desktop

Grida Desktop Electron shell and release-impact work: BrowserWindow, preload, `window.grida`, menus, protocol/deep links, file associations, Forge, path-scoped bridge security, Electron-only UI bugs, and CDP / Playwright verification. Use for `desktop/`, `editor/app/desktop/**`, `editor/scaffolds/desktop/**`, `editor/lib/desktop/**`, `/desktop/*` CSP, GRIDA-SEC-004, and deciding whether linked-package or hosted-renderer changes require a native Desktop version bump or coordinated release. For implementing daemon/agent-tenant core behavior, use `agent-system` as well.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

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

A strong, actionable body with executable commands, clear sequenced workflows, and validation checkpoints, supported by a real referenced bundle script. Its main weakness is verbosity from structural redundancy across the Shape, Boundaries, and Pointers sections.

Suggestions

Consolidate the overlap between the Shape diagram, the Boundaries table, and the Pointers list into a single 'layout' section to cut redundancy and reduce length.

Tighten the long Pointers bullet for the deep-link scheme (#955) into a one-line pointer with the detail moved to a reference, so the overview stays scannable.

Consider extracting the CDP/Playwright verification recipes into a references file referenced one level deep, keeping SKILL.md focused on the minimal probe.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with no concept-explanation padding, but it is long (~315 lines) with notable redundancy — the Boundaries table, Pointers list, and Shape/invariants all restate the same structure — so it could be tightened.	2 / 3
Actionability	It provides copy-paste-ready commands and code throughout — two-terminal `pnpm` setup, CDP `curl` probes, a Playwright `connectOverCDP` snippet, clean kill commands, and the `audit-release-impact.sh` invocation — fully executable guidance.	3 / 3
Workflow Clarity	Multi-step processes are sequenced with explicit checkpoints: a numbered Verification checklist with `typecheck`/`test` owner checks and a cold-reload step, plus a decision procedure for release impact that requires a recorded handoff line.	3 / 3
Progressive Disclosure	SKILL.md is a well-sectioned overview; the only bundle file (`scripts/audit-release-impact.sh`) exists and is referenced one level deep from repo root, and adjacent skills (agent-system, security, code-react) are clearly signaled as links.	3 / 3
	Total	11 / 12 Passed

Description

85%

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 highly specific, well-scoped description that clearly states both what it does and when to use it, with strong distinctiveness via explicit path triggers and a sibling-skill hand-off. The only weakness is trigger phrasing dominated by path-globs and internal issue IDs rather than natural user language.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete capabilities — 'BrowserWindow, preload, `window.grida`, menus, protocol/deep links, file associations, Forge, path-scoped bridge security ... CDP / Playwright verification' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It states what the skill covers ('Grida Desktop Electron shell and release-impact work: ...') and gives an explicit 'Use for `desktop/`, ...' trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	Domain terms like desktop, Electron, deep links, file associations, and CDP/Playwright are present, but the triggers lean heavily on path-globs (`editor/app/desktop/**`) and internal IDs (GRIDA-SEC-004) rather than natural-language phrasings a user would say, so coverage is good but not the natural-variation ideal of level 3.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to the Electron shell with path-scoped triggers and an explicit hand-off ('use `agent-system` as well' for the daemon core), making conflict with adjacent skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: gridaco/grida
Path: .agents/skills/desktop/SKILL.md
Commit: 2e0d276

Reviewed: 3 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.