Designs bespoke GitHub README hero visuals — animated GIF, static PNG, or animated SVG — through a structured discovery dialog. Retina capture, scope-matched copy, optional upstream PR.
Plugin repo-visuals from marketplace livlign in livlign/claude-skills. Commands read from the repo's manifest — 29 days ago.
repo-visuals-retroRetrospective meta-skill for the `repo-visuals` skill. Reads accumulated evaluation logs from past runs, spots patterns (recurring low-score criteria, repeated iteration failures, unsatisfied requests), consults other expert skills (skill-creator, frontend-design, etc.) where relevant, and proposes
repo-visualsCreate hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the use
Characterization-test backfill and spec-test enforcement for .NET services. Deterministic C0/C1 coverage via dotnet-coverage, with per-method classification and a checked-in manifest explaining every inclusion, exclusion, and cannot-test entry.
4 skills
Rewrites a thin or empty PR description in the repo's own PR voice, learned from its merged-PR history. Grounded in the actual diff — no invented motivation or testing claims. Before/after preview; applies via gh pr edit only on explicit confirmation.
1 skill
Audits a GitHub repo's README against best-practice patterns and produces a prioritized punch list (P0/P1/P2) of fixes — hero presence, install-to-first-success length, audience-jargon match, drift signals. Read-only diagnostic by default.
1 skill
Audit and rewrite prose that reads as machine-generated, across READMEs, changelogs, PR descriptions, docs, and blog copy, with detect-only, rewrite, and edit-in-place modes.
1 skill
Tooling and developer productivity experts - CLI tools, documentation, README generation, and DX optimization
The session-lifecycle commands from aigent-OS, the open-source Claude Code operating system: /open (boot the session — load memory from the vault, surface what changed and what's blocked) and /close (bank the session back to memory so the next /open resumes with full context). Both skills declare scoped allowed-tools and run a vault-root preflight that verifies the configured aigent-OS vault before any write or script execution. Assumes the aigent-OS vault structure; see the repo and the plugin README for the full system and the security model.
2 skills
Documentation generation, API docs, and README maintenance
3 commands
Sync root README.md with current skills inventory from skills/ directory.
1 command
Generate comprehensive documentation from code
1 command
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.