agentleFS
totorototototorototo/ledger/.claude/skills/weekly-review/SKILL.md

weekly-review

Skill0 starsChanged 12 days agoMITView on GitHub

Review the runner's last 7 days of training against the 4 weeks before them — volume, load, intensity, notable sessions, and one or two takeaways. Use when asked how the week went, for a weekly review or recap, or "how was my training this week".

  • Reads credentials

99 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use quarterly-review, daily-plan 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.
  • Phoenixrr2113Skill

    quarterly-review

    Quarterly review — strategic look at the last 3 months. Career trajectory, project health, life balance, big decisions ahead. Runs 1st of Jan/Apr/Jul/Oct.

    Also in 3 projects that use this

  • steptianSkill

    daily-plan

    每日待办计划与日程管理。触发词:'今天要做'、'今日计划'、'今日待办'、'今天安排'、'安排一下'、'加个任务'、'记个任务'、'今日复盘'、'今日回顾'、'今天总结'、'本周计划'、'周总结'、'开始工作'、'上班了'、'完成了'、'加个日程'、'记个日程'、'改一下时间'、'日程调整'、'面试'、'开会'、'约了'。支持四象限优先级、时段分配、固定日程管理、智能时间估算、每日/每周复盘。当用户提到有明确时间的安排(如'下午两点面试'、'10点开会'),自动识别为日程并写入日程表。

    Also in 3 projects that use this

  • seedprodSkill

    daily-brief

    Send a morning briefing via Telegram with weather, news, and a motivational quote. Designed to run via launchd for automated daily delivery.

    Also in 5 projects that use this

  • claude-office-skillsSkill

    meeting-notes

    >

    Also in 8 projects that use this

  • Phoenixrr2113Skill

    morning-brief

    Full morning brief — calendar, email, meeting prep, execute actionable items, create follow-up tasks. Runs at 8:03 AM or when Randy asks for a morning update.

    Also in 4 projects that use this

  • JerovinoSkill

    process-inbox

    Processes tasks.md inbox items by triaging each one to its proper location in the vault

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 0 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 85 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every number comes from data/metrics.json, written by npm run export from the same sums the app shows (src/utils/insights.js).

    line 8
  2. Very specific:

    Read data/metrics.json. If it's missing, its until isn't today, or its version isn't 1, run npm run export (it needs …

    line 14
  3. Very specific:

    If empty is true, say there are no activities and stop.

    line 17
  4. Very specific:

    All under lastWeek (the 7 days from–until, every sport, Garmin's faults screened out):

    line 21
  5. Very specific:

    Plan: read the week through notes: a lighter week marked planned or health is explained, say so rather than asking.

    line 63
  6. Very specific:

    After the write-up, the same reading as a page in Ledger's style (scripts/reports/weekly-review.html).

    line 100
  7. Very specific:

    Write data/reports/weekly-review.notes.json (shape below).

    line 103
  8. Very specific:

    Run npm run report -- weekly-review.

    line 105

“Common” is measured: kept by at least 6 in 10 of the 85 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Weekly review

Every number comes from data/metrics.json, written by npm run export from the same sums the app shows (src/utils/insights.js). Never compute a figure yourself: quote it, or say it isn't there. Your job is to interpret.

1. Get fresh numbers

  1. Read data/metrics.json. If it's missing, its until isn't today, or its version isn't 1, run npm run export (it needs GARMIN_PERSONAL_API_KEY in .env; if that fails, say so and stop, never guess numbers).
  2. If empty is true, say there are no activities and stop.

2. Read

All under lastWeek (the 7 days from–until, every sport, Garmin's faults screened out):

FieldMeaning
volumecount, km, hours, climbM, runs, runKm, load (Garmin's training load, summed)
previous4WeeksAveragethe same fields, averaged per week over the 28 days before from (only the weeks the history covers)
weeksCoveredhow many of those 4 weeks the history covers; under 4 on a new account: say the average rests on less
changekm, hours, load as "+12%", "−8%", "±0%"; null when the 4 weeks were empty
loadacute (7-day load), chronic (28-day load per week), ratio (acute / chronic)
intensityhours with heart rate, and easyPct / moderatePct / hardPct as % of that time (Z1–2 / Z3 / Z4–5)
sessions[]date, name, type, km, hours, climbM, averageHR, load, easy (≥ 80% of HR time in Z1–2), effect (Garmin's label: TEMPO, RECOVERY…), aerobicTE / anaerobicTE (0–5)
effectssessions per effect label
hrvnights, average (ms), belowBand / aboveBand against the runner's own balanced band, and days[] (date, lastNightAvg, status, balancedLow, balancedUpper); null with no reading
restingHraverage (bpm), baseline (median of the 28 days before), raised (days ≥ 5 bpm over it), days[] (date, resting); null with no reading
sleepaverageHours, averageScore (Garmin's 0–100), under7h, days[] (date, hours, score); null with no reading
notesthe runner's plan entries overlapping the week: "race: …", "planned: …", "health: …"

