review
Skill0 starsChanged 6 months agoMITView on GitHub
Read recent data and produce analysis. Weekly review (last 7 days adherence + weight trend + ONE change for next week). Monthly review (4-week trend + body comp progress + supplement adherence). Quarterly review (biomarker progression + goal alignment + protocol adjustment). Annual (year-in-review). Biomarker-event review (after a new bloodwork ingest, generated automatically by ingest, but can be re-run). Correlation review (symptoms vs food, sleep vs eating, mood vs sleep, recovery vs lifting). Lint (find contradictions across pages, stale claims, orphan pages, missing cross-references, gaps). Risk projection (where biomarkers are headed if current pace continues; e.g., "HbA1c will hit 6.0 by November"). Pattern dashboards (weight + kcal + protein + sleep + RHR over 30/90 days as a chart). Invoke when the user says "weekly review", "how am I doing", "review my week", "monthly review", "quarterly", "year in review", "am I on track", "what's my trend", "show me a chart", "where am I headed", "what does my data say", "check my data", "lint", "/review", or after an ingest of bloodwork (auto-chains to biomarker-event review).
192 other projects use a version of this.
Adopted by
Most recently taken up by
- dzhng/skillstheir own version, first seen Nov 15, 2026
- muxy-app/muxytheir own version, first seen Nov 15, 2026
- macro-inc/macrotheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- markmhendrickson/neotomatheir own version, first seen Nov 15, 2026
- felipeam86/pipe-skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use close-spec, daily-arxiv 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.
dzhngSkillclose-spec
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Also in 5 projects that use this
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
dzhngSkilldesign-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
- +5 more from Lambenthan
- +3 more from dzhng
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 192
- garrytan/gstack★ 142ksame name
- ansible/ansible★ 71ksame name
- docling-project/docling★ 71ksame name
- traefik/traefik★ 66ksame name
- ClickHouse/ClickHouse★ 51ksame name
- temporalio/temporal★ 24ksame name
- ccch1mneyyy/dsh-Go★ 24ksame name
- tisfeng/Easydict★ 15ksame name
- juicedata/juicefs★ 15ksame name
- elie222/inbox-zero★ 13ksame name
182 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
8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 156 edited versions we read keep these.
4
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
- Distinctive: line 8
Read data, produce analysis.
- Very specific: line 12
If wiki/profile/identity.md is empty, redirect: "We don't have a baseline yet.
- Very specific: line 18
Read last 7 daily logs from wiki/logs/YYYY/MM/.
- Distinctive: line 61
Consider revising CLAUDE.md operating defaults if anything materially shifted (rare)
- Very specific: line 84
Read daily logs over the last 30/60/90 days (let user pick window or default to 60).
- Distinctive: line 113
Read the relevant biomarker series.
- Distinctive: line 125
Read relevant series (weight, kcal, protein, sleep, RHR, HRV, etc.) over user-chosen window.
- Very specific: line 134
Update index.md with new review page.
“Common” is measured: kept by at least 6 in 10 of the 156 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
Review skill
Read data, produce analysis. Always cite the wiki pages your analysis comes from.
Pre-flight
If wiki/profile/identity.md is empty, redirect: "We don't have a baseline yet. Want to onboard first?" then invoke checkin (onboarding).
Sub-flows
Weekly review
- Read last 7 daily logs from
wiki/logs/YYYY/MM/. - Compute:
- kcal hit %, protein hit %, fiber hit % (vs
wiki/targets/current.md) - Days with no log (missed days)
- Weight 7-day moving average + trend (↓/→/↑)
- Workouts done vs planned
- Sleep average
- Symptoms recurring this week
- kcal hit %, protein hit %, fiber hit % (vs
- Identify wins (best day, easiest meal, biggest improvement).
- Identify friction (worst day, where adherence broke, recurring failure mode).
- Propose ONE change for next week (one only, per adherence principle).
- Save as
wiki/reviews/weekly/YYYY-WXX.md. - Refresh
hot.md. - Append
## [DATE TIME] review | weekly YYYY-WXXtolog.md.
Monthly review
Same as weekly but for last 4 weeks. Add:
- Body comp delta (waist, weight, photo if available)
- Supplement adherence rate
- Lab results if any happened this month
- Strategic adjustment (multiple changes are OK at monthly cadence)
Save as wiki/reviews/monthly/YYYY-MM.md.
