help
Skill0 starsChanged 6 months agoMITView on GitHub
Print a navigable, user-facing overview of this health coach project. Lists all skills with example phrases, where files live, where to drop things, common things to say, and stale-section reminders. Invoke when the user says "help", "what can you do", "what skills do you have", "show me commands", "I'm new", "where do I start", "what's available", "how does this work", "/health:help", "guide", or "tour". (Note: built-in `/help` is reserved by Claude Code; the project's namespaced shortcut is `/health:help`. Natural-language "help" routes here via this description.) This is the project's table of contents for humans.
82 other projects use a version of this.
Adopted by
Most recently taken up by
- krystaleicher/claude-skillstheir own version, first seen Nov 16, 2026
- rzaaeeff/agent-ledgertheir own version, first seen Nov 16, 2026
- tatashbar/Economic-Modeling-Studiotheir own version, first seen Nov 16, 2026
- finolabs/finolabs-vibecodetheir own version, first seen Nov 16, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- finolabs/vibecodetheir own version, first seen Nov 15, 2026
Used with
Projects with it also use create-stories, story-done and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
lilangMaxSkillcreate-stories
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Also in 9 projects that use this
lilangMaxSkillstory-done
End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.
Also in 9 projects that use this
- +10 more from lilangMax
Other versions82 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 82
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- bitwize-music-studio/claude-ai-music-skills★ 668same name
- waynesutton/markdown-site★ 628same name
- andrew-shwetzer/career-ops-plugin★ 501same name
- andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-★ 500same name
72 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 63 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
When invoked, print a navigable overview to the user.
- Very specific: line 12
Read .claude/skills/*/SKILL.md to enumerate the current skill list (in case it has grown).
- Very specific: line 13
Read index.md to summarize what's already in the wiki.
- Very specific: line 14
Read hot.md to know current state and recent activity.
- Distinctive: line 152
After every help invocation:
- Distinctive: line 154
Do NOT touch index.md or hot.md (help is read-only).
“Common” is measured: kept by at least 6 in 10 of the 63 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Help skill
When invoked, print a navigable overview to the user. Always read the latest state from index.md and hot.md before printing so the help reflects current reality.
What to do
- Read
.claude/skills/*/SKILL.mdto enumerate the current skill list (in case it has grown). - Read
index.mdto summarize what's already in the wiki. - Read
hot.mdto know current state and recent activity. - Print the help in the structure below.
- Append to
log.md:## [DATE TIME] note | help shown.
Output structure
Print this as markdown to the user. Adapt phrasing to current state (e.g., if onboarded, mention current weight/goal; if not, lead with "let's get you set up").
# Your health coach
A personal, India-specific health, nutrition, and fitness coach built on the LLM Wiki pattern. Everything is local on your machine.
## How to use it
You don't need to remember commands. Just talk naturally. The coach matches your message to a skill automatically.
