CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

57

Quality

66%

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 ./.github/skills/try-fix/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is exceptionally actionable and workflow-clear, with strong validation gates and properly structured references. Its sole meaningful weakness is conciseness: it over-explains rationale and repeats guardrails, inflating the token budget beyond what Claude needs.

Suggestions

Collapse the repeated baseline/restore warnings into a single canonical block referenced from Steps 2, 8, and 9 instead of restating each time.

Trim explanatory prose like the Step 7.5 drift-commentary paragraphs and the 'Why before testing?' callout to one line each, trusting Claude to grasp the rationale.

Compress the parallel-execution warning from a multi-bullet 'If run in parallel' list into a single 'Never run in parallel: shared files and device cause conflicts' statement.

DimensionReasoningScore

Conciseness

The body is heavily padded: it re-explains why parallel runs are bad over multiple bullets, repeats the baseline/restore guidance in Steps 2, 8, and 9, and includes lengthy prose rationales (e.g. Step 7.5's drift-detection commentary and the 'Why before testing?' callout) that assume Claude needs concepts it already knows.

1 / 3

Actionability

Provides concrete, copy-paste PowerShell commands for every step (directory setup, baseline, self-review, test scripts, artifact capture), explicit file-existence gates, and a full results template with exact field formats.

3 / 3

Workflow Clarity

An explicit 10-step (plus 7.5) sequence with mandatory validation checkpoints (baseline verification, JSON-parse check, artifact gate deferred until after restore, drift detection), iteration limits, and a Pass/Fail/Blocked decision matrix.

3 / 3

Progressive Disclosure

Body is an overview that pushes detail to real one-level-deep references (references/compile-errors.md, references/example-invocation.md), both of which exist as actual files, with clearly signaled inline links.

3 / 3

Total

10

/

12

Passed

Description

70%

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 concrete and clearly differentiated, with explicit 'what' actions and a distinct niche around independent fix alternatives. Its main weakness is the 'when to use' framing, which leans on technical/invoke-style language rather than natural user triggers.

Suggestions

Add a clearer natural-language 'Use when...' clause naming user-style triggers (e.g., 'Use when asked to try another way to fix a bug that prior attempts missed').

Lead with the user-facing trigger terms before the invocation contract (problem, test command, target files) so the description matches how a user would phrase the need.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'Attempts ONE alternative fix', 'tests it empirically', and 'reports results', and names the operational inputs (problem, test command, target files, hints).

3 / 3

Completeness

It states what the skill does and offers 'Use when CI or an agent needs...', but there is no crisp natural-language trigger clause equivalent to 'Use when the user asks...', and the 'when' guidance is mixed with operational invocation detail.

2 / 3

Trigger Term Quality

Includes relevant phrases like 'try independent fix alternatives' and 'CI or an agent needs to try', but the natural trigger terms a user would say are sparse and somewhat technical ('alternative fix', 'PR fixes').

2 / 3

Distinctiveness Conflict Risk

The 'ALWAYS explores a DIFFERENT approach from existing PR fixes' framing carves out a clear niche (independent fix alternatives) unlikely to overlap with general review or test skills.

3 / 3

Total

10

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (576 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
dotnet/maui
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.