Tessl • The management layer for AI agent skills

An exemplary skill body: lean, entirely project-specific, with executable code patterns, explicit guardrails (no new assertion kinds, no snapshot reuse, prefer TUI over invoke_git), and validation guidance. Nothing to trim and no structural gaps.

Dimension	Reasoning	Score
Conciseness	Every line carries project-specific knowledge Claude could not infer — harness APIs ("test_status_tui", "input_then_render"), snapshot conventions, and exact paths ("crates/but/src/command/legacy/status/tui/tests/"). No padding or explanations of concepts Claude already knows.	5 / 5
Actionability	Fully executable guidance: a complete copy-paste-ready Rust test pattern, concrete input-driving examples for every key type, and exact commands ("cargo test -p but <test-name>", "SNAPSHOTS=overwrite cargo test -p but <test-name>").	5 / 5
Workflow Clarity	The basic pattern is unambiguous and the skill includes explicit validation ("cargo test -p but tui ... Do this after changing things") plus an error-recovery feedback loop ("If a test fails the output will include the rendered state ... way of inspecting the state"). Not a destructive/batch process, so no validation cap applies.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed; the ~78-line body is organized into tight sections (where tests live, pattern, driving, assertions, running) with clearly signaled one-level pointers to the two harness util files for specialized assertions.	5 / 5
	Total	20 / 20 Passed

Description

73%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 distinct, well-targeted trigger description for a narrow niche, weakened only by its lack of a capability statement. It answers "when" excellently but leaves "what the skill provides" implicit.

Suggestions

Add a capability statement before the trigger clause, e.g. "Guides writing Ratatui TUI tests using GitButler's snapshot test harness and assertions. Use when adding or modifying tests for one of GitButler's Ratatui TUIs."

Include natural trigger variations users might say, such as "snapshot tests", "TUI test harness", or "terminal UI tests", to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("GitButler's Ratatui TUIs") and 1-2 concrete actions ("adding or modifying tests"), but does not mention what the skill actually provides — the test harness, snapshot assertions, or running conventions. Matches anchor 3; anchor 4 would require several specific actions.	3 / 5
Completeness	The "when" is explicit and concrete ("Use when adding or modifying tests for one of GitButler's Ratatui TUIs"), but the description is entirely a trigger clause — the "what" (guidance on harness patterns, assertions, and running tests) is only implied, never stated. Falls between anchors 4 and 5.	4 / 5
Trigger Term Quality	Good natural keyword coverage — "tests", "TUI", "Ratatui", "GitButlet" — that a contributor would plausibly say. Missing common variations like "snapshot tests", "test harness", or "terminal UI".	4 / 5
Distinctiveness Conflict Risk	"one of GitButler's Ratatui TUIs" carves out a highly specific niche with distinct triggers; virtually no overlap risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gitbutlerapp/gitbutler
Path: .agents/skills/tui-tests/SKILL.md
Revision: 217a8ce

Reviewed: 26 days ago

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.

tui-tests

Table of Contents

Is this your skill?