CtrlK
BlogDocsLog inGet started
Tessl Logo

orbit-github

Open Orbit briefing skill — selected by the Orbit pipeline when GitHub is the user's only connected connector, or when the user explicitly scopes their daily digest to GitHub. Pulls the past 24 hours of PRs, review requests, issues, CI runs, and merges from the user's authenticated GitHub connection and renders them in a layout that mirrors GitHub's native Notifications + PR-diff visual language. This skill should not be triggered manually — it is invoked by Orbit's daily-digest scheduler against live GitHub data.

60

Quality

71%

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

Quality

Content

50%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, well-organized visual spec with concrete tokens and a clear reproduction protocol, but it is undermined by a missing example.html that the entire workflow assumes, plus redundant restatement of values across sections.

Suggestions

Ship the referenced example.html (and index.html) in the bundle so the 'read the shipped example.html' step in the source-of-truth protocol has a real referent.

Add an explicit verification checkpoint (e.g. 'before finishing, confirm your output's DOM hierarchy, rail items, and event groups match example.html 1:1') to turn the do/don't table into a validation step.

De-duplicate the color/typography values that appear in both 'Page sections' / 'Canvas tokens' and the 'Implementation constraints' table by referencing the token block once.

DimensionReasoningScore

Conciseness

Mostly efficient spec with no concept-over-explanation, but the same values recur across sections (e.g. CI-fail colors in 'Page sections' and the do/don't table; review-request attention block described twice) and the source-of-truth protocol is heavy with repeated emphasis.

3 / 5

Actionability

Token and layout guidance is concrete and copy-paste ready (exact hex, font stack, px sizes, repo name), but the foundational executable step — 'Open and read the shipped example.html' — references a file that is not present in the bundle, leaving the reproduction task without its primary reference.

3 / 5

Workflow Clarity

A clear three-step source-of-truth sequence exists, but validation checkpoints are implicit (the do/don't table is not framed as a verify step) and the opening step depends on the missing example.html.

3 / 5

Progressive Disclosure

SKILL.md is well-sectioned with clearly signaled references to example.html, but no bundle files ship — the one-level-deep canonical reference (example.html) the skill depends on is absent, and all design detail is inlined rather than split as intended.

3 / 5

Total

12

/

20

Passed

Description

92%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 strong, specific description that clearly states what the skill does and when it fires, using concrete actions and a well-scoped trigger model. Minor room to expand user-natural trigger phrasing beyond the pipeline-selection framing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Pulls the past 24 hours of PRs, review requests, issues, CI runs, and merges' and 'renders them in a layout that mirrors GitHub's native Notifications + PR-diff visual language' — covering the domain comprehensively.

5 / 5

Completeness

Explicitly answers both 'what' (pulls and renders GitHub activity) and 'when' ('when GitHub is the user's only connected connector, or when the user explicitly scopes their daily digest to GitHub') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keywords (GitHub, PRs, review requests, issues, CI runs, daily digest) with synonyms (briefing/digest), but the framing leans on pipeline-selection logic rather than maximally comprehensive user-utterance terms.

4 / 5

Distinctiveness Conflict Risk

Highly specific niche — single-connector GitHub-only Orbit daily digest — with distinct, scoped triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.