checkin
Skill0 starsChanged 6 months agoMITView on GitHub
Periodic structured interview to keep the wiki current. Modes: onboarding (first session, ~30 min, AUTO-RUNS when wiki/profile/identity.md is empty), weekly (5 min, every 7 days), monthly (15 min, body comp + supplements + preferences), quarterly (30 min, lifestyle + goals + bloodwork prompt), annual (60 min, year-in-review), and ad-hoc (refresh a specific section). Invoke when the user says "checkin", "let's start", "first time", "set me up", "let's onboard", "weekly review", "let me update X", "weighed myself" (then chain to log), "haven't checked in", "let's catch up", "monthly review", "quarterly review", "year in review", "tell me what's missing", or when CLAUDE.md detects a stale wiki section. If wiki/profile/identity.md is empty or missing, auto-run onboarding mode after a one-line "let's set you up" intro.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- altisvc/claude-skillstheir own version, first seen Nov 16, 2026
- chrisblattman/claudeblattmantheir own version, first seen Nov 8, 2026
- Chadlenberg/chief-of-stafftheir own version, first seen Nov 8, 2026
- AsiaOstrich/EngramGraphtheir own version, first seen Nov 8, 2026
- AsiaOstrich/universal-dev-standardstheir own version, first seen Nov 1, 2026
- pqmcgill/familytheir own version, first seen Oct 13, 2026
Used with
Projects with it also use audit and code-review.
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.
OpenAISkillaudit
Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.
Also in 3 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- chrisblattman/claudeblattman★ 483same name
- AsiaOstrich/universal-dev-standards★ 84same name
- AsiaOstrich/EngramGraph★ 4same name
- mpaarating/ai-workflow-kit★ 2same name
- altisvc/claude-skills★ 0same name
- byun-alex/claude-session-continuity★ 0same name
- Chadlenberg/chief-of-staff★ 0same name
- pqmcgill/family★ 0same name
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
Show its rules and text
We split this skill into the rules it gives an agent
19 rules. 0 are common, 9 are distinctive, and 10 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
If invoked without a specified mode, decide from the file system + log.md:
- Distinctive: line 20
When in doubt, ask: "Last weekly was X days ago, last monthly Y.
- Distinctive: line 26
Before starting, say one line: "Let's set you up.
- Distinctive: line 31
Ask in one message:
- Distinctive: line 76
If a cook is involved, what's her existing routine and capacity for change
- Very specific: line 101
Write wiki/targets/current.md with all the above + reasoning.
- Very specific: line 102
Write wiki/targets/protocol.md (current dieting approach, why this protocol).
- Distinctive: line 107
If user shared bloodwork in Round 2, the ingest skill ran and updated biomarkers.
- Very specific: line 111
Update index.md with all new pages.
- Very specific: line 158
Update wiki/biomarkers/body-composition.md (timestamped row).
- Very specific: line 159
Update wiki/profile/preferences.md, inventory.md, supplements.md.
- Distinctive: line 169
When was last bloodwork
- Distinctive: line 170
If 6+ months ago, recommend a panel (lipid + HbA1c + LFT + B12 + Vit D + thyroid + CBC + creatinine)
- Very specific: line 171
If user has fresh bloodwork in raw/bloodwork/, invoke ingest skill now
- Very specific: line 192
If bloodwork ingested: wiki/reviews/biomarker-events/YYYY-MM-DD.md already created by ingest.
- Distinctive: line 229
When invoked without a specified mode, also report any stale sections (per CLAUDE.md table).
- Distinctive: line 233
After ANY checkin mode completes:
- Very specific: line 235
Update index.md with any new pages.
- Very specific: line 237
If targets changed: also append ## [DATE TIME] target-change | <reason> to log.md.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Checkin skill
Periodic interview to keep the wiki current. Six modes: onboarding, weekly, monthly, quarterly, annual, ad-hoc.
Mode auto-detection
If invoked without a specified mode, decide from the file system + log.md:
wiki/profile/identity.mdempty → onboarding (auto, no need to ask).- Last
checkin | weekly>7 days ago → suggest weekly. - Last
checkin | monthly>30 days ago → suggest monthly. - Last
checkin | quarterly>90 days ago → suggest quarterly. - Last
checkin | annual>365 days ago → suggest annual.
When in doubt, ask: "Last weekly was X days ago, last monthly Y. Want to do [recommended], or pick a different mode?"
Modes
Onboarding (~30 min, first time only)
Before starting, say one line: "Let's set you up. About 30 minutes, six quick rounds. Ready?" If yes, proceed.
