tui-widgets

Author live widget apps for the Hermes TUI dock.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/productivity/tui-widgets/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable examples, concrete commands, and a clear verification loop, scoring well on actionability and workflow clarity. It is held back only by minor redundancy between sections and a referenced template file that is missing from the bundle.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no padding about ESM, reducers, or React basics), but the 'How to Run' and 'Procedure' sections overlap on hot-reload and `/<id>` launch mechanics, so it could be tightened — not the level-3 'every token earns its place'.	2 / 3
Actionability	Provides a fully executable register(sdk) example, exact API signatures (sparkline, sparkRows, gauge, hbars), concrete slash commands (`/widgets-reload`, `/<id>`), and specific file paths (~/.hermes/tui-widgets/<name>.mjs, crash log), matching the level-3 copy-paste-ready anchor.	3 / 3
Workflow Clarity	Sequenced numbered steps in 'How to Run' and 'Procedure' plus a dedicated 'Verification' section with explicit checkpoints (file listed under loaded:, ambient dock behavior, re-toggle to remove) and a 'Pitfalls' error-recovery pointer, matching the level-3 clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a single monolithic file with a large inline 'Quick Reference' API section that could be split out, and it references a 'templates/clock.mjs' bundle file that is not present in the skill bundle (no references/scripts/assets directories exist) — a dangling, one-level reference rather than the level-3 well-signaled split.	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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, distinctive purpose but is held back by the absence of an explicit 'Use when...' trigger clause and limited action/keyword coverage. It is unlikely to trigger for the wrong skill, yet it underspecifies when it should fire.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks for a live docked panel (clock, ticker, countdown, status card) or a modal tool bound to a slash command in the Hermes TUI'.

Broaden trigger terms to include the widget kinds users would naturally name (ticker, clock, countdown, status card, modal, picker) so trigger_term_quality reaches full coverage.

List more than one concrete action (e.g. 'Author and dock live ambient panels and modal overlays') to lift specificity from one action to multiple.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Author") and a specific domain ("Hermes TUI dock"), but offers only a single action rather than multiple, so it is not comprehensive — not the level-3 'lists multiple specific concrete actions', yet well above the level-1 vague 'Helps with documents'.	2 / 3
Completeness	Clearly answers 'what' ("Author live widget apps for the Hermes TUI dock") but provides no explicit 'Use when...' trigger guidance, so per the rubric guideline completeness is capped at 2; it is not level 1 because the 'what' is clearly stated.	2 / 3
Trigger Term Quality	Contains natural domain terms a user would say ("widget apps", "TUI", "dock"), but lacks common variations and the specific widget kinds (clock, ticker, modal, status card) users might request, so coverage is partial rather than level-3 broad.	2 / 3
Distinctiveness Conflict Risk	The narrow "Hermes TUI dock" widget niche is highly specific with distinct triggers and is unlikely to conflict with other skills, matching the level-3 'clear niche' anchor.	3 / 3
	Total	9 / 12 Passed

Validation

81%

Warnings & errors only

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

Criteria	Description	Result
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: skills/productivity/tui-widgets/SKILL.md
Commit: d0d116b

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.