Skip to main content
NeVibeCode · author · 23 items

riekelt: skills, plugins and MCP servers

Every card from riekelt repositories on GitHub: what each one does, an install command and example prompts. They work in Claude Code, Codex, Cursor — 8 platforms in total.

Repositories3

multi-agent-review skill multi-agent-review dispatches six automated reviewers across two model tiers to audit specs and plans before execution. Flags blockers, gaps, and risks prior to code generation. CX Codex +1 26,900installs technical-writing skill technical-writing — a skill for drafting and reviewing technical documents with source and style rules. Use it for READMEs, specs, design docs, reports, and plans. CX Codex +1 27,800installs reviewing-technical-prose skill reviewing-technical-prose — a skill for reviewing someone else's technical writing: it flags banned constructions, unsupported claims and structural defects, then runs a delivery checklist before a document ships. CX Codex +1 26,900installs principal-engineering skill principal-engineering enforces core engineering discipline for AI agents: mandates pre-change checkpoints, bans silent error suppression, and requires evidence from real code. CX Codex +1 25,700installs writing-unit-tests skill writing-unit-tests guides an agent through writing or revising unit tests around observable behavior. Useful for flaky tests, confusing cases, and new test coverage. CX Codex +1 25,700installs writing-design-docs skill writing-design-docs is a Claude Code skill that structures RFCs and architecture proposals with conclusions, goals and non-goals, Why & What boxes, and vagueness checks. CX Codex +1 26,900installs writing-changelogs skill writing-changelogs writes changelog entries, release notes, and shipped-work summaries. Use it after meaningful features, fixes, or removals. CX Codex +1 26,700installs keeping-one-source-of-truth skill keeping-one-source-of-truth — an agent skill that keeps each fact in exactly one place and stops copies from drifting apart. Useful the moment a value begs to be pasted elsewhere. CX Codex +1 25,600installs testing-changes skill testing-changes defines test requirements for code changes, enforcing regression tests for bug fixes, edge-case coverage, and strict checks against empty test diffs. CX Codex +1 25,600installs writing-runbooks skill A skill for writing runbooks, setup and release procedures, migration guides and troubleshooting entries people execute under time pressure. CX Codex +1 26,700installs documenting-legacy-codebases skill documenting-legacy-codebases rebuilds documentation from the code itself when the existing docs are missing, stale or untrusted. Survey first, prose second. CX Codex +1 26,600installs guarding-architecture skill guarding-architecture enforces system boundaries by turning structural invariants into breaking build tests. Useful when code crosses module limits or adds unwanted cross-package imports. CX Codex +1 25,600installs grounding-before-coding skill The grounding-before-coding skill makes the agent inspect code and data before changing a project or explaining a bug. It fits unfamiliar repositories and non-trivial work. CX Codex +1 25,600installs writing-postmortems skill writing-postmortems is a Claude Code skill that drafts postmortems after outages, user-facing defects, data incidents, and near misses. It can turn incident logs and team discussions into a lasting record. CX Codex +1 26,600installs writing-issues skill writing-issues formats epics, stories, tasks, bugs, and spikes for issue trackers. It turns raw discussions and notes into tickets with verifiable acceptance checks. CX Codex +1 26,500installs verifying-before-done skill verifying-before-done — an agent skill that forces a check on the changed code's real surface and a pasted verify output before any completion claim goes out. CX Codex +1 25,600installs adding-dependencies skill The adding-dependencies skill helps decide whether a project needs a dependency and how to assess and update it. Use it before adding a package, SDK, or GitHub Action. CX Codex +1 25,500installs recording-decisions skill recording-decisions — a skill that writes decisions down as a full ADR or a short log entry, so the reasoning does not stay buried in chat. CX Codex +1 26,500installs diagramming-processes skill diagramming-processes — a coding-agent skill that makes the agent draw processes, states and message exchanges as diagrams whose source lives in git, not as pictures. CX Codex +1 26,400installs handling-failures skill handling-failures — a skill that forces AI assistants to write honest error paths. Every failure either gets logged and rethrown, returns a typed error, or shifts the system into an explicit degraded mode. CX Codex +1 25,500installs operating-safely skill operating-safely sets safety guards for destructive commands, secret handling, and parallel edits. It activates before dangerous operations like deleting data or restarting live processes. CX Codex +1 25,500installs documenting-contracts skill documenting-contracts defines strict rules for documenting machine contracts like HTTP APIs, message payloads, and DTOs. It separates wire format from implementation types. CX Codex +1 26,300installs scoping-changes skill scoping-changes is a Claude Code skill for keeping a change tied to the issue that prompted it. It activates when a fix starts expanding or parts of an agreed plan are being dropped. CX Codex +1 25,500installs

More in NeVibeCode

Project sponsors

Companies that keep this analytics open