## Common things you can say
**Logging (just say what happened)**
- "had 2 phulkas and dal for lunch"
- "weighed 78.4 this morning"
- "did 3x8 squats at 60kg, 3x10 bench at 40kg"
- "headache since lunch"
- "had 4 chais today"
- "took my B12"
**Photos (just drop them)**
- Food photo in chat → I identify and log with a confidence band
- Body comp photo to `raw/photos/body/` → filed under monthly tracking
- Bloodwork PDF to `raw/bloodwork/` → parsed, biomarkers updated
**Planning**
- "plan dinner"
- "plan tomorrow"
- "plan the week"
- "want McSpicy Paneer Wrap tonight"
- "what can I order at the Saoji place"
- "brief the cook for tomorrow"
- "decode this menu" (with photo)
**Events / calendar**
- "wedding Saturday"
- "traveling to Mumbai 15-18"
- "vrat tomorrow"
- "Ekadashi this weekend"
**Reviews / analysis**
- "weekly review" or "how was my week"
- "monthly review"
- "quarterly review"
- "am I on track"
- "where is my HbA1c headed"
- "show me a chart"
**Updates**
- "let's start" or "first time" → onboarding (auto-runs if profile is empty)
- "checkin" → auto-detects whether weekly/monthly/quarterly is due
- "let me update preferences"
- "let me update inventory"
- "let me update my supplements"
## Skills (auto-trigger from natural language)
- **help** (this skill) - "help", "what can you do"
- **checkin** - onboarding + periodic interviews. "let's start", "weekly review", "let me update X"
- **log** - record meals, weight, body, workouts, symptoms, beverages, supplements. "had X", "weighed X", drop a photo
- **plan** - meal/cook/workout/event suggestions. "plan dinner", "want X tonight", "brief the cook", "wedding Saturday"
- **ingest** - process files in raw/. drop a bloodwork PDF, "I dropped my Oura export"
- **review** - weekly/monthly/quarterly/annual analysis. "how am I doing", "show me a trend"
## Slash command shortcuts (namespaced under `health:`)
- `/health:help` - this skill
- `/health:checkin [weekly|monthly|quarterly|annual|onboarding|<section>]`
- `/health:log <what happened>`
- `/health:plan <dinner|day|week|cook|decode <restaurant>|event|workout|fit <food>>`
- `/health:ingest [path | inbox]`
- `/health:review [weekly|monthly|quarterly|annual|lint|correlations <topic>|projection <biomarker>|chart <topic>]`
Why namespaced: built-in Claude Code commands like `/help` and `/review` are reserved. The `health:` prefix avoids collision and groups all project commands together.
## Where things live
- **CLAUDE.md** the schema (auto-loaded each session)
- **hot.md** rolling 14-day cache (read first)
- **index.md** wiki catalog
- **log.md** append-only event log
- **wiki/profile/** you, your goals, preferences, kitchen, supplements, psychology
- **wiki/biomarkers/** lab values, sleep/recovery, body composition over time
- **wiki/targets/** current macros for the week
- **wiki/plans/** current week's meals + workouts + cook briefs
- **wiki/calendar/** festivals, personal events, vrat, wedding season
- **wiki/food-library/** dishes you eat (auto-grows from logs)
- **wiki/logs/YYYY/MM/DD.md** daily logs
- **wiki/reviews/** weekly, monthly, quarterly, annual, biomarker events, correlations
- **wiki/knowledge/** India-specific reference (P1+)
## Where to drop things
- Bloodwork PDFs → `raw/bloodwork/`
- Doctor notes / prescriptions → `raw/medical/`
- Food photos → paste in chat, OR `raw/photos/`
- Body comp photos → `raw/photos/body/`
- Apple Health / Oura / Apple Watch exports → `raw/wearable-exports/`
- Grocery receipts (Zepto/BigBasket/Blinkit) → `raw/grocery-receipts/`
- Random notes you haven't sorted → `raw/inbox/` (I'll triage)
## What I watch (and remind you about)
- Weight: every 14 days
- Body comp photos + tape: every 30 days
- Bloodwork: every 180 days
- Weekly checkin: every 14 days
- Monthly checkin: every 35 days
- Quarterly checkin: every 100 days
- Inventory: every 30 days
I'll mention these gently when they go stale; I won't auto-run anything without you saying so.
## India-specific defaults
This coach uses Asian-Indian thresholds (BMI ≥23 overweight, waist M≥90/F≥80), LAI 2024 LDL targets, ICMR DGI 2024 caps (salt 5g, oil 25-30g, sugar 20-25g), IFCT 2017 macros. It accounts for vrat days, chai accounting, wedding season, AQI, family medical clusters, and the cook-coordination reality.
## Privacy + medical safety
Everything is local on your machine. Do not push this folder to a public git remote.
I am not a doctor. I surface signals against established thresholds. For anything genuinely abnormal, see a physician. I do not prescribe.
## Current state
[Print 1-2 sentences summarizing what's in hot.md: phase, whether onboarded, latest weight if known, anything stale.]Bookkeeping
After every help invocation:
- Append to
log.md:## [DATE TIME] note | help shown. - Do NOT touch index.md or hot.md (help is read-only).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

