CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An excellent operational skill body: nearly everything is executable commands, verified file paths, or non-obvious project invariants, with clear sequenced verification workflows and real error-recovery guidance. The bundled release-audit script is appropriately externalized and well-signaled. Remaining improvements are marginal: deduplicate the agent-system guidance and move the deep-link history and release-decision detail into reference files.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious project specifics ("The `--` is required so Forge forwards the flag to Electron", "EDITOR_BASE_URL lives in `desktop/src/env.ts`", the post-hydration screenshot caveat) and assumes competence in Electron, Forge, and Next.js without explaining basics. It is not a 5 because of minor duplication — the agent-system redirect appears both in the intro and again in 'When to use' — and the intro paragraph repeats scope information. It is well above anchor 3 since there is no generic concept explanation or padding.

4 / 5

Actionability

Guidance is fully executable and copy-paste ready: the two-terminal dev commands (`pnpm --filter editor dev`, `pnpm --dir desktop dev`), CDP launch and probes (`curl -s http://127.0.0.1:9222/json`), a complete runnable Playwright probe script, kill commands, `chrome://inspect/#devices` + `localhost:5858` main-process inspection, the bundled audit script invocation, and owner checks (`pnpm --dir desktop typecheck`, `pnpm --dir desktop test`). The only vagueness is an edge-case fallback (importing playwright-core from pnpm's `.pnpm` path), which still offers three concrete options — matching anchor 5's 'specific examples cover the common cases'.

5 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with validation checkpoints: the Verification section is a 4-step sequence ending in explicit owner checks, and error-recovery guidance appears throughout — "electron-forge start can return the shell prompt while Electron stays alive. Confirm with: lsof...", the playwright-core resolution fallbacks, and the instruction to wait for a post-hydration element before judging bridge state. This matches anchor 5's clear sequence, explicit validation, and error-recovery feedback; anchor 4's 'minor validation gaps' is less accurate since each workflow carries its own checkpoint.

5 / 5

Progressive Disclosure

The body is well-sectioned (Shape, Running Locally, CDP/Playwright, Bridge, Boundaries, Security, Release impact, Verification, Pointers) and the single bundle file (`scripts/audit-release-impact.sh`, verified to exist) is clearly signaled with its output described, keeping 110 lines of audit logic out of the body. It stops short of anchor 5 because some deep-dive content is inlined rather than split into reference files (the dense #955 deep-link pointer with its full history, and the detailed release-coupling decision rules), leaving minor organization gaps consistent with anchor 4.

4 / 5

Total

18

/

20

Passed

Description

87%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 highly effective description: it names a specific niche, lists concrete capabilities, and gives an explicit 'Use for' clause with path-level and identifier-level triggers, plus explicit deconfliction with the adjacent agent-system skill. Its only weakness is that the capability list is component-oriented rather than action-oriented and lacks a few natural synonyms.

DimensionReasoningScore

Specificity

The description enumerates many concrete, domain-specific capabilities ("BrowserWindow, preload, `window.grida`, menus, protocol/deep links, file associations, Forge, path-scoped bridge security, Electron-only UI bugs, and CDP / Playwright verification"), but it is largely a component/topic list rather than a list of concrete actions, and packaging/auto-update coverage is only implied via "coordinated release". It exceeds anchor 3 (only 1-2 concrete actions) but does not match anchor 5's action-oriented comprehensiveness.

4 / 5

Completeness

Both questions are answered explicitly: the "what" ("Grida Desktop Electron shell and release-impact work: BrowserWindow, preload, `window.grida`...") and a concrete "when" ("Use for `desktop/`, `editor/app/desktop/**`... and deciding whether linked-package or hosted-renderer changes require a native Desktop version bump or coordinated release"), plus delegation guidance to `agent-system`. This matches anchor 5 exactly; anchor 4's 'when could be more explicit' does not apply since the Use-for clause lists concrete triggers.

5 / 5

Trigger Term Quality

Strong natural trigger coverage for this repository: "Use for `desktop/`, `editor/app/desktop/**`, `editor/scaffolds/desktop/**`, `editor/lib/desktop/**`, `/desktop/*` CSP, GRIDA-SEC-004" plus terms like Electron, Forge, deep links, and window.grida. It falls short of anchor 5's comprehensive synonym coverage (e.g., no "native app", "desktop app", or "packaging" phrasing) but is well above anchor 3's partial keyword set.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (the Grida Desktop Electron shell) with path-scoped, project-specific triggers (`window.grida`, GRIDA-SEC-004, `desktop/**`) and proactively resolves the main adjacent-skill overlap within the description itself ("For implementing daemon/agent-tenant core behavior, use `agent-system` as well"), matching anchor 5's minimal conflict risk. The residual overlap with a React skill on `editor/app/desktop/**` is minor and those paths are scoped to this skill's bridge surface.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

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.