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

96%

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

Quality

Content

93%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.

A lean, highly actionable SKILL.md body that loads Claude with repo-specific operational knowledge (commands, paths, boundaries, verification) instead of generic concepts. Its only soft spot is workflow_clarity, where the primary verification flow could state the error-recovery feedback loop explicitly rather than leave it implicit.

Suggestions

In the 'Verification' numbered list, add an explicit feedback loop after the owner checks (e.g. 'If typecheck/test fails: fix the reported issues and re-run until green before handoff').

Spell out the release-impact decision as a validate-then-act sequence: run the audit, then for each branch state the corrective action if the condition is unmet, rather than only listing outcomes.

Consider extracting the dense deep-link/protocol-router detail in the 'Pointers' bullet into a short `references/deep-links.md` and linking one level deep to tighten the main body.

Dimension	Reasoning	Score
Conciseness	The body is dense, repo-specific operational detail and assumes Claude's competence — it never explains what Electron, Next.js, CSP, or CDP are — so every section earns its tokens rather than padding.	5 / 5
Actionability	Copy-paste-ready commands (`pnpm --dir desktop dev`, `lsof -iTCP:9222`, CDP probe curls), a runnable Playwright probe, and explicit `pnpm --dir desktop typecheck`/`test` owner checks give fully executable guidance across the common cases.	5 / 5
Workflow Clarity	Sequenced workflows (two-terminal setup, numbered verification list, release-impact decision flow) include checkpoints like confirming Electron is alive and waiting for post-hydration bridge state, but the canonical 'if validation fails → fix → re-run' feedback loop is implied rather than spelled out.	4 / 5
Progressive Disclosure	Clean section structure with only one-level-deep references — the referenced `scripts/audit-release-impact.sh` bundle file exists on disk — plus a 'Pointers' section for navigation and no nested reference chains.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An exceptionally well-crafted description: it states a precise capability surface, gives concrete path/trigger guidance for when to use it, and explicitly routes overlapping work to `agent-system` to avoid misfiring. It earns top marks across all four dimensions with no verbosity or over-claiming.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete capabilities — BrowserWindow, preload, `window.grida`, menus, protocol/deep links, file associations, Forge, path-scoped bridge security, and CDP/Playwright verification — with no vague filler, matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers 'what' (the enumerated capability surface) and 'when' (the 'Use for ...' trigger list with concrete paths), and adds boundary routing to `agent-system`, matching the both-what-and-when anchor.	5 / 5
Trigger Term Quality	Natural repo trigger terms appear with synonyms and path variants (`desktop/`, `editor/app/desktop/`, `editor/scaffolds/desktop/`, `editor/lib/desktop/*`, `/desktop/` CSP, GRIDA-SEC-004, Electron, Forge), giving comprehensive coverage a user would actually cite.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Grida Desktop Electron shell only) with distinct triggers and explicit de-confliction ('For implementing daemon/agent-tenant core behavior, use `agent-system`'), giving minimal conflict risk.	5 / 5
	Total	20 / 20 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: 03fb751

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.