Drive the oma-deepsec skill end-to-end. Installs .deepsec/, calibrates cost, runs the right scan/process/triage/revalidate/export pass, gates PRs with process --diff, writes custom matchers, and routes findings to follow-up specialists.
Author a new Copilot Studio component — a topic on the standard harness or a behavior on the GitHub Copilot harness — with a description the planner will actually match.
You're a senior expert software engineer with extensive experience in open source projects. You always make sure the README files you write are appealing, informative, and easy to read.
Documentation drift detection and sync via oma-docs. Verify mode finds broken refs in all repo markdown (default glob /.md), sync mode proposes patches for docs affected by a git diff.
You are a docs-to-skills sync assistant for PowerSync. You run in GitHub Actions inside a checkout of powersync-ja/agent-skills, as claude[bot]. Your job: for each candidate docs PR merged in powersync-ja/powersync-docs, decide whether it warrants updates to agent skills, and if so, open a PR in…
Upgrade the Claude astrophotography-processing skill into an evidence-driven, non-destructive processing copilot with tested diagnostic tools and optional AI-model adapters.
Adds or updates GitHub Actions based security scanning for existing repositories using CodeQL, Semgrep, and Gitleaks. Use when a project needs SAST, secret scanning, or a security CI baseline in GitHub pipelines.
Launch a local, localhost-only browser wizard for a project with ult-repo-layout installed (initialized or not) — guides an uninitialized or not-yet-discovered repo through Run Discover, then shows resolved layer/slot state through four labeled boxes and a directory picker, and lets you resolve pending layout…
End-to-end Katalon True Platform testing workflow and lifecycle router. Use when one request spans several stages and no single skill owns it, for example analyze a requirement, design and import the cases, build a suite, run it with AI, and report the outcome. Also use to route any testing request across the 7-stage…
You are scoring a Build Battle submission. Participants had 45 minutes with Claude Code, the Northwind Payments merchant console, and one ticket: NWP-201, issue virtual cards from the console.
Pipeline Step 0 — Specify what you want to build and why, before any technical planning. Surfaces ambiguities early with [NEEDS CLARIFICATION] markers.
A code-review command that examines a pull request, which is a proposed set of code changes, and produces a Traditional Chinese report with weighted scores from 1 to 5.
'Detect and fix AI writing patterns recursively. Use when: reviewing text for AI tells, cleaning AI-generated drafts, checking for CoT leakage, measur.
A database-design command that creates an entity-relationship diagram, data dictionary, indexes, and SQL table definitions from a confirmed database profile. An entity-relationship diagram shows data objects and how they relate.
Second-pass re-review of a PR that already has comments. Verify fixes, resolve addressed threads, then approve or draft new comments.
★not rated 4
changed 5d agoA26 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: