hyperfocus
/hyperfocus
ADHD-friendly output formatting. Restructures responses with chunking, visual hierarchy, and front-loaded key points. Modes: clean, flow (default), zen. Use when user says "hyperfocus", "focus mode", "adhd mode", "adhd friendly", or invokes /hyperfocus.
- Author
- nextor2k ↗
- Repository
- hyperfocus ↗
- Licence
- MIT
- Last repository change
- 29.07.2026
Assessment and security
- Files in this package
- 5
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 29.07.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
ADHD-friendly output formatting. Restructures responses with chunking, visual hierarchy, and front-loaded key points. Modes: clean, flow (default), zen. Use when user says "hyperfocus", "focus mode", "adhd mode", "adhd friendly", or invokes /hyperfocus.
Triggers from the description
Arguments
/hyperfocus [clean|flow|zen|off|persistent [project] [mode]|disable|status]
Original author description
ADHD-friendly output formatting. Restructures responses with chunking, visual hierarchy, and front-loaded key points. Modes: clean, flow (default), zen. Use when user says "hyperfocus", "focus mode", "adhd mode", "adhd friendly", or invokes /hyperfocus.
How it works
- Commands
- Session activation
- Persistent, disable, status
- Legacy migration (≤0.2)
- Boundaries
- Auto-Clarity
SKILL.md preview
---
name: hyperfocus
description: >
ADHD-friendly output formatting. Restructures responses with chunking, visual
hierarchy, and front-loaded key points. Modes: clean, flow (default), zen.
Use when user says "hyperfocus", "focus mode", "adhd mode", "adhd friendly",
or invokes /hyperfocus.
argument-hint: "[clean|flow|zen|off|persistent [project] [mode]|disable|status]"
---
Format responses for ADHD-optimized reading: structure beats brevity. Parse `$ARGUMENTS` against the table below.
## Commands
| Argument | Effect |
|----------|--------|
| *(none)*, `clean`, `flow`, or `zen` | Activate/switch mode for this session only. Default mode: flow |
| `off` | Deactivate hyperfocus for this session |
| `persistent [mode]` | Enable global auto-injection at every future session start (default mode: flow) |
| `persistent project [mode]` | Same, scoped to this project only |
| `disable` | Turn off persistent mode in both global and project state, wherever present |
| `status` | Report session mode plus persistent state |
Plain "stop hyperfocus" or "normal mode" is equivalent to `off`.
## Session activation
On activation or mode switch, read `references/core.md` and `references/<mode>.md` (relative to this skill's directory) and apply their rules to every subsequent response until the user says "stop hyperfocus", "normal mode", or `/hyperfocus off`.
## Persistent, disable, status
Run `scripts/hyperfocus-state`, resolved at `${CLAUDE_PLUGIN_ROOT}/scripts/hyperfocus-state` when installed as a plugin:
- `persistent [mode]` → `hyperfocus-state enable [mode]`
- `persistent project [mode]` → `hyperfocus-state enable [mode] --project`
- `disable` → `hyperfocus-state disable --all`
- `status` → `hyperfocus-state status`
If `${CLAUDE_PLUGIN_ROOT}` is unset (standalone skill install, no plugin root), there is no hook to attach persistence to: tell the user persistent mode isn't available in this install, and apply the requested mode for the current session only.
## Legacy migration (≤0.2)
Check for `~/.claude/hyperfocus-rules.txt` or a `settings.json` hook whose command contains `hyperfocus-rules`. If found, tell the user it's a leftover from hyperfocus ≤0.2 and offer to remove it. Only edit settings.json after the user confirms.
## Boundaries
Code blocks, error messages, technical output, commits, PRs, and code reviews: write normally, without hyperfocus formatting.
## Auto-Clarity
Drop hyperfocus formatting for security warnings and irreversible-action confirmations — use full prose. Numbered steps stay allowed elsewhere; only symbol-substitution and density compression are dropped for safety-critical sequences. Resume formatting after.
Files in this package (5)
- SKILL.md 3 KB
- references/clean.md 1 KB
- references/core.md 1 KB
- references/flow.md 1 KB
- references/zen.md 2 KB
Versions
The database has no other skills named hyperfocus.
Database snapshot: 13.11.2026 · package version 4a8e18214119 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100i-have-adhd
Use when the user invokes /i-have-adhd, says they have ADHD, or asks for ADHD-friendly output. Also used as a required writing filter by the docs skill. Don't use for marketing copy or after the user says "stop adhd mode" or "normal mode". - 90adhd
Formats output for ADHD-friendly action — lead with the next step, number tasks, restate state, cut fluff. Use when named (adhd), when the user mentions ADHD or focus/executive-function constraints, or when they ask for steps they can execute immediately. - 100hyperfocus-brake
operator健康提醒:三猫撒娇打断 hyperfocus。 Use when: hook 触发提醒、用户输入 /hyperfocus-brake。 Not for: 正常工作流程、非operator用户。 Output: 三猫温柔提醒 + typed check-in。 - 90i-have-adhd
Apply adhd-friendly communication as a bounded agent workflow while preserving user intent, privacy, and host capabilities. Use when the user explicitly requests adhd-friendly communication behavior or files. - 100i-have-adhd
为ADHD读者优化输出格式:先给出下一步行动,将多步骤工作编号,在每次对话中重复当前状态,避免无关话题,提供具体的时间估算,让成果清晰可见。通过“/i-have-adhd”启用此模式;在说“停止adhd模式”前持续生效。 - 100action-first-output
Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.