed: 6 days 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.