Menu
SkillsMP a collecté 28 skills depuis cobusgreyling/loop-engineering. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 28 skills collectés sur 28.
Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks…
Langue du texte source : anglais
Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.
Langue du texte source : anglais
Read loop-constraints.md at the start of every run and enforce every rule. This skill runs BEFORE triage or any action skill. Constraints are binding.
Langue du texte source : anglais
An advanced skill for L3 autonomous loops. When the token budget nears exhaustion, the agent analyzes its ROI and autonomously drafts a negotiation request for a budget increase rather than silently failing.
Langue du texte source : anglais
Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.
Langue du texte source : anglais
Triage open pull requests for CI status, review comments, and merge readiness. Use in PR babysitter loops. Respects project review norms and required checks.
Langue du texte source : anglais
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
Langue du texte source : anglais
Scan merged PRs and commits since a given reference, extract titles, labels, types, and signals. Produces structured input for release notes drafting.
Langue du texte source : anglais
Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.
Langue du texte source : anglais
Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.
Langue du texte source : anglais
Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.
Langue du texte source : anglais
Scan recent merges to main for tech debt, TODOs, debug code, and small cleanup opportunities. Produces a prioritized fix list.
Langue du texte source : anglais
Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or issue tracker.
Langue du texte source : anglais
Verify goal completion.
Langue du texte source : Indéterminée
Scan open issues and discussions. Dedupe, prioritize, and propose labels. Updates issue-triage-state.md. L1 propose-only — never auto-label or close.
Langue du texte source : anglais
Scan recent merges/PRs/commits for release note content. Structured output for drafter.
Langue du texte source : anglais
Turn changelog-scan output into polished, categorized release notes draft. Propose only.
Langue du texte source : anglais
Scan recent merges and commits since last release for changelog content.
Langue du texte source : anglais
Generate categorized release notes draft from scan data. Human must approve before publish.
Langue du texte source : anglais
Scan recent merges to main (and noteworthy direct commits) since a given window (last tag or date in state). Extract titles, labels, types, linked issues, and signals for breaking changes or security. Produces structured input for a release notes drafter. Use…
Langue du texte source : anglais
Takes a structured list of changes from changelog-scan and produces a clean, categorized, user-facing release notes draft. Follows project voice and conventions. Never publishes — only proposes a draft file or section.
Langue du texte source : anglais
Independent checker for release note drafts. Reviews accuracy against the changelog-scan data, tone, completeness, and flags breaking/security items. Use after draft-release-notes. Never let the drafter verify itself.
Langue du texte source : anglais
Parse CI failures, identify failing job/step, classify as flake, regression, env, or config. Use in CI sweeper loops before any fix attempt.
Langue du texte source : anglais
Scan package manifests and lockfiles for outdated packages and known CVEs. Groups updates by risk (patch, minor, major). Use in dependency sweeper loops.
Langue du texte source : anglais
Scan recent merges to main for follow-up cleanup: TODOs, deprecations, broken doc links, stale flags. Use in post-merge cleanup loops.
Langue du texte source : anglais
Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.
Langue du texte source : anglais
Produce the smallest possible code change that fixes a specific, well-scoped issue (CI failure, reviewer comment, typo). Use only when the fix target is explicit. Never refactor unrelated code.
Langue du texte source : anglais
Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.
Langue du texte source : anglais