CtrlK
BlogDocsLog inGet started
Tessl Logo

orbit-gmail

Open Orbit briefing skill — selected by the Orbit pipeline when Gmail is the user's only connected connector, or when the user explicitly scopes their daily digest to Gmail. Pulls the past 24 hours of inbox activity (replies awaited, mentions, cc, auto- categorized bulk) from the user's authenticated Gmail connection and renders the digest as the Orbit Daily Digest email opened inside Gmail's reading view. This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against live Gmail data.

63

Quality

75%

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 ./design-templates/orbit-gmail/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 thorough, actionable single-purpose skill body with a clear reproduce-the-canonical-example workflow and explicit guardrails against scope creep; the main weakness is conciseness, as the same don't-invent-UI constraints are restated across the protocol, design-policy, and do/don't sections.

Suggestions

Consolidate the repeated 'no left rail / no inbox list / no Categories tabs / no extra sections' prohibitions, which currently appear in the source-of-truth protocol, the page-section notes, and the do/don't table — state each once.

Add an explicit verify step (e.g. 'diff your output structure against example.html's DOM and class names before finalizing') to turn the workflow into a validate→fix→retry loop and lift workflow clarity.

If example.html is the canonical reference, confirm it is shipped alongside the skill so the one-level reference is resolvable at runtime.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence, but the repeated 'Do not' inventories, the duplicated source-of-truth protocol, and the paired do/don't table restate the same constraints several times, adding padding that could be tightened.

3 / 5

Actionability

Concrete, executable guidance dominates: exact token values (colors, type stack, avatar sizes), a 1:1 DOM hierarchy, ordered section list, and a do/don't table with specific examples; minor gaps are that the canonical example.html is referenced but its full markup is not inlined.

4 / 5

Workflow Clarity

A clear three-step sequence ('Open example.html' → 'Mirror structure 1:1' → 'Refresh mock copy only') with explicit identity and design-system guardrails serves as validation checkpoints; it stops short of a full validate→fix→retry loop, hence just below 5.

4 / 5

Progressive Disclosure

Structure is well-organized with clear sections and a clearly signaled one-level reference to the bundled example.html as the canonical source; no bundle directory files are present beyond example.html, so most detail lives inline, leaving only minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

83%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 highly specific, well-scoped description that names concrete actions and a clear trigger niche; its main gap is that the 'when' guidance is framed as scheduler invocation rather than an explicit user-facing 'Use when...' clause, and trigger term coverage could include more synonyms.

Suggestions

Add an explicit user-facing 'Use when...' clause (e.g. 'Use when the user asks for their daily Gmail digest or inbox summary') to strengthen completeness beyond the scheduler-invocation framing.

Broaden trigger terms with common synonyms such as 'daily digest', 'gmail summary', and 'inbox summary' to improve natural-keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Pulls the past 24 hours of inbox activity (replies awaited, mentions, cc, auto-categorized bulk)... and renders the digest as the Orbit Daily Digest email opened inside Gmail's reading view'), giving comprehensive, specific coverage of what the skill does.

5 / 5

Completeness

It clearly answers 'what' (pulls 24h inbox activity, renders the digest email) and 'when' ('selected by the Orbit pipeline when Gmail is the user's only connected connector, or when the user explicitly scopes their daily digest to Gmail'), but the 'when' is scheduler-driven rather than framed as a direct 'Use when...' clause, so it is not maximally explicit.

4 / 5

Trigger Term Quality

Triggers ('gmail briefing', 'inbox digest', 'email summary', plus Chinese variants) are natural phrases a user would say, but lack file-extension-style synonyms and a few common variations (e.g. 'daily digest', 'gmail summary').

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — single-connector Gmail-only Orbit daily digest rendered inside Gmail's reading view — with distinct triggers and an explicit note that it 'should not be triggered manually', minimizing conflict with other skills.

5 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.