122 skills · sorted by relevance
Prepare selected pull requests for maintainer review by comparing failures with their current base, fixing authorized defects, and preserving contributor credit. Report complete or partial validation with evidence and outstanding checks before any separately authorized merge.
Cleanup and triage of the task ledgers FOUND_DEFECTS.md, CURRENT_ERRORS.md, .matrx/AGENT_TASKS.md, .matrx/ARMAN_TASKS.md. Use when invoked as /task-hygiene <step>, cleaning up tasks, defects, or errors, triaging an error dump, promoting defects, or bootstrapping these files.
The English summary is being prepared. Showing the original description.
Investigate failed Agent QA runs using logs, recorded artifacts, and local source code. Make a focused code or test-definition repair, then verify the affected behavior while keeping product and infrastructure defects visible.
Fix defects in Composio SDK through focused reproduction, root-cause analysis, regression tests that check for recurrence, and targeted verification. Use it for reported bugs, failing tests, CI regressions, runtime errors, or incorrect SDK behavior.
Review code changes for concrete defects. Use it to examine modified code when you want to check whether a change contains a bug, with the review focused on specific problems in the changes.
Diagnose and fix MSBuild property problems, including overwritten settings, ineffective conditions, and environment-dependent paths. Review defaults, list appending, and evaluation order so project files and shared build settings retain the intended values.
Diagnose and fix concrete MSBuild property defects in projects and existing shared-file hierarchies. USE FOR: conditions, defaults, append versus overwrite, last-write-wins values, OS/TFM checks, portable paths, normalization, and reviews centered on those property defects. Property defects in Directory.Build.* remain in scope, including overwritten values across parent/child imports and conditions that run before TargetFramework is set, even when the fix changes import order or moves a property group to .targets. DO NOT USE FOR: placement-only or import-only requests with no concrete property defect, such as discovering shared files or choosing which file owns a target or customization (use directory-build-organization); item operations; target structure; broad reviews without a concrete property defect; non-MSBuild work.
The English summary is being prepared. Showing the original description.
Audit REA’s automated checks and test suites to find missed failures, outdated test data, and unnecessary work. Use reproducible experiments and timing measurements to assess fixes or efficiency changes while preserving checks that catch real defects.
Review code changes without modifying files, checking surrounding code, tests, and callers for defects introduced by the change. Receive actionable findings ranked by severity, with precise file locations and a brief assessment of remaining risks.
Reproduce and fix LazyCodex or Codex defects in a temporary workspace. Verify the change with regression tests and real usage, then deliver an upstream Codex pull request or a LazyCodex issue containing the tested patch.
Review a specified code change without editing files. Checks the full diff, surrounding code, tests, and callers to identify actionable defects introduced by the change, then reports findings by severity with file and line references.
Inspect 3MF files for 3D printing, detect cylindrical holes, and resize them to a chosen diameter. Repair mesh defects and compare files while preserving BambuStudio and PrusaSlicer metadata during file repacking.
Review concrete code for exploitable security defects, including missing access checks, unsafe input handling, and exposed secrets. Report verified issues with file locations, reachable attack paths, severity, and suggested fixes.
Turn defects found during Oracle-to-PostgreSQL migration into structured bug reports. Document expected and actual behavior, reproduction steps, severity, root causes, proposed changes, and validation on both databases so teams can act on the findings.
Review completed code changes for defects, security risks, unnecessary complexity, and missing tests. Findings are verified and reported with severity, file locations, and concrete failure scenarios, with separate assessments of standards and intended behavior for larger changes.
Test user journeys affected by a branch’s changes in a real browser. Check correctness and the experience for intended users, fix small defects with regression tests, and commit fixes alongside a report documenting results and unresolved decisions.
Investigate incidents and recurring defects with structured methods such as Five Whys and Fishbone cause maps. Identify multiple contributing conditions, build a blame-free account of what happened, and propose practical changes to prevent similar failures.
Review a specified code change without editing files. Checks the full diff, surrounding code, tests, and callers to identify actionable defects introduced by the change, then reports findings by severity with file and line references.
Review OpenClaw frontend code and rendered screens for departures from Carapace design rules, accessibility issues, responsive defects, and inconsistent copy. Produce evidence-based JSON and Markdown reports that distinguish documented violations from judgment-based suggestions and guide narrowly scoped fixes.
Guide an approved defect fix from reproduction on current main through testing and independent validation. Record evidence for each operator workflow, track change size and rollback scope, and apply review records when receipt-driven development is enabled.
Review websites, apps, screenshots, or design code for redundant decoration, generic patterns, and usability defects. Receive prioritized findings tied to specific evidence, with removal or small corrections that preserve the interface’s existing design direction.
Review and refine websites and apps by finding generic decoration, inconsistent visual choices, and interface defects. Preserve the established art direction while improving hierarchy, layout, interaction states, and the connection between design choices and product needs.
Review MSBuild project files and build definitions for correctness and maintainability. Get prioritized findings with concrete recommendations, distinguishing confirmed defects from conditional risks and valid exceptions such as F# source ordering or required imports.
Qualify a check before it is allowed to clear anything — prove it can detect the failure it is meant to catch. Seeds known defects into a copy of a real artifact plus a clean control, runs the checker, and reports recall and false-positive rate into a qualification ledger. Use when the user says "does this check work", "qualify the gate", "test my reviewer", "seed defects", "vaccinate", "qualify the checks", "can I trust this review", "does it pass for the right reason", or before relying on any automated check or referee simulation for a decision that matters. NOT a code fixer and NOT a reviewer itself — it grades the grader.
The English summary is being prepared. Showing the original description.