26 skills (repositories by cobusgreyling) · sorted by popularity
Review dependency manifests and lockfiles to find outdated packages and known security vulnerabilities. Group proposed updates by version change, report current and suggested versions, and identify updates that need human review.
Turns changelog-scan results into a readable, categorized release notes draft. Places breaking changes and security items at the top and ends with a human review note, providing a proposal for review.
Analyze failures in CI, the automated checks run during development. Identify the failing job and step, classify the likely cause, and suggest a small fix, continued monitoring, or human review.
Review open pull requests, or proposed code changes, for automated checks, approvals, blocking comments, and conflicts. Assess whether project requirements allow merging, and suggest a next step such as a small fix, rebase, or human review.
Drafts a token budget extension request when an autonomous loop approaches its daily limit and high priority work remains. Uses logged results and remaining issues to justify the request, then pauses until a human increases the budget.
Check estimated token usage against daily limits before and after each automated loop run. Switch to reporting only, exit early when required, and record run outcomes so repeated agent work stays within configured limits.
Fix one clearly defined code issue, such as a failed automated check, review comment, or typo, with the smallest necessary change. Run relevant tests and summarize the changes, verification results, and any need for human review.
Review recent changes, automated test failures, issues, and conversations to prioritize engineering work. Produce a concise report separating urgent actions, watch items, noise, and state updates, with suggested next steps and rough effort estimates.
Load project rules before an agent starts work, then apply restrictions to file edits, tests, pushes, and merges. Check pause settings and identify actions that require human approval.
Scan merges and commits since the previous release to collect user-facing changes for a changelog. Produce structured entries and a summary, with explicit lists of breaking changes and security signals.
Classify failures in CI, automated checks run during development, to distinguish code regressions, temporary infrastructure problems, security test failures, and inconsistent results. Record each failure's category, suggested next action, and attempt count in a structured report.
Independently checks code changes against the original issue, runs tests, and verifies that edits stay within scope. Produces an approval, rejection, or request for human judgment, supported by test results and specific findings.
Scan recent merges to main for unfinished tasks, deprecated APIs, broken documentation links, and obsolete feature flags. Get a concise report with file locations, risk, effort, and suggested follow-up actions for each merge.
Turn a structured change list into a categorized release notes draft for users. Follow the project's writing style, highlight breaking changes and security items, and include upgrade guidance where evident, leaving publication to human review.
Review merged pull requests and significant commits within a release window, then organize features, fixes, breaking changes, and security signals into structured source material for drafting release notes.
Scan recent merges, pull requests, and commits for release note material. Produce structured entries and a summary with PR references, highlighting breaking changes and security items while filtering routine dependency and bot noise.
Reviews recent changes, CI failures, open issues, pull requests, and conversations to produce a prioritized findings report. It separates urgent work from monitoring and noise, suggests next actions, and records facts for the next automated review cycle.
Inspect recent merges for leftover debug code, TODO comments, lint warnings, and technical debt, meaning deferred maintenance work. Create a prioritized cleanup list that separates small fix candidates from issues requiring human judgment.
Scans merged pull requests and commits since a chosen reference, using titles, labels, milestones, and messages to categorize changes. Produces a release notes draft, highlights breaking changes and security items, and records the scan window.
Track open pull requests, proposed code changes awaiting integration, and identify blockers in automated checks, reviews, conflicts, and unanswered comments. Receive a prioritized watchlist and the top three actions for a human to take.
Review dependency files to find outdated packages and security vulnerabilities. Sort updates by severity and version change, identify cases needing human review, and record a prioritized update list with testing requirements.
Review open issues and discussions to organize a project's backlog. Identify possible duplicates, suggest priorities and labels, and record the top five actionable items and cases needing human attention in a state file.
Set up Loop Engineering through a single command-line tool, choosing a workflow pattern and agent tool. Start in report-only mode, check setup health and readiness, and provide next actions and first-run instructions.
Turn scan data into a categorized release notes draft covering features, fixes, breaking changes, and security. Get clean Markdown suitable for a CHANGELOG or GitHub release, with a review disclaimer and human approval required before publication.