CtrlK
BlogDocsLog inGet started
Tessl Logo

native-wsl-workspaces

Reliably inspect, create, edit, validate, and transfer files in a Windows-hosted WSL workspace. Use when a task names a WSL path, a `\\wsl.localhost` path, a Windows/WSL project location, or when remote file writes, UNC paths, mounted workspaces, and WSL shell execution may disagree.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 strong, disciplined skill body: an explicit seven-step workflow with real validation checkpoints and recovery guidance, and clean progressive disclosure across three existing bundle files. The two weaknesses are mild — a redundant conceptual sequence block and a missing copy-paste example for the short-change route.

Suggestions

Trim the "Command patterns" text block, which restates the mandatory workflow as a diagram; keep only the pointer to references/remote-execution.md and fold the route summary into the workflow steps to remove the duplication.

Add a copy-paste example of the "single noninteractive WSL command" pattern for short edits (e.g., the exact wsl.exe -d <distro> -- invocation used to apply and verify a small change in one shell), since this is the most common write route and currently has no concrete example.

In the recovery step, state concretely how the "verified transfer" is performed (e.g., naming scripts/install_verified_url.sh as the transfer mechanism) so recovery is executable rather than only conceptual.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence throughout — it never explains what WSL, drvfs, or SHA-256 are, and each step is information-dense — but the "Command patterns" text block re-sequences the already-numbered mandatory workflow ("Windows shell at C:\ → wsl.exe -d <distro> -- bash verify_wsl_workspace.sh…"), a minor redundancy a careful editor could trim. This matches anchor 4 (efficient with minor trimmable instances) rather than anchor 5's "every token earns its place".

4 / 5

Actionability

Concrete, executable guidance dominates: an exact probe invocation ("wsl.exe -d <distro> -- bash verify_wsl_workspace.sh … with --probe-write"), named scripts with roles, and a hash-verified atomic install path. It falls short of anchor 5 because the common "short change" route is only described ("use a single noninteractive WSL command from C:\, then verify the target in the same WSL shell") without a copy-paste example, leaving a minor gap.

4 / 5

Workflow Clarity

The seven-step "Mandatory workflow" is explicitly sequenced with hard validation checkpoints ("Stop if it reports /mnt, drvfs, a nonexistent directory, or a write/read/delete failure"), in-flight verification (SHA-256 record-and-verify), in-place validation (step 6), and a dedicated recovery step with hash comparison and backup retention (step 7). This matches anchor 5's explicit validation plus feedback/error-recovery loop; the "Non-negotiable constraints" section additionally functions as a checklist.

5 / 5

Progressive Disclosure

The ~40-line body is a genuine overview: it keeps the workflow in SKILL.md and defers route selection to a real, one-level-deep reference (references/remote-execution.md, which links nowhere deeper), clearly signaled ("Read [references/remote-execution.md]… before selecting a route"), with both bundled scripts referenced in the workflow steps they serve and summarized in the "Bundled resources" table. All referenced bundle files exist and navigation is easy, matching anchor 5.

5 / 5

Total

18

/

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.

This is a near-ideal description: it states a clear, comprehensive set of concrete capabilities in a distinct niche and provides an explicit, trigger-rich "Use when" clause that mirrors what a user would naturally say or paste (WSL paths, \\wsl.localhost, UNC paths). Third-person voice and tight phrasing with no filler.

DimensionReasoningScore

Specificity

The description lists five concrete actions — "inspect, create, edit, validate, and transfer files" — anchored to a specific domain ("a Windows-hosted WSL workspace"), matching the anchor's comprehensive multi-action coverage. It is not score 4 because there are no meaningful gaps in the action coverage within its declared file-operations scope.

5 / 5

Completeness

The first sentence answers "what" with concrete verbs and the second gives an explicit "Use when…" clause with concrete trigger phrases ("a task names a WSL path", "when remote file writes, UNC paths, mounted workspaces, and WSL shell execution may disagree") — a clear anchor-5 match. It is not 4 because the "when" guidance is fully explicit, not merely present.

5 / 5

Trigger Term Quality

It covers natural terms comprehensively for the domain: "WSL path", "\\wsl.localhost path", "Windows/WSL project location", "UNC paths", "mounted workspaces", and "WSL shell execution", including synonyms and the literal path format a user would paste. Only marginal variants (e.g. \\wsl$ or "distro") are missing, which does not break comprehensiveness, so it fits anchor 5 rather than anchor 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (Windows/WSL path duality) and every trigger term is WSL-anchored, so the risk of firing for a generic file-transfer or remote-execution skill is minimal. Even the broadest phrase ("remote file writes… mounted workspaces") is qualified by the WSL context in the same sentence, so anchor 5 fits better than anchor 4's "minor overlap risk".

5 / 5

Total

20

/

20

Passed

Validation

100%

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
pvnkmnk/AgenticSelfHostSkills
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.