CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

makepad-event-action

CRITICAL: Use for Makepad event and action handling. Triggers on: makepad event, makepad action, Event enum, ActionTrait, handle_event, MouseDown, KeyDown, TouchUpdate, Hit, FingerDown, post_action, makepad 事件, makepad action, 事件处理

Quality

72%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/makepad-event-action/SKILL.md

The canonical home for this skill is makepad-event-action in administrakt0r/AI-Agents-Safe-Coding-Skills

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.

The content is an efficient, actionable Makepad API reference with executable patterns and a sensible fallback workflow for missing docs, but its structure is defective: it names two reference files that are absent from the bundle while inlining the very API-detail content those files should hold. Shipping the reference files (or moving the enum/helper listings into them) would resolve the main weakness.

Suggestions

Create the referenced bundle files ./references/event-system.md and ./references/action-system.md (or remove the references) — as delivered, both links are dead and every invocation falls into the completeness-check fallback path.

Move the full Event and Hit enum listings and the Widget Action Helpers signatures into the reference files, keeping SKILL.md to a short overview plus one handle_event and one action-capture example.

Replace the 'Version / Last Updated: 2026-01-19' header (or fold it into a clearly labeled versioning/deprecation section) and define MyWidgetAction once so the main code example is self-contained.

DimensionReasoningScore

Conciseness

The body is dense and factual — API enums, idiomatic code patterns, and a short answering checklist with almost no conceptual padding about things Claude already knows. Minor trims are possible: the version/last-updated header is time-sensitive information not placed in a deprecation section, and the 'IMPORTANT: Documentation Completeness Check' section adds process overhead, keeping it below the lean 5 anchor.

4 / 5

Actionability

Code is concrete and executable Makepad idiom (event.hits with Hit variants, cx.action/capture_actions, DefaultNone derive, start_timer/new_next_frame) covering the common cases. Minor gaps remain: 'MyWidgetAction' is referenced but never defined, the Widget Action Helpers section is signature-only, and the timer example compares against self.timer/self.next_frame fields whose declaration is implied, so it is not fully copy-paste ready.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced: the Documentation Completeness Check has an explicit failure branch (missing file → inform user, answer from SKILL.md patterns + built-in knowledge), the Event Flow section gives a 6-step propagation order, and 'When Answering Questions' is a 5-point checklist. It is not a destructive or batch skill so no validation loop is required, but the flow sections describe behavior rather than guiding a procedure with checkpoints, keeping it just below the 5 anchor.

4 / 5

Progressive Disclosure

The body points to './references/event-system.md' and './references/action-system.md', but no references/ directory exists in the bundle — the referenced files are missing, so navigation is broken. Additionally, ~200 lines of API reference (full Event and Hit enum listings, widget action helper signatures) are inlined in SKILL.md even though separate reference files are already named for exactly this material, matching the anchor 'content that clearly belongs in separate files is inlined'. The section headers and clearly labeled Documentation section are what keep it from being scored lower still.

2 / 5

Total

14

/

20

Passed

Description

65%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 has strong, explicit trigger guidance with a clear Makepad niche, but its capability statement is thin — it names the domain without describing what the skill concretely does, and prefixes it with attention-fluff ('CRITICAL:') that adds no information. Tightening the what-clause to enumerate concrete capabilities would lift it into the top tier.

Suggestions

Replace the generic 'Use for Makepad event and action handling' with 2–3 concrete capabilities, e.g., 'Handle mouse, keyboard, and touch events in Makepad widgets; define and emit actions; capture child-widget actions' — this would raise the specificity score toward the 4–5 anchors.

Add a few missing natural trigger terms users would actually say: 'click', 'scroll event', 'key input', 'event propagation', and qualified forms like 'makepad MouseDown' to reduce overlap with other GUI-framework skills.

Drop the 'CRITICAL:' prefix; it is emphasis fluff that occupies description budget without stating a capability or trigger.

DimensionReasoningScore

Specificity

The description states only 'Use for Makepad event and action handling' — it names the domain with the generic action 'handling' but never lists concrete capabilities (e.g., handling mouse/keyboard/touch events, defining and emitting widget actions, capturing child actions). The long trigger list names API identifiers, not actions the skill performs, matching the anchor 'Names the domain but actions are minimal or generic' rather than the 3-anchor, which requires 1–2 explicitly stated concrete actions.

2 / 5

Completeness

Both parts are present: the 'what' ('Makepad event and action handling') and an explicit 'when' ('Triggers on: …' with concrete trigger phrases). It falls short of the 5 anchor because the 'what' is a single generic phrase rather than an enumerated list of concrete capabilities like the 5-anchor example.

4 / 5

Trigger Term Quality

Triggers include natural user-facing and API terms — 'makepad event', 'handle_event', 'MouseDown', 'KeyDown', 'TouchUpdate', 'post_action', plus Chinese variants ('makepad 事件', '事件处理') — giving good coverage of how a Makepad developer would phrase a request. A few natural terms are missing (e.g., 'click', 'scroll', 'key input', 'event propagation'), keeping it below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

'Makepad' plus framework-specific identifiers (ActionTrait, post_action) establish a clear niche with minimal conflict risk. However, bare generic GUI terms in the trigger list ('MouseDown', 'KeyDown', 'Hit', 'FingerDown') lack a makepad qualifier and could overlap with other GUI-framework skills, so it does not fully meet the 5 anchor's 'minimal conflict risk'.

4 / 5

Total

14

/

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.

Validation — 15 / 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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/makepad-event-action/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.