try-fix

Attempts ONE alternative fix for a bug, tests it empirically, and reports results. ALWAYS explores a DIFFERENT approach from existing PR fixes. Use when CI or an agent needs to try independent fix alternatives. Invoke with problem description, test command, target files, and optional hints.

Quality

86%

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

81%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 thorough, highly actionable workflow with excellent sequencing and validation gates for a destructive-operation skill. The main weakness is verbosity from restating a few critical safety rules multiple times rather than consolidating them.

Suggestions

Consolidate the script-only-restore, preserve-untracked, and wait-for-completion rules into a single authoritative statement and reference it from Steps 2/9 and the Error Handling table instead of restating each in full.

Consider moving the detailed Step 6 self-review procedure or the reviewer-findings JSON schema into a references file so SKILL.md reads more like an overview pointing to detail.

Trim the repeated Pass/Fail semantics in Completion Criteria — the table already appears once; cross-reference it rather than restating the 'NEVER claim Pass' list elsewhere.

Dimension	Reasoning	Score
Conciseness	The body is actionable and avoids explaining concepts Claude already knows, but critical rules (script-only restore, preserve-untracked, wait-for-completion) are restated three to four times across Core Principles, Steps 2/9, and the Error Handling table, which could be consolidated.	3 / 5
Actionability	Provides copy-paste-ready PowerShell/bash commands (git diff, EstablishBrokenBaseline.ps1, Tee-Object, Select-String, dotnet test) and complete file-creation examples including the reviewer-findings JSON schema, covering the common cases.	5 / 5
Workflow Clarity	An 11-step numbered sequence with explicit validation checkpoints (baseline-verified marker, pre-test self-review, Step 7.5 drift-detection refresh, deferred-throw artifact gate) and a test iteration feedback loop for a destructive/batch operation.	5 / 5
Progressive Disclosure	Two well-signaled one-level-deep references (references/compile-errors.md, references/example-invocation.md, both real files) with clear section structure, but the ~650-line body keeps most detailed procedure inline rather than splitting it out, which is good but not fully an overview-pointing-to-details.	4 / 5
	Total	17 / 20 Passed

Description

92%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 strong, specific description that clearly states the skill's single-purpose action, explicit trigger conditions, and required inputs in third person. The only minor gap is synonym coverage in trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Attempts ONE alternative fix for a bug", "tests it empirically", "reports results", "ALWAYS explores a DIFFERENT approach from existing PR fixes", and specifies the invocation inputs (problem, test command, target files, hints), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ("Attempts ONE alternative fix… tests it empirically, and reports results") and when ("Use when CI or an agent needs to try independent fix alternatives") with concrete trigger phrasing and required inputs.	5 / 5
Trigger Term Quality	Good natural-term coverage with "independent fix alternatives", "CI or an agent needs to try", "existing PR fixes", and "DIFFERENT approach"; a few common synonyms (e.g., "bug fix", "alternative patch") are missing, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	A clear niche — proposing a single alternative fix distinct from existing PR fixes for CI/agent contexts — with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (653 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: dotnet/maui
Path: .github/skills/try-fix/SKILL.md
Commit: 90afade

Reviewed: ~16 hours 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.