CtrlK
BlogDocsLog inGet started
Tessl Logo

windows-compatibility

Cross-platform path handling and command patterns

48

Quality

51%

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 ./.copilot/skills/windows-compatibility/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 skill body is a strong, lean pattern catalog: concrete do/don't rules backed by executable TypeScript and PowerShell examples, with validation checkpoints in its git and repair workflows. Its weaknesses are minor — a duplicated bullet, an undefined safeTimestamp() utility, and a dangling reference to a script that is not part of the bundle.

Suggestions

Deduplicate the "Resolve first, compare second" bullets (stated at both the top and bottom of the path-comparison section) and merge the repeated case-sensitivity rationale into one statement.

Show the actual implementation of the safeTimestamp() utility (or point to where it lives) rather than prescribing it by name only, and clarify in the repair workflow how to perform step 2's content-difference exclusion.

DimensionReasoningScore

Conciseness

The body is a dense pattern catalog that assumes Claude's competence — no basic concepts are explained, and every rule carries its concrete justification ("ISO 8601 format ... is illegal on Windows"). It falls short of anchor 5 because "Resolve first, compare second" is stated twice as separate bullets and the path-comparison section reiterates its case-sensitivity rationale multiple times, padding that could be trimmed.

4 / 5

Actionability

Guidance is overwhelmingly executable: a complete TypeScript `isPathWithin()` implementation, a full PowerShell staging/commit workflow using `git commit -F $msgFile`, and specific commands like `git checkout-index -f` and `git diff --cached --quiet`, plus concrete counter-examples. Not anchor 5 because `safeTimestamp()` is mandated as a utility but its implementation is never provided, and the PowerShell staging filter is hardcoded to specific .squad files without noting how to adapt it.

4 / 5

Workflow Clarity

The two real workflows are clearly sequenced with checkpoints: the CRLF repair flow ends with "Re-measure the complete repair set and report repaired, skipped, and remaining paths", and the commit flow gates on `git diff --cached --quiet` / `$LASTEXITCODE -ne 0`. It stays at anchor 4 rather than 5 because the repair workflow's step 2 ("Exclude files with a real content difference") gives no command or method for performing the exclusion, leaving the most delicate step implicit.

4 / 5

Progressive Disclosure

The single file is well organized (Context → Patterns subsections → Examples → Anti-Patterns) with each pattern clearly signaled. Not anchor 5: the body cites `scripts/fix-crlf-worktree.mjs`, which does not exist in the bundle, and the path-comparison section is long and detailed enough that it arguably belongs in its own reference file — minor organization gaps consistent with anchor 4.

4 / 5

Total

16

/

20

Passed

Description

28%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 is a concise topic label that correctly identifies the skill's domain but fails as a trigger: it states no concrete capabilities, no use-when guidance, and none of the platform-specific keywords (Windows, PowerShell, case sensitivity, git) that would let a user or Claude reliably select this skill. It would be skipped in most situations where it is actually needed.

Suggestions

Add an explicit trigger clause, e.g. "Use when writing file paths, git commands, or scripts that must work on Windows as well as macOS/Linux, or when a bug traces to platform-specific path or shell assumptions."

Include the natural trigger terms users actually say: "Windows", "PowerShell", "backslashes", "case-sensitive macOS", "git commit on Windows", "path traversal".

List 2-3 concrete actions in third person, e.g. "Sanitizes ISO timestamps for Windows-legal filenames, provides Windows-safe git commit and staging patterns, and confines resolved paths to a root directory with volume-aware case handling."

DimensionReasoningScore

Specificity

The description names the domain ("Cross-platform path handling and command patterns") but lists no concrete actions — "handling" and "patterns" are generic labels, not capabilities like 'sanitize timestamps' or 'confine paths to a root'. It is above anchor 1 because the domain is genuinely named, but does not reach anchor 3 since no concrete action is stated.

2 / 5

Completeness

It offers a vague 'what' ("path handling and command patterns") and entirely lacks a 'when' — no "Use when..." clause or equivalent trigger guidance. This is an exact match for anchor 2 ('vague what and no when') and the judging guideline caps it at 3 even if a when were weakly implied.

2 / 5

Trigger Term Quality

Only "cross-platform", "path handling", and "command patterns" appear — none of the natural phrases a user would say when needing this skill ("Windows", "PowerShell", "git on Windows", "case-sensitive macOS") are present. This matches anchor 2 (a couple of generic keywords, natural phrases missing) rather than anchor 3, which would require at least the key variations such as the platform names.

2 / 5

Distinctiveness Conflict Risk

"Cross-platform" carves out a niche, but "path handling" and "command patterns" are broad enough to overlap with general file, shell, and git skills. Anchor 3 ('somewhat specific but could still overlap') fits; anchor 4 would require more distinct triggers like named platforms or specific commands.

3 / 5

Total

9

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
bradygaster/squad
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.