try-fix skill: Apply multi-model review recommendations #33762
Merged
+166
−59
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Co-authored-by: PureWeen <5375137+PureWeen@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Update markdown documentation based on PR 33747
Improve try-fix skill documentation with mandatory validation and sequential execution constraints
Jan 29, 2026
Changes based on consolidated review from Gemini 3 Pro, Claude Sonnet 4.5, Codex 5.2, and Claude Opus 4.5: - Add compatibility field to frontmatter (PowerShell, git, device requirements) - Delete redundant references/output-structure.md (content already in SKILL.md) - Standardize result values to Pass/Fail/Blocked (was PASS/FAIL) - Add Blocked as valid result.txt value for device unavailability - Add Tee-Object capture to Step 6 test command for test-output.log - Reduce warning markers from 8 to 4 (kept critical ones only) All changes validated against agentskills.io specification.
PureWeen
changed the title
Contributor
There was a problem hiding this comment.
Pull request overview
Updates the try-fix skill documentation to enforce serial execution and a stricter, verifiable artifact/output workflow per attempt.
Changes:
- Documented a critical “sequential execution only” constraint to prevent concurrent try-fix runs from corrupting state and device testing.
- Made the output directory + per-attempt artifacts mandatory, including a checklist and explicit Pass/Fail/Blocked criteria.
- Removed the standalone output-structure reference doc after folding guidance into the main skill doc.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 6 comments.
| File | Description |
|---|---|
.github/skills/try-fix/SKILL.md |
Adds sequential-execution constraints, mandatory artifact structure/checks, and clarified pass/fail criteria. |
.github/skills/try-fix/references/output-structure.md |
Removes the separate output-structure reference after consolidating guidance into SKILL.md. |
Cherry-picked from PR #33747. When using -DryRun, the script now properly: - Extracts existing TRY-FIX content to preserve previous attempts - Checks if the current attempt already exists (replace vs append) - Maintains the same logic as the GitHub comment update path
- Use *>&1 for all-stream capture (Write-Host uses Information stream) - Clarify comment about setting issue number explicitly - Add Blocked status to Pass/Fail table for consistency - Update analysis template to include Blocked option - Add test-output.log to verification checklist
kubaflo
approved these changes
Jan 29, 2026
kubaflo
pushed a commit
to kubaflo/maui
that referenced
this pull request
Feb 2, 2026
> [!NOTE] > Are you waiting for the changes in this PR to be merged? > It would be very helpful if you could [test the resulting artifacts](https://github.com/dotnet/maui/wiki/Testing-PR-Builds) from this PR and let us know in a comment if this change resolves your issue. Thank you! ## Summary Updates the try-fix skill based on consolidated review from 4 AI models (Gemini 3 Pro, Claude Sonnet 4.5, Codex 5.2, Claude Opus 4.5), validated against the [agentskills.io specification](https://agentskills.io/specification). ## Changes | Change | Rationale | |--------|-----------| | Add `compatibility` field to frontmatter | Documents PowerShell, git, and device requirements per spec | | Delete `references/output-structure.md` | Content already in SKILL.md - eliminates duplication | | Standardize result values to `Pass`/`Fail`/`Blocked` | Was inconsistent (`PASS`/`FAIL` vs `Pass`/`Fail`) | | Add `Blocked` as valid result.txt value | For device/emulator unavailability scenarios | | Add `Tee-Object` capture to Step 6 | Fixes missing `test-output.log` capture in workflow | | Reduce 🚨 markers from 8 to 4 | Kept only critical warnings to reduce warning fatigue | ## Validation - ✅ SKILL.md under 500 lines (407 lines) - ✅ Under 5000 token recommendation - ✅ No prohibited auxiliary files - ✅ All frontmatter fields valid per spec - ✅ Progressive disclosure maintained (references/ for compile-errors.md, example-invocation.md) --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: PureWeen <5375137+PureWeen@users.noreply.github.com> Co-authored-by: Shane Neuville <shneuvil@microsoft.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Note
Are you waiting for the changes in this PR to be merged?
It would be very helpful if you could test the resulting artifacts from this PR and let us know in a comment if this change resolves your issue. Thank you!
Summary
Updates the try-fix skill based on consolidated review from 4 AI models (Gemini 3 Pro, Claude Sonnet 4.5, Codex 5.2, Claude Opus 4.5), validated against the agentskills.io specification.
Changes
compatibilityfield to frontmatterreferences/output-structure.mdPass/Fail/BlockedPASS/FAILvsPass/Fail)Blockedas valid result.txt valueTee-Objectcapture to Step 6test-output.logcapture in workflowValidation