Append ## [DATE TIME] review | monthly YYYY-MM to log.md.
Quarterly review
Same as monthly but for last 12 weeks. Add:
- Biomarker progression (read all ingested bloodwork over the quarter)
- Goal alignment check
- Protocol adjustment proposal
- Big-picture narrative
Save as wiki/reviews/quarterly/YYYY-Q?.md.
Append ## [DATE TIME] review | quarterly YYYY-Q? to log.md.
Annual review
Same as quarterly but for last 12 months. Add:
- Year-in-review story (what changed, what didn't, what we learned)
- Goal reset proposal for next year
- Workout periodization for next year
- Consider revising CLAUDE.md operating defaults if anything materially shifted (rare)
Save as wiki/reviews/annual/YYYY.md.
Append ## [DATE TIME] review | annual YYYY to log.md.
Biomarker event review
(Usually generated automatically by ingest skill on bloodwork ingest. Re-run if user wants a fresh re-analysis or didn't get the auto-version.)
For a specific bloodwork date:
- Compare to previous reading (numeric diff per marker).
- Flag abnormals against India thresholds.
- Connect to recent diet/lifestyle changes if visible in logs (e.g., "switched to mustard oil 6 weeks ago, LDL dropped 15 points").
- Propose plan adjustments (specific: "raise fiber target from 35 to 40g for next 12 weeks").
- Recommend physician follow-up if needed.
Save as wiki/reviews/biomarker-events/YYYY-MM-DD-<labname>.md.
Append ## [DATE TIME] biomarker-event | <summary> to log.md.
Correlation review
Find patterns across symptoms + food + sleep + mood + recovery over time.
- Read daily logs over the last 30/60/90 days (let user pick window or default to 60).
- Look for:
- Symptoms that recur after specific foods (gluten, dairy, high-carb meals, specific spices like Saoji)
- Energy crashes correlated with meal timing or composition (post-rice 3pm crash)
- Mood dips correlated with sleep deprivation (Oura readiness <70 + low energy)
- Workout PR days correlated with rest/sleep/food the day before
- Bloating correlated with specific dals or vegetables
- Sleep quality vs alcohol/caffeine timing
- Save findings as
wiki/reviews/correlations/YYYY-MM-DD-<topic>.md. - Surface the most actionable insight to the user.
- Append
## [DATE TIME] review | correlations: <topic>tolog.md.
Lint
- Walk all wiki pages.
- Find:
- Contradictions: two pages claiming different facts about the same thing (e.g., target weight in goals.md vs targets/current.md)
- Stale claims: data superseded by newer entries (old weight in profile vs latest in anthropometry)
- Orphan pages: no inbound links from anywhere
- Missing cross-references: pages that should link to each other (food-library entry referencing a nonexistent knowledge page)
- Gaps: recurring questions in chat history (or recurring symptoms in logs) that lack a dedicated page
- Report findings to the user. Offer to fix each one.
- Save report as
wiki/reviews/lint-YYYY-MM-DD.md. - Append
## [DATE TIME] lint | <N findings>tolog.md.
Risk projection
User: "where is my HbA1c headed" / "what's my trajectory" / "if I keep going like this"
- Read the relevant biomarker series.
- Fit a simple linear trend (or piecewise if there's a clear regime change).
- Project to 3 months / 6 months / 12 months.
- Flag if projection crosses any India threshold (HbA1c 5.7 → prediabetic, LDL 100 → at-risk, etc.).
- State clearly: "this is a linear projection assuming current pace continues. Behavior change can bend the curve."
- Save as
wiki/reviews/projections/YYYY-MM-DD-<biomarker>.md. - Append
## [DATE TIME] review | projection: <biomarker>tolog.md.
Pattern dashboard (chart)
User: "show me a chart" / "dashboard" / "visualize my X"
- Read relevant series (weight, kcal, protein, sleep, RHR, HRV, etc.) over user-chosen window.
- Generate matplotlib chart via Bash (small Python script). Save PNG to
wiki/reviews/charts/YYYY-MM-DD-<topic>.png. - Embed in a markdown wrapper page that explains what's shown.
- Append
## [DATE TIME] review | chart: <topic>tolog.md.
Bookkeeping (always)
After every review:
- Append to
log.mdwith rightkind. - Update
index.mdwith new review page. - Refresh
hot.mdwith the key insight from this review.
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.

