Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Weekly Review Skill · ballred | DecimalAI

ballred/weekly

SkillScore77Maintained

Facilitate weekly review process with reflection, goal alignment, and planning. Create review notes, analyze past week, plan next week. Use on Sundays or whenever doing weekly planning.

productivityby ballred

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Knowledge Management pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/ballred-weekly/SKILL.md

decimalai skills pull ballred-weekly --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ballred-weekly/SKILL.md https://app.decimal.ai/s/ballred-weekly/SKILL.md

Raw file: /s/ballred-weekly/SKILL.md ↗ · machine-readable summary at /s/ballred-weekly.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 46d ago

—+60% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	55%	0%
case-05	✗→✓	▲ Improved	53%	0%
case-06	✗→✓	▲ Improved	56%	0%
case-07	✗→✓	▲ Improved	77%	0%
case-10	✗→✓	▲ Improved	47%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ballred / obsidian-claude-pkm

vault-template/.claude/skills/weekly/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Weekly Review Skill

Facilitates your weekly review process by creating a review note and guiding reflection on the past week while planning the next.

Usage

Invoke with /weekly or ask Claude to help with your weekly review.

/weekly

What This Skill Does

Creates Weekly Review Note

Uses weekly review template
Names it with current week's date
Places in Goals folder

Guides Review Process

Reviews last week's accomplishments
Identifies incomplete tasks
Plans upcoming week
Aligns with monthly goals

Automates Housekeeping

Archives old daily notes
Updates project statuses
Cleans up completed tasks

Review Process Steps

Step 1: Reflection (10 minutes)

Review daily notes from past week
Identify wins and challenges
Capture lessons learned

Step 2: Goal Alignment + Project Rollup (10 minutes)

Check monthly goal progress
Adjust weekly priorities
Ensure alignment with yearly goals
Auto-scan Projects/*/CLAUDE.md for current status
Compile project progress table for the review note

Step 3: Planning (10 minutes)

Set ONE big thing for the week
Include project next-actions when planning week
Schedule important tasks
Block time for deep work

Interactive Prompts

The skill guides you through:

"What were your top 3 wins this week?"

Celebrates progress
Builds momentum
Documents achievements

"What were your main challenges?"

Identifies obstacles
Plans solutions
Learns from difficulties

"What's your ONE big thing next week?"

Forces prioritization
Creates focus
Drives meaningful progress

Weekly Review Checklist

] Review all daily notes
] Process inbox items
] Update project statuses
] Check upcoming calendar
] Review monthly goals
] Plan next week's priorities
] Block time for important work
] Clean digital workspace
] Archive completed items
] Commit changes to Git

Weekly Review Note Format

markdown
# Weekly Review: YYYY-MM-DD

## Last Week's Wins
1.
2.
3.

## Challenges & Lessons
- Challenge:
- Lesson:

## Goal Progress
### Monthly Goals
- [ ] Goal 1 (XX%)
- [ ] Goal 2 (XX%)

### This Week's Contribution
- [Task] -> [[Goal]]

## Project Progress
| Project | Phase | Progress | Next Action |
|---------|-------|----------|-------------|
| [[ProjectA]] | Active | 60% | [Next step] |
| [[ProjectB]] | Planning | 10% | [Next step] |

## Next Week Planning

### ONE Big Thing
>

### Key Tasks
- [ ]
- [ ]
- [ ]

### Project Next-Actions
- [ ] [ProjectA] - [specific next step]
- [ ] [ProjectB] - [specific next step]

### Time Blocks
- Monday:
- Tuesday:
- Wednesday:
- Thursday:
- Friday:

## Notes

Automation Features

Auto-Archive

Suggest moving daily notes older than 30 days to Archives.

Project Status Update

For each active project:

Update completion percentage
Note blockers
Set next actions

Habit Tracking

Calculate habit success rates from daily notes:

Count habit checkboxes
Show completion percentage
Identify patterns

Best Practices

Consistent Timing

Same day each week (Sunday recommended)
Same time if possible
Block calendar time
Treat as non-negotiable

Preparation

Clean inbox before review
Have calendar ready
Gather project updates
Review any feedback

Follow-through

Share highlights with team/family
Update external systems
Communicate changes
Celebrate wins

Task-Based Progress Tracking

The weekly skill uses session tasks to show progress through the 3-phase review.

