focused-fix
CommandDeep-dive feature repair — systematically fix an entire feature/module across all its files and dependencies. Usage: /focused-fix…
@alirezarezvaniInstall CommandAI & Agents
Command
/cs-claude-coach
Activate the claude-coach skill — personal Claude power-user coaching for the rest of the conversation.
$ npx -y skills add alirezarezvani/claude-skills --agent claude-code
Command definition
cs-claude-coach.mddisable-model-invocation: true
description: Activate the claude-coach skill — personal Claude power-user coaching for the rest of the conversation.
argument-hint: "[use cases, e.g. 'writing, coding']"
/cs-claude-coach
Activates the `claude-coach` skill. From this point on, the conversation gains:
- A personalized cheat-code glossary delivered on the first turn (ranked by impact, filtered to your use cases)
- At most one ⚡ power-user tip per response, only when a tip would genuinely 10x your next attempt
- On-demand `"rate that prompt"` and `"how am I doing"` feedback
What happens when this command fires
1. If `$ARGUMENTS` contains use cases (e.g. `writing, coding`), skip the use-case question and proceed. 2. Otherwise, ask exactly one question: **"What are your top 2-3 use cases for Claude?"** and wait. 3. Load `engineering/claude-coach/skills/claude-coach/references/cheat-codes.md`, rank techniques against the stated use cases, and present the top 5-7 with one-line explanations and one concrete example each. 4. End with: *"I'll watch your prompts going forward and surface tips when I spot an easy win — max one per response. Ask me 'rate that prompt' anytime for direct feedback."* 5. Stay active for the rest of the conversation. On every subsequent turn, run the 5-gate decision tree from `skills/claude-coach/references/coaching-rules.md` before deciding whether to surface a tip.
Examples
/cs-claude-coach
/cs-claude-coach writing, coding
/cs-claude-coach research, learning
To turn it off
Say "stop with the tips" or "no more coaching" mid-conversation and the persona goes silent until re-activated.
Read more
disable-model-invocation: true description: Activate the claude-coach skill — personal Claude power-user coaching for the rest of the conversation. argument-hint: "[use cases, e.g. 'writing, coding']"
/cs-claude-coach
Activates the `claude-coach` skill. From this point on, the conversation gains:
- A personalized cheat-code glossary delivered on the first turn (ranked by impact, filtered to your use cases)
- At most one ⚡ power-user tip per response, only when a tip would genuinely 10x your next attempt
- On-demand `"rate that prompt"` and `"how am I doing"` feedback
What happens when this command fires
1. If `$ARGUMENTS` contains use cases (e.g. `writing, coding`), skip the use-case question and proceed. 2. Otherwise, ask exactly one question: **"What are your top 2-3 use cases for Claude?"** and wait. 3. Load `engineering/claude-coach/skills/claude-coach/references/cheat-codes.md`, rank techniques against the stated use cases, and present the top 5-7 with one-line explanations and one concrete example each. 4. End with: *"I'll watch your prompts going forward and surface tips when I spot an easy win — max one per response. Ask me 'rate that prompt' anytime for direct feedback."* 5. Stay active for the rest of the conversation. On every subsequent turn, run the 5-gate decision tree from `skills/claude-coach/references/coaching-rules.md` before deciding whether to surface a tip.
Examples
/cs-claude-coach /cs-claude-coach writing, coding /cs-claude-coach research, learning
To turn it off
Say "stop with the tips" or "no more coaching" mid-conversation and the persona goes silent until re-activated.
Stats
29,589
Stars
4,104
Forks
Active
Maintenance
Python
Language
MIT
License
Last commit
Created
Ships withclaude-skills
411 production-ready skills for Claude Code and 12 other coding agents, covering engineering, product, marketing, compliance, finance and the C-suite. We test whether each skill loads when you ask in plain words, and publish the results.
30k200 skills127 agents2 MCP
Stars on GitHub
Momentum
- stars in total
- 29.6k
Other commands on claude-skills.
@alirezarezvaniInstall Commandclean
CommandClean up merged branches locally and on remote, keeping only main, dev, and gh-pages.
@alirezarezvaniInstall Commandcm
CommandStage working tree changes and create a Conventional Commit (no push).
@alirezarezvaniInstall Commandcp
CommandStage, commit, and push the current branch following git governance rules.
@alirezarezvaniInstall Commandplugin-audit
CommandComprehensive audit pipeline for skills, plugins, agents, and commands. Validates structure, quality, security, marketplace…
@alirezarezvaniInstall CommandMore commands from other plugins.
devbox-entrypoint
CommandContext: runloop resumes a devbox by re-running the same entrypoint script, which invokes `cn serve --id <agentId> ...`. Because…
@continuedevInstall Commandc
CommandShortcut for "continue working" — pick the work in flight back up exactly where it stopped and keep going until it is done or…
@danielmiesslerInstall Commandsidecar
CommandSpawn a read-only sidecar subagent to investigate something in this checkout without editing files, moving branches, or touching…
@builderioInstall Command