CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

onboarding

Connect a new user's accounts, learn their real work, choose a voice, and set up concrete help.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/onboarding/skills/onboarding/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a dense, highly actionable instruction document: concrete API endpoints, exact persistence markers, explicit decision branches, and built-in verification checkpoints (re-check, confirm before creating, exercise before publishing). Its main weaknesses are minor: reliance on external skill documents the reader must already have, and step numbering that does not align between the intro and section headers.

DimensionReasoningScore

Conciseness

The body is dense imperative rules with no padding or explanation of concepts Claude already knows; every section gives operational instructions. Minor trimming is possible (e.g., repeated "skip silently"/"do not advertise setup" negations across the Slack bot section), which matches the 4 anchor rather than the fully lean 5 anchor or the noticeably padded 3 anchor.

4 / 5

Actionability

It provides copy-paste-ready curl commands with exact endpoints and headers ("GET /v1/composio/toolkits", "GET /v1/admin/slack-installation", the consent mint POST), exact memory marker strings, and explicit per-branch decision rules. Minor gaps remain: undefined external references such as "the selected access skill" and "the signals in the admin skill's **Check connector sources** section" keep it below the fully executable 5 anchor.

4 / 5

Workflow Clarity

The intro orders four steps to "complete the steps in order", and each has a detailed section with explicit checkpoints ("When they say it is done, re-check", "Confirm exact behavior and timing before creating anything", "Build and exercise an app locally before publishing", "List existing crons first and patch a match"). It falls short of 5 because the section header numbering (1, unnumbered Voice, 2, 3) does not match the intro's four-step numbering, and there is no explicit error-recovery loop for the workflow as a whole.

4 / 5

Progressive Disclosure

No bundle files exist, and the single-file body is well organized into clearly signaled sections (State and persistence, Connect accounts with subsections, Voice, Read their work, Confirm and help), all serving the one onboarding flow. Minor organization gaps (the inconsistent step numbering, ~40 lines of admin-only detail that could live in a reference file) place it at the 4 anchor rather than the fully split-and-navigable 5 anchor.

4 / 5

Total

16

/

20

Passed

Description

51%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.

The description states a clear, multi-action "what" in concise third person, but it entirely lacks any "when" trigger guidance. Without trigger phrases like "onboarding" or "new user", the skill risks not being surfaced when needed and its keywords remain generic.

Suggestions

Append a trigger clause such as "Use when onboarding is pending, a new user starts, or the user asks to onboard again."

Include natural trigger terms and synonyms users would say: "onboarding", "new user setup", "get started", "set me up".

Replace the vague "set up concrete help" with a concrete action, e.g., "propose and create reminders, follow-ups, and published apps".

DimensionReasoningScore

Specificity

Quotes like "Connect a new user's accounts" and "choose a voice" are concrete actions, and "learn their real work" is moderately concrete, but "set up concrete help" is vague, leaving minor gaps rather than the comprehensive coverage of the 5 anchor. It exceeds the 1-2 concrete actions of the 3 anchor.

4 / 5

Completeness

It clearly answers "what" (connect accounts, learn work, choose a voice, set up help) but has no "Use when..." clause or equivalent explicit trigger guidance, which the rubric explicitly caps at 3. The "what" is not vague, so the 2 anchor's vague-what case does not fit.

3 / 5

Trigger Term Quality

The description contains no natural phrases a user would say to invoke this skill (e.g., "onboard", "get started", "new user setup"); only generic keywords like "accounts", "voice", and "help" appear. It is not entirely generic jargon (1 anchor) but clearly misses the natural phrases users say.

2 / 5

Distinctiveness Conflict Risk

The combination of account connection, voice choice, and help setup is a distinctive onboarding signature with minor overlap risk against pure account-connection skills. It lacks the explicit distinct triggers of the 5 anchor but is more specific than the 3 anchor's single-domain phrasing.

4 / 5

Total

13

/

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

yc-software/qm

Path

plugins/onboarding/skills/onboarding/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.