focused-fix
Deep-dive feature repair — systematically fix an entire feature/module across all its files and dependencies. Usage: /focused-fix <feature-path>
/cs:deep-work — Plan a deep work day the Cal Newport way: audit the task list deep vs shallow against a budget, build an energy-first time-blocked schedule with a hard 4-hour deep ceiling and an immovable hard stop, then log focus sessions and close with the shutdown ritual.
$ npx -y skills add alirezarezvani/claude-skills --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/cs-deep-workContext preview
What this command does when you run it.
/cs:deep-work — Plan a deep work day the Cal Newport way: audit the task list deep vs shallow against a budget, build an energy-first time-blocked schedule with a hard 4-hour deep ceiling and an immovable hard stop, then log focus sessions and close with the shutdown ritual.
name: "cs-deep-work" description: "/cs:deep-work — Plan a deep work day the Cal Newport way: audit the task list deep vs shallow against a budget, build an energy-first time-blocked schedule with a hard 4-hour deep ceiling and an immovable hard stop, then log focus sessions and close with the shutdown ritual." argument-hint: "[today's task list, with rough minutes per task]"
**Command:** `/cs:deep-work [today's task list]`
A calendar full of reactions is not a plan. `/cs:deep-work` runs the full attention-first workflow: classify every task deep vs shallow, audit the shallow share against a budget, build a time-blocked day where deep work owns the earliest hours, and close the loop with a focus-session ledger and a shutdown ritual.
1. **A shallow-work audit** — every task classified DEEP/SHALLOW with the basis shown, the shallow share vs your budget (default 50%), a WITHIN-BUDGET / OVER-BUDGET verdict, and the recent-graduate forcing question for every shallow item. 2. **A time-blocked day** — deep blocks ≥90 min in the earliest hours (capped at 4 hours), shallow work in at most two batches, 10-minute buffers, fixed lunch, hard stop. Refusals name exactly what to cut or defer. 3. **A focus ledger** — sessions logged, weekly deep hours vs target (default 15), streak count. 4. **A shutdown ritual** — open loops captured, tomorrow's first block chosen, "shutdown complete."
never squeezed in or pushed into the evening.
# 1. Audit the task list — deep vs shallow, share vs budget (OVER-BUDGET exits 2) python ../skills/deep-work/scripts/shallow_work_auditor.py \ --task "Write investor update:60" --task "Email triage:45" \ --task "Analyze churn cohort:90:deep" --budget 50 # 2. Build the time-blocked day (deep-cap and overflow refusals exit 2, naming deferrals) python ../skills/deep-work/scripts/time_block_planner.py --start 08:30 --end 17:00 --lunch 12:30 \ --task "Write investor update:90:deep" --task "Analyze churn cohort:90:deep" \ --task "Email triage:45:shallow" # 3. After each real focus block, log it; check the week and the streak python ../skills/deep-work/scripts/focus_session_logger.py log --minutes 90 --label "Investor update" python ../skills/deep-work/scripts/focus_session_logger.py status --target 15 python ../skills/deep-work/scripts/focus_session_logger.py streak # 4. End of day: walk ../skills/deep-work/assets/shutdown_checklist.md to "shutdown complete"
it refuses again, the day is overcommitted — cut scope, don't fight the arithmetic.
---
**Version:** 1.0.0
388 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools. The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents.
Repo: alirezarezvani/claude-skills
Deep-dive feature repair — systematically fix an entire feature/module across all its files and dependencies. Usage: /focused-fix <feature-path>
Clean up merged branches locally and on remote, keeping only main, dev, and gh-pages.
Stage, commit, and push the current branch following git governance rules.
Comprehensive audit pipeline for skills, plugins, agents, and commands. Validates structure, quality, security, marketplace compliance, cross-platform…