Phase Tasks

Create tasks at skill start:

TaskCreate:
  subject: "Phase 1: Collect"
  description: "Gather daily notes from past week, extract wins and challenges"
  activeForm: "Collecting daily notes and extracting highlights..."

TaskCreate:
  subject: "Phase 2: Reflect"
  description: "Calculate goal progress, analyze alignment gaps"
  activeForm: "Calculating goal progress and alignment..."

TaskCreate:
  subject: "Phase 3: Plan"
  description: "Identify ONE Big Thing, plan daily focus areas for next week"
  activeForm: "Planning next week's focus..."

Dependencies

Phases must run in order:

TaskUpdate: "Phase 2: Reflect", addBlockedBy: [phase-1-collect-id]
TaskUpdate: "Phase 3: Plan", addBlockedBy: [phase-2-reflect-id]

Reflect is blocked until Collect completes. Plan is blocked until Reflect completes. This provides visibility into the 30-minute review process.

Mark each task in_progress when starting, completed when done using TaskUpdate.

Task tools are session-scoped and don't persist between Claude sessions—your actual weekly review content is saved in the review note.

Agent Team Workflow (Optional)

For a faster, more thorough weekly review, use agent teams to parallelize the collection phase:

Team Lead (coordinator)
├── collector agent — Read all daily notes, extract wins/challenges/tasks
├── goal-analyzer agent — Read goal files, calculate progress, find gaps
└── project-scanner agent — Scan Projects/*/CLAUDE.md, get status updates

How to Use

When invoking /weekly, you can request the team-based approach:

/weekly
"Use the team approach for a thorough review"

The team lead:

Spawns three agents to work in parallel
Collector reads daily notes and extracts highlights
Goal-analyzer reads all goal files and calculates progress
Project-scanner reads all project CLAUDE.md files for status
Team lead synthesizes findings into the weekly review note

This makes the review faster (parallel collection) and more thorough (dedicated analysis per area).

Vault Health Check (Ad-hoc)

The weekly review can optionally include a vault health check using multiple agents:

note-organizer: Scan for broken links, orphan notes
goal-aligner: Check daily-to-goal alignment
inbox-processor: Check for unprocessed items

Request with: "Include a vault health check in my weekly review"

Integration

Works with:

/daily - Reviews daily notes from the week
/monthly - Weekly reviews feed monthly rollup
/project - Project status in review
/push - Commit after completing review
/onboard - Load context for informed review
Goal tracking skill - Progress calculations

Illustrative Want to see what ballred/weekly would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/12/2026, 16:20 UTC · 22 cases

Measured on 20 comparable cases — below the 22 needed to publish a lift, so this result is shown here but not on the registry card or leaderboard.