Then run six batched rounds. ONE round per message. Wait for answers between rounds. Save into wiki/profile/*.md as you go.
Round 1: Identity Ask in one message:
- Name and what to call you
- Age, sex
- Height, current weight
- City
- Daily routine (desk job? travel? shift work? field work?)
Save → wiki/profile/identity.md, append first weight to wiki/profile/anthropometry.md.
Round 2: Medical Ask in one message:
- Diagnosed conditions (diabetes, BP, thyroid, fatty liver, PCOS, IBS, cholesterol, anything else)
- Medications and supplements (name, dose, timing)
- Allergies / intolerances
- Family medical history (T2DM, CVD, cancer, obesity in parents/siblings)
- Date of last bloodwork. If recent and they have it, ask them to drop the PDF in
raw/bloodwork/now.
Save → wiki/profile/medical.md, wiki/profile/supplements.md. If they share bloodwork, invoke ingest skill before continuing to Round 3.
Round 3: Goals Ask in one message:
- What feels broken right now (energy, weight, lab numbers, specific symptom, mood)
- What does winning look like in 3 months
- What does winning look like in 12 months
- What have you tried before, why didn't it stick
Save → wiki/profile/goals.md. Use the failure modes to inform target-setting (e.g., "couldn't stick to 1500 kcal" → use deficit ≤400 kcal/day).
Round 4: Preferences Ask in one message:
- Top 5 favorite foods (be specific: "paneer butter masala", not "paneer")
- Top 5 hated foods (so I never suggest them)
- Off-limits (vegetarian, vegan, eggless, religious, allergic)
- Comfort foods that NEED to fit (the wraps, biryanis, sweets you'll eat anyway)
- Best and worst restaurants you'd order from
Save → wiki/profile/preferences.md.
Round 5: Kitchen Ask in one message:
- Who cooks at home (you, family, dedicated cook, mostly outside)
- Weekly meal rotation: typical Mon-Sun breakfast/lunch/dinner
- Cooking oils used (mustard, sunflower, ghee, groundnut, refined)
- Pantry staples (jowar, bajra, rice, dals, milk, curd, paneer, eggs)
- Eating-out frequency per week, what kind of places
- If a cook is involved, what's her existing routine and capacity for change
Save → wiki/profile/kitchen.md, wiki/profile/kitchen-cook.md (if applicable), wiki/profile/inventory.md.
Round 6: Constraints + Workout + Lifestyle Ask in one message:
- Cooking time available on weekdays
- Budget concerns
- Workout setup: gym available (when, how often), home equipment, outdoor walking access
- Current activity level (sedentary, lightly active, moderately active, very active)
- Sleep schedule (typical bed/wake times, quality)
- Stress level 1-10 and main stressors
- Caffeine pattern (cups/day) and alcohol pattern
- Wearables to ingest from: iPhone Apple Health, Apple Watch, Oura - which one's data do you trust most?
Save → wiki/profile/constraints.md, wiki/profile/lifestyle.md.
After all 6 rounds, you compute and write:
- BMR via Mifflin-St Jeor.
- TDEE = BMR × activity multiplier.
- Calorie target. If weight loss is the goal, deficit ≤400 kcal/day for first 8 weeks. If maintenance/lab-fix, hold at TDEE.
- Protein at 1.6 g/kg.
- Fiber 35 to 40 g/day.
- ICMR caps (salt ≤5g, oil 25-30g, sugar 20-25g).
- Asian-Indian risk overlay if relevant.
- Write
wiki/targets/current.mdwith all the above + reasoning. Include a YAML frontmatter block at the top withkcal,protein_g,fiber_g,sodium_mg,added_sugar_g,cooking_oil_g,effective_from(per Frontmatter contract in CLAUDE.md). This is what the Obsidian dashboard reads to compute today's progress bars. - Write
wiki/targets/protocol.md(current dieting approach, why this protocol). - Generate
wiki/plans/current-week-meals.md(7-day plan respecting kitchen rotation, with one favorite/splurge baked in). - Generate
wiki/plans/current-week-workouts.md(gym schedule + walks, recovery-aware). - Show the plan, take feedback, adjust, then prompt "ready to start logging? Just tell me what you eat or drop a photo."
If user shared bloodwork in Round 2, the ingest skill ran and updated biomarkers. Use those results in target-setting.
Bookkeeping:
- Append
## [DATE TIME] onboard | initial onboarding completetolog.md. - Update
index.mdwith all new pages. - Refresh
hot.mdwith the new state.
