Claude skills and agent skills

DeepSeekSkill

dsh-speed-up-perf

deepseek-ai/deepseek-harness/.agents/skills/dsh-speed-up-perf/SKILL.md

Use when investigating or optimizing DeepSeek Harness performance, designing realistic synthetic benchmarks or CI performance gates, profiling long Sessions or Web responsiveness, or turning performance PR evidence into measured behavior-preserving fixes.

DeepSeekSkill

dsh-translate-docs

deepseek-ai/deepseek-harness/.agents/skills/dsh-translate-docs/SKILL.md

Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.

Often used withdsh-doc-site-sync·dsh-doc-standards

DeepSeekReads credentialsSkill

record-browser-gif

deepseek-ai/deepseek-harness/.agents/skills/record-browser-gif/SKILL.md

Record browser or Web UI interaction demos as optimized GIFs using the available browser-control workflow, optional Playwright Videos for higher capture frame rates, and deterministic encoding, then attach the GIF to a pull request with `gh --attach`; publication requires gh v2.99.0 or later, and a GIF over 5 MiB is split into parts. Use when asked to make, record, or generate a GIF that demonstrates a browser workflow, and for every pull request that changes product-user-visible GUI behavior, which MUST include a GIF recorded from the pull request's real server and model flow.

Often used withdsh-doc-site-sync·dsh-doc-standards

DeepSeekSkill

editing-cordis-compositions

deepseek-ai/deepseek-harness/packages/preset/agent-preset/skills/editing-cordis-compositions/SKILL.md

Use when creating, changing, or validating an agent preset or other Cordis composition for this harness, including deciding host versus preset placement and checking that an authored preset mounts.

NousResearchReads credentialsSkill

claude-code

NousResearch/hermes-agent/skills/autonomous-ai-agents/claude-code/SKILL.md

Delegate coding to Claude Code CLI (features, PRs).

NousResearchReads credentialsSkill

codex

NousResearch/hermes-agent/skills/autonomous-ai-agents/codex/SKILL.md

Delegate coding to OpenAI Codex CLI (features, PRs).

Often used withios-sync·compare-screenshots·touchdesigner-mcp

NousResearchPipes a download into a shellSkill

computer-use

NousResearch/hermes-agent/skills/autonomous-ai-agents/computer-use/SKILL.md

Drive the desktop background-first; escalate on signal.

Often used withcompetitor-news-monitor

NousResearchSkill

claude-design

NousResearch/hermes-agent/skills/creative/claude-design/SKILL.md

Design one-off HTML artifacts (landing, deck, prototype).

Often used withtouchdesigner-mcp·p5js·sdlc-review

NousResearchSkill

humanizer

NousResearch/hermes-agent/skills/creative/humanizer/SKILL.md

Humanize text: strip AI-isms and add real voice.

NousResearchSkill

manim-video

NousResearch/hermes-agent/skills/creative/manim-video/SKILL.md

Manim CE animations: 3Blue1Brown math/algo videos.

Often used withsongwriting-and-ai-music·p5js·ascii-video

NousResearchSkill

google-workspace

NousResearch/hermes-agent/skills/productivity/google-workspace/SKILL.md

Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.

Often used withheartmula·songwriting-and-ai-music·teams-meeting-pipeline

NousResearchSkill

dogfood

NousResearch/hermes-agent/skills/software-development/dogfood/SKILL.md

Exploratory QA of web apps: find bugs, evidence, reports.

Often used withdep-refs·yuanbao·architecture-governance

NousResearchSkill

github

NousResearch/hermes-agent/skills/software-development/github/SKILL.md

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

Often used withtaskflow-inbox-triage·BlueBubbles·node-connect

NousResearchSkill

simplify-code

NousResearch/hermes-agent/skills/software-development/simplify-code/SKILL.md

Parallel 4-agent cleanup of recent code changes.

Often used withcompetitor-news-monitor·teams-meeting-pipeline·p5js

NousResearchSkill

systematic-debugging

NousResearch/hermes-agent/skills/software-development/systematic-debugging/SKILL.md

4-phase root cause debugging: understand bugs before fixing.

Often used withchinese-code-review·diagnosing-superpowers·chinese-commit-conventions

affaan-mSkill

competitive-platform-analysis

affaan-m/ECC/.agents/skills/competitive-platform-analysis/SKILL.md

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong to, and which sources to mine. First step in the three-skill competitive pipeline; precedes benchmark-methodology.

affaan-mSkill

competitive-report-structure

affaan-m/ECC/.agents/skills/competitive-report-structure/SKILL.md

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space analysis, strategic recommendations, and team alignment trigger questions. Final step in the three-skill competitive pipeline.

affaan-mSkill

dmux-workflows

affaan-m/ECC/.agents/skills/dmux-workflows/SKILL.md

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

Often used witheverything-claude-code-conventions·nextjs-turbopack·everything-claude-code

affaan-mSkill

eval-harness

affaan-m/ECC/.agents/skills/eval-harness/SKILL.md

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles. Use when a Claude Code workflow needs a formal eval before it is trusted or changed.

Often used withbrand-discovery·agent-sort·configure-ecc

affaan-mSkill

everything-claude-code

affaan-m/ECC/.agents/skills/everything-claude-code/SKILL.md

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.