Lift

+50%

77% vs 27%

Agent turns

1.0 vs 1.0

Tokens

+60%

2,294.8 vs 1,431.5

fail → pass · 11pass → pass · 6fail → fail · 5

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 It's Sunday evening and I need to complete my end-of-week reflection. Can you help me review my daily logs, pull in updates from my project files, and compile a structured weekly review note with my accomplishments and plans for next week?	fail→fail	5,793	7,269	+25%	1	1	0%	1,033	2,114	+105%	0	0	—
case-02 I'd like to perform a full weekly review using the multi-agent approach. Please gather achievements from my daily notes, evaluate my goal alignment, and build the summary document for my Goals folder.	fail→fail	5,983	35,024	+485%	1	1	0%	1,064	2,230	+110%	0	0	—
case-03 Can we kick off `/weekly`? I want to reflect on my major wins and challenges, generate the project progress matrix, and outline my primary focus and calendar blocks for the upcoming week.	fail→fail	6,390	4,432	-31%	1	1	0%	1,102	2,203	+100%	0	0	—
case-04 I am finishing my weekly review and need to save my note file titled 'Weekly Review 2025-03-30'. I usually save administrative reviews in a 'Reviews' or 'Archives' folder. Where should this note be placed?	fail→pass	7,974	3,541	-56%	1	1	0%	1,402	2,168	+55%	0	0	—
case-05 I want to set up an automated script to harvest status updates from all my project directories for the review summary. Should I parse the main README.md files or top-level project markdown files in each project directory?	fail→pass	11,550	6,889	-40%	1	1	0%	1,778	2,713	+53%	0	0	—
case-06 When setting up session task tracking for the weekly review process, I want to execute all three phases simultaneously to save time. How should phase dependencies be configured?	fail→pass	10,753	8,490	-21%	1	1	0%	1,964	3,071	+56%	0	0	—
case-07 I want to kick off the interactive reflection step. What exact question should be asked first to prompt the user for their achievements?	fail→pass	7,301	1,956	-73%	1	1	0%	1,059	1,879	+77%	0	0	—
case-08 During the interactive planning step, what exact question should be asked to help the user identify their main priority for the upcoming week?	pass→pass	5,520	1,762	-68%	1	1	0%	837	1,821	+118%	0	0	—
case-09 My daily notes folder has accumulated files over several months. Should I move daily notes older than 7 days, 14 days, or 30 days into Archives during housekeeping?	pass→pass	9,467	5,514	-42%	1	1	0%	1,658	2,398	+45%	0	0	—
case-10 I am designing the Markdown table layout for summarizing project statuses in the review note. What four column headers should be included across the table?	fail→pass	8,402	2,858	-66%	1	1	0%	1,359	2,000	+47%	0	0	—
case-11 When using agent teams for parallelizing the review collection phase, I plan to assign generic roles like 'Note Extractor', 'Goal Evaluator', and 'Doc Writer'. What specific agent names should be used instead?	fail→pass	13,127	4,092	-69%	1	1	0%	2,097	2,337	+11%	0	0	—
case-12 I want to run an ad-hoc vault health check as part of my weekly review. Which specialized sub-agents should be requested for this health check?	fail→pass	12,132	3,640	-70%	1	1	0%	2,105	2,203	+5%	0	0	—
case-13 Under Next Week Planning in the review note, I want to block time for major priorities. Which specific days should have designated time block lines in the note template?	pass→pass	6,918	1,477	-79%	1	1	0%	1,124	1,772	+58%	0	0	—
case-14 I want to calculate habit success rates automatically during weekly housekeeping. Should I measure word count length in journal entries, count habit checkboxes in daily notes, or track git commits?	pass→pass	11,170	9,268	-17%	1	1	0%	1,969	3,113	+58%	0	0	—
case-15 What is the final action listed on the weekly review checklist after cleaning up the digital workspace and archiving completed items?	fail→pass	6,820	12,806	+88%	1	1	0%	1,105	1,763	+60%	0	0	—
case-16 I have 30 minutes scheduled for my weekly review. How many minutes are allocated to each of the three steps: Reflection, Goal Alignment + Project Rollup, and Planning?	fail→pass	7,605	1,893	-75%	1	1	0%	1,344	1,856	+38%	0	0	—
case-17 When laying out the Goal Progress section in the weekly review note, what two sub-headings should be used to separate long-term goals from short-term efforts?	fail→pass	5,995	2,000	-67%	1	1	0%	984	1,886	+92%	0	0	—
case-18 What exact interactive prompt question should be asked right after reviewing wins to discuss obstacles encountered during the week?	pass→pass	6,121	1,817	-70%	1	1	0%	967	1,852	+92%	0	0	—
case-19 When creating the session task for Phase 1 Collect in task tracking, what subject string and activeForm description should be specified?	fail→pass	8,427	2,235	-73%	1	1	0%	1,260	1,821	+45%	0	0	—
case-20 I need to perform my end-of-month synthesis across all four past weeks to calculate overall quarterly trajectory and update strategic milestones. Can you write my monthly rollup note?	fail→fail	8,465	8,175	-3%	1	1	0%	1,462	3,066	+110%	0	0	—
case-21 I am launching a new software project in my vault. Can you draft a full root-level CLAUDE.md file for the new project folder including code style guidelines and build commands?	fail→fail	11,364	10,835	-5%	1	1	0%	1,988	3,481	+75%	0	0	—
case-22 It's Tuesday morning at 9 AM and I want to log my morning standup notes, track today's water intake, and record my immediate task list for today.	pass→pass	5,971	5,204	-13%	1	1	0%	1,066	2,493	+134%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 20 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +50 percentage points is the difference between those two pass rates over the 20 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 27.3%
Pass rate with the skill: 77.3%
Cases attempted: 22
Cases counted toward lift: 20
Cases that regressed: 0
Skill version measured: v1
Run completed: 8/12/2026, 16:20 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-04

Prompt

I am finishing my weekly review and need to save my note file titled 'Weekly Review 2025-03-30'. I usually save administrative reviews in a 'Reviews' or 'Archives' folder. Where should this note be placed?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run77

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+77% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 46 days ago

Other measured skills in the registry, with their headline benchmark lift.