Weekly (~5 min)
Quick numbers:
- Weight (morning, fasted, today's reading or this week's lowest stable)
- Sleep this week (avg hours, Oura readiness if available)
- Workouts done (list)
- Anything painful or symptomatic worth noting
Adherence:
- 1-10: how was the week
- One win
- One friction point
- Anything you need from me next week
You then:
- Append weight to
wiki/profile/anthropometry.md. Update 7-day moving average. - Generate
wiki/reviews/weekly/YYYY-WXX.md(adherence stats from logs, weight trend, wins, friction, ONE proposed change for next week). - Update
hot.md. - Append
## [DATE TIME] checkin | weeklytolog.md.
Adjust wiki/targets/current.md ONLY if data demands it. One change per week max. When you do change a target, rewrite the YAML frontmatter block at the top of the file alongside the body table edit (per Frontmatter contract in CLAUDE.md), and bump effective_from to today's date.
Monthly (~15 min, target 1st of month)
Weekly content PLUS:
Body composition:
- Waist tape: 3 measurements (umbilical, narrowest, widest) → record narrowest
- Hip tape
- Optional: thigh, neck, arm
- Front + side photo (same lighting, same time of day, same clothing) → drop into
raw/photos/body/YYYY-MM-front.jpgandYYYY-MM-side.jpg
Preferences refresh:
- Any new foods you fell in love with this month
- Any foods you got tired of
- New restaurants worth adding to food-library
Inventory + supplements:
- What's currently in pantry/fridge
- What ran out, restock list
- Are you taking the supplements we agreed
- Side effects, brand changes
You then:
- Update
wiki/biomarkers/body-composition.md(timestamped row). - Update
wiki/profile/preferences.md,inventory.md,supplements.md. - Generate
wiki/reviews/monthly/YYYY-MM.md(4-week trend, body comp progress, supplement adherence, ONE strategic adjustment). - Refresh
hot.md. - Append
## [DATE TIME] checkin | monthlytolog.md.
Quarterly (~30 min)
Monthly content PLUS:
Bloodwork:
- When was last bloodwork
- If 6+ months ago, recommend a panel (lipid + HbA1c + LFT + B12 + Vit D + thyroid + CBC + creatinine)
- If user has fresh bloodwork in
raw/bloodwork/, invokeingestskill now
Lifestyle:
- Job/hours/travel pattern shifts
- Sleep schedule shifts
- Stress level (1-10) and main stressors
- Caffeine/alcohol pattern shifts
- Workout setup changes
Goals:
- Are we still aiming at the right thing
- Have priorities shifted (energy vs weight vs labs vs aesthetics)
- Anything new you want to fix
Medical:
- New diagnoses
- New meds or supplement changes
- Family medical updates
You then:
- Update
wiki/profile/lifestyle.md,goals.md,medical.md. - If bloodwork ingested:
wiki/reviews/biomarker-events/YYYY-MM-DD.mdalready created by ingest. - Possibly trigger
wiki/targets/current.mdrevision (multiple changes are OK at quarterly). - Generate
wiki/reviews/quarterly/YYYY-Q?.md. - Refresh
hot.md. - Append
## [DATE TIME] checkin | quarterlytolog.md.
Annual (~60 min, target birthday or January)
Quarterly content PLUS:
- Year-in-review: weight trend over 12 mo, biomarker trends, big wins, stuck points.
- Goal reset for next year.
- Workout periodization for next year.
- Bloodwork: definitely repeat the full panel.
- Coach effectiveness review: what's working about how we work together, what isn't.
You then:
- Generate
wiki/reviews/annual/YYYY.md. - Optionally revise
CLAUDE.mdoperating defaults if anything materially changed (rare). - Reset target trajectory.
- Append
## [DATE TIME] checkin | annualtolog.md.
Ad-hoc (variable)
User says "let me update <section>". Ask only the questions for that section. Save. Done.
Common ad-hoc:
- "update preferences" → preferences refresh from monthly
- "update inventory" → kitchen + pantry
- "update meds" or "update supplements" → medical + supplements
- "update goals" → goals + targets
- "update kitchen rotation" → kitchen.md
- "update constraints" → constraints.md (e.g., job change, less time to cook)
Append ## [DATE TIME] checkin | ad-hoc <section> to log.md.
Stale-section reporting
When invoked without a specified mode, also report any stale sections (per CLAUDE.md table). Offer to refresh the most overdue one in addition to the cadenced checkin.
Bookkeeping (always)
After ANY checkin mode completes:
- Append to
log.md:## [DATE TIME] checkin | <mode> completed, <one-line summary>. - Update
index.mdwith any new pages. - Refresh
hot.md(trim entries >14 days). - If targets changed: also append
## [DATE TIME] target-change | <reason>tolog.md.
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.