Also check coverage (how many activities carry load or heart rate) and faults dated in the week: mention them if they change the picture.

plan (null without data/plan.md): nextRace (date, text, daysTo), races[], and ignored, the plan's lines the export couldn't read: name them so the runner can fix them. Without a plan, say once that scripts/plan.example.md copied to data/plan.md lets the review tell a planned week from a slump.

3. Interpret

  • Volume: say whether the week was bigger, smaller or about the same, by change. Treat ±10% as "about the same".
  • Load ratio: about 0.8–1.3 is steady; above 1.5 the week rose much faster than recent training (Gabbett, Br J Sports Med 2016, "The training–injury prevention paradox"). Under 0.8 is a lighter week, fine if planned (taper, recovery, illness).
  • Intensity: endurance athletes typically spend about 80% of their time easy (Seiler, Int J Sports Physiol Perform 2010). Point out a week far below that (a lot of Z3 "grey zone") without calling it wrong: one week is one week.
  • HRV: nights in the band mean the week was absorbed; three or more under it, with a heavier week, mean it wasn't yet (Plews et al., Sports Med 2013). Under band on a light week points away from training (illness, stress, sleep): say that, don't guess which.
  • Resting HR and sleep: supporting signs. raised days beside HRV under band firm up "not absorbed yet"; nights under 7 h beside HRV under band on a light week point to sleep (Hirshkowitz et al., Sleep Health 2015). Resting HR alone is a weak signal (Buchheit, Front Physiol 2014): never a verdict by itself.
  • Plan: read the week through notes: a lighter week marked planned or health is explained, say so rather than asking. With a nextRace, frame the takeaways by daysTo (build, taper, race week), without writing a plan.
  • Session labels: set effects beside the intensity split. A week of mostly TEMPO or THRESHOLD labels is the grey zone by another name; RECOVERY and AEROBIC_BASE are the easy end.
  • Notable sessions: the longest by time, the biggest climb, the highest load, any hard session (easy: false). Two or three at most.
  • Takeaways: one or two, concrete, about the coming week ("keep next week near this volume", "the long run carried half the week's load"). No training plans.

4. Write

**Week of <from> – <until>**

<runKm> km running · <hours> h · <climbM> m climb · <count> sessions
vs 4-week average: km <change.km> · time <change.hours> · load <change.load>
Load ratio <ratio> (7-day <acute> / 28-day <chronic> per week)
Intensity: <easyPct>% easy · <moderatePct>% moderate · <hardPct>% hard
Sessions: <effects, as "2 tempo · 1 recovery">
HRV: <average> ms, <belowBand> nights under / <aboveBand> over band (or "no reading")
Resting HR <average> bpm (baseline <baseline>) · Sleep <averageHours> h, score <averageScore>
Notes: <notes> · Next race: <text> in <daysTo> days (only with a plan)

**Stand-out sessions**
- <date> <name> (<effect>): <why it stands out, with its numbers>

**Takeaways**
1. …

Then one line of caveats when they apply: activities without load or heart rate, screened faults. End with: Based on Garmin's activity and wellness summaries; not medical advice.

5. Publish the page

After the write-up, the same reading as a page in Ledger's style (scripts/reports/weekly-review.html). The page takes its numbers from metrics.json itself: you write only words.

  1. Write data/reports/weekly-review.notes.json (shape below). Text may quote numbers from metrics.json, as the write-up does; never one of your own.
  2. Run npm run report -- weekly-review. It checks the notes, writes data/reports/weekly-review.html and prints the page's link, if it has one. On an error, fix the notes it names and run it again.
  3. Publish data/reports/weekly-review.html with the Artifact tool. With a link: read that artifact first, then publish with it as url, so the page updates in place. Without one: publish it new (icon chart), then record its link with npm run report -- weekly-review --url <link>.
  4. End the reply with the link. The page uploads the account's data to claude.ai, private until the runner shares it: never share it yourself.
{
  "takeaway": "one sentence: how the week went",
  "standouts": [
    { "date": "YYYY-MM-DD", "name": "the session's name", "text": "why it stands out" }
  ],
  "takeaways": ["one or two, about the coming week"],
  "caveat": "the caveats line, or null"
}

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.