CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

help

Explain the bundled skills, supported MCP tools, OAuth setup, and support options.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/claude-directory/skills/help/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary lean overview for a plugin help skill: a precise routing table, targeted safety pointers, and operational guardrails in 14 lines. Its only weakness is that guardrail policies like readback verification are asserted without a concrete example of how to perform them.

DimensionReasoningScore

Conciseness

Every sentence delivers plugin-specific information Claude cannot know (OAuth architecture, the skill routing map, tool constraints, spend-approval guardrails) with zero padding and no explanation of known concepts. This matches the lean anchor where every token earns its place; the nearest lower anchor (4) requires trimmable over-explanation, which is absent.

5 / 5

Actionability

Concrete, executable routing ("Use **report** and **attribution** to review performance, **media-plan** and **launch** to prepare approved campaign changes") and specific guardrails ("obtain explicit approval for spend-changing actions") with pointers to real files. It falls short of fully copy-paste-ready anchor 5 because "verify provider readback" and the MCP tool usage are stated as policies without an example invocation.

4 / 5

Workflow Clarity

This is a simple single-purpose router skill under 50 lines whose single action is unambiguous: each user intent maps to a named skill. It even includes explicit checkpoints (read brand-and-safety guidance before copy or spend, obtain approval, verify provider readback before claiming completion), satisfying the simple-skill exception for a top score.

5 / 5

Progressive Disclosure

The body is a pure overview that delegates detail to well-signaled, one-level-deep references — "[brand and safety guidance](../../context/brand-and-safety.md)" with its purpose stated, the bundled tool directory, and eight named sibling skills — with no nested reference chains. This matches the clear-overview anchor 5 rather than anchor 4, which requires organization gaps.

5 / 5

Total

19

/

20

Passed

Description

50%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 is concise and names its topics concretely, but it is a bare capability list with no trigger guidance and only one generic action verb. It reads as a table of contents rather than an invocable skill description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks what this plugin does, how to sign in, or which skill to use for a task."

Include natural user phrasings as trigger terms such as "help", "sign in", "connect account", and "Synter" so the skill fires on real requests.

Replace the single generic verb with the concrete actions a help interaction performs, e.g. "Routes requests to the bundled skills (quickstart, report, audience, ...) and explains OAuth setup" — this also reduces overlap with generic help skills.

DimensionReasoningScore

Specificity

The description names its domain and topics concretely ("bundled skills, supported MCP tools, OAuth setup, and support options") but relies on a single generic action verb ("Explain") and never says what the plugin actually does. This matches the anchor for a named domain with 1-2 concrete actions that is not comprehensive, not the level above which requires several specific actions.

3 / 5

Completeness

The "what" is clear (explains the bundle's skills, MCP tools, OAuth setup, support), but there is no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 2 because the "what" is specific rather than vague.

3 / 5

Trigger Term Quality

"OAuth" and "support" are terms a user would naturally say, and "MCP tools" is semi-natural, but common variations like "help", "sign in", "connect", or "what can this plugin do" are missing. Some relevant keywords with missing synonyms fits anchor 3, below the good-coverage anchor 4.

3 / 5

Distinctiveness Conflict Risk

"OAuth setup" and "bundled skills" anchor it to this specific plugin, but a generic explain/help description could overlap with other help or onboarding skills. Somewhat specific with residual overlap risk matches anchor 3 rather than the mostly-distinct anchor 4.

3 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository

Synter-Media-AI/plugin

Path

packages/claude-directory/skills/help/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.