khasky/awesome-agent-skills

Skills for AI coding agents: code review, debugging, security audits, refactoring, cleaning up AI-written code and text, and more.

8Stars on the repository
41Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

khasky/awesome-agent-skills

Skill Claude CodeCodex

An accessibility audit for web interfaces and markup, based on WCAG rules for people using keyboards, screen readers, or other assistive technology. It reviews structure, labels, focus, contrast, motion, and dynamic content.

not rated 8 changed yesterday A SkillSpector: pass 113 tokens original MIT

awesome-api-design

02

khasky/awesome-agent-skills

Skill Claude CodeCodex

A guide for designing an HTTP API, the agreed way that software systems exchange requests and responses. It covers resources, URLs, versioning, pagination, retries, and errors before implementation.

not rated 8 changed yesterday A SkillSpector: pass 117 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Read-only whole-project audit of design: module boundaries and dependency direction, docs-vs-code fidelity, YAGNI/KISS/SOLID, and extensibility (build from source, add a provider), producing a prioritized report with a SHIP / FIX / BLOCK verdict. Language-agnostic. Use when asked to audit the architecture of a whole…

not rated 8 changed yesterday A SkillSpector: pass 139 tokens original MIT

awesome-bug-fix

04

khasky/awesome-agent-skills

Skill Claude CodeCodex

A structured method for finding and fixing software bugs. It first creates a repeatable test that shows the failure, traces the underlying cause, and only then applies a fix.

not rated 8 changed yesterday A SkillSpector: pass 102 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Audits every checkable public claim — marketing pages, README, store listing, privacy policy, docs, structured data — against the constants, manifests, catalogs and locale strings that decide it, across repos, then fixes the drift in a separate phase. Use when asked whether the site still matches the code, to find…

not rated 8 changed yesterday A SkillSpector: pass 122 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Repo-wide cleanup of AI-like code noise, behavior-preserving: a comment pass (delete narration, condense bloat, fix stale, keep load-bearing), a read-only audit mode, an opt-in refactor mode for vague names and over-abstraction, a detection mode for dead code and logical inconsistencies, and an execution mode that…

not rated 8 changed yesterday A 166 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

A method for handling comments left during code review, the process where another person checks proposed changes. It verifies each comment against the code before deciding whether to implement, clarify, or challenge it.

not rated 8 changed yesterday A 74 tokens original MIT

awesome-code-review

08

khasky/awesome-agent-skills

Skill Claude CodeCodex

A structured examination of code changes, such as a diff or pull request, before they are merged. It checks correctness, security, and the team's standards, then groups findings by severity and confidence.

not rated 8 changed yesterday A SkillSpector: warn 86 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

A set of coding conventions for naming, file structure, error handling, type safety, immutability, and application architecture. Conventions are shared rules that keep a codebase consistent.

not rated 8 changed yesterday A SkillSpector: pass 97 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Builds a scheduled batch of platform-fit marketing posts from any sources (repos, sites, files): a knowledge map where every claim traces to evidence, an interview for voice, frequency, platforms and timezone, live checks of each platform's limits, posts written to a per-genre register, a two-stage anti-slop audit…

not rated 8 changed today A SkillSpector: pass 170 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Publishes a prepared batch of scheduled posts to the user's own accounts through their live browser (Playwright MCP bridge): bridge and format preflights, per-platform login checks that never automate a login, a persistent ledger that prevents duplicate posts across restarts, timezone-mapped scheduling that can idle…

not rated 8 changed yesterday A SkillSpector: pass 148 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Turns one existing text — a URL, a file, or pasted notes — into platform-native posts: source notes every claim traces back to, an interview for platforms, voice and length, the per-genre registers and dated platform limits of awesome-content-campaign, a two-stage anti-slop audit, one dated file per platform in the…

not rated 8 changed today A SkillSpector: warn 147 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Builds one reusable author-voice profile from whatever evidence exists — the user's own posts read through their logged-in browser, files, pasted samples, or an interview plus a tuned archetype — and writes it as a file other skills read instead of re-deriving a voice: presence and counted absence signals…

not rated 8 changed yesterday A SkillSpector: warn 153 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Read-only audit of third-party dependencies — lockfile discipline, typosquats and hallucinated package names, dependency confusion, install-script exposure, provenance, licenses, CVE reachability — with a SHIP / FIX / BLOCK verdict. Use when asked to audit dependencies or the supply chain, judge whether a package is…

not rated 8 changed yesterday A SkillSpector: warn 117 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

A workflow for upgrading software dependencies, which are external packages a project relies on, in risk-based batches.

not rated 8 changed yesterday A SkillSpector: warn 96 tokens original MIT

awesome-design-doc

16

khasky/awesome-agent-skills

Skill Claude CodeCodex

Produces a design document or ADR for a feature or architectural decision: requirements and scale numbers first, real alternatives with trade-offs, a recommendation grounded in the requirements, explicit non-goals and migration path. Use when asked to write a design doc, write an ADR, decide which approach to take…

not rated 8 changed yesterday A SkillSpector: pass 109 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

An editor for Markdown documents, a plain-text format commonly used for technical and project documentation. It improves clarity, specificity, consistency, and factual honesty while preserving code, tables, links, citations, and document structure.

not rated 8 changed today A 77 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

A guide for handling failures consistently in an application or API. It distinguishes expected operational problems, such as timeouts or invalid input, from programmer errors that indicate a bug.

not rated 8 changed yesterday A SkillSpector: pass 80 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex needs its repo

Rewrites the author and committer identity on a commit — or on every commit carrying a wrong identity — and force-pushes it safely: ownership and write-access checks, a verified mirror backup, a counted hash blast radius, and a confirmation gate before anything irreversible. Takes a commit URL plus the replacement…

not rated 8 changed yesterday A SkillSpector: warn 134 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex needs its repo

Erases a repository's git history and rebuilds it as a curated commit series over the same tree: an approved split plan (proposed here or supplied by awesome-git-commit-plan), the repo's own commit rules and hooks, paced timestamps, signed commits, a verified mirror backup, a confirmation gate before every…

not rated 8 changed yesterday A SkillSpector: warn 150 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Erases a repository's entire git history and replaces it with a single fresh commit, then force-pushes — safely: access checks, a verified mirror backup, a secret scan, and a confirmation gate before anything irreversible. Takes a repository URL. Use when asked to wipe git history, squash every commit into one Initial…

not rated 8 changed yesterday A SkillSpector: warn 116 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

Reconstructs every commit a repository has ever held, force-pushed-away history included, by merging current refs, pull-request refs, any mirror backup and every ref state the host's activity log recorded, then fetching unreachable commits by SHA over the git protocol. Emits sha/date/author/subject rows at the detail…

not rated 8 changed yesterday A SkillSpector: warn 146 tokens original MIT

khasky/awesome-agent-skills

Skill Claude CodeCodex

An advisory editor that finds grammar, reasoning, and flow problems in English prose and returns suggested corrections with explanations. It leaves the original wording for the author to change.

not rated 8 changed yesterday A 95 tokens original MIT

awesome-humanize-en

24

khasky/awesome-agent-skills

Skill Claude CodeCodex

An English editing guide for making text that sounds AI-generated read more naturally while keeping its meaning. It is for connected prose, not code, logs, legal writing, or literary work.

not rated 8 changed today A SkillSpector: warn 153 tokens original MIT

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: