CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

live-dashboard

Build self-updating dashboards from live sources.

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 ./optional-skills/productivity/live-dashboard/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 exemplar of a procedural skill: concrete tool calls, exact file contracts, per-step done-conditions, a dedicated pitfalls section, and a closing verification checklist. Its only weaknesses are small internal redundancies and inline detail (HTML layout, state-file schema) that could live in reference files.

DimensionReasoningScore

Conciseness

The body is lean and operational — no explanations of concepts Claude already knows — with only minor trimmable redundancy (the source-connector list repeated in Prerequisites and step 2; the [SILENT] delivery rule stated in both the blueprint and step 7), matching 'efficient; minor instances of over-explanation' rather than the every-token-earns-its-place bar of 5.

4 / 5

Actionability

Guidance is fully concrete and executable: exact artifact paths (dashboards/<slug>/dashboard.json, index.html), a copy-paste-ready cronjob(...) call template, an exact desktop_preview(...) call, per-field source/timestamp contract rules, and stale-field handling. Per the scoring notes, an instruction-only skill with this specificity is not penalized for lacking code.

5 / 5

Workflow Clarity

Setup (steps 1-4), tick (5-7), and show (8) are explicitly sequenced; every step has a 'Done when...' validation checkpoint; failed reads feed an explicit recovery loop (keep last-known-good, mark stale, renegotiate sources); and a final Verification checklist covers the batch sweep — clear sequence with explicit validation, feedback loops, and a checklist.

5 / 5

Progressive Disclosure

The skill has no bundle files and the body is a single-level, well-sectioned overview with no nested references. The only organization gap is that the index.html layout spec and a sample dashboard.json schema are described inline where a template under references/ would keep the overview lean — good structure with minor gaps.

4 / 5

Total

18

/

20

Passed

Description

53%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, concise 'what' but entirely lacks 'when to use' guidance, and its keyword coverage misses the natural phrases users would say when needing this skill. It is serviceable but under-sells a well-built skill.

Suggestions

Add a 'Use when...' clause with natural trigger phrases, e.g., "Use when the user asks to make a dashboard, status page, or tracker and keep it updated (e.g., 'show me where my visa applications stand, updated daily')."

Broaden trigger keywords with common synonyms: "status page", "keep it updated", "track X across email and websites", "monitor and show me where it stands".

Name the concrete capabilities to raise specificity: building self-contained HTML dashboards, reading email/calendar/website/file sources, and scheduling recurring refreshes.

DimensionReasoningScore

Specificity

"Build self-updating dashboards from live sources" names the domain and 1-2 actions (build, self-update) but omits the concrete capabilities the skill actually performs (reading email/website/file sources, scheduling a cron tick, rendering HTML) — matching anchor 3, not the several specific actions of anchor 4.

3 / 5

Completeness

The 'what' is clearly stated but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3; it is not 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

"dashboards", "self-updating", and "live sources" are relevant keywords, but common natural phrasages like "status page", "keep it updated", "track X", or "monitor" are missing — some relevant keywords without common variations or synonyms.

3 / 5

Distinctiveness Conflict Risk

"Dashboards" is a distinctive niche term a user would naturally say, but "live sources" is generic enough to overlap with closely related monitoring skills (e.g., product-price-monitor, competitor-news-monitor) with no disambiguating trigger — mostly distinct with minor overlap risk, not the clear-niche-with-distinct-triggers of anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/productivity/live-dashboard/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.