Ready to supercharge your AI agents?

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

Get Started Free →

weekly-review — measured AI agent skill | DecimalAI

abaans/weekly-review

SkillScore77Maintained

End-of-week review — close loops, surface drift, set next week's top three. Run once a week.

by abaans

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

Automatic

Knowledge Management pack

decimalai skills pull abaans-weekly-review

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/abaans-weekly-review/SKILL.md

Raw file: /s/abaans-weekly-review/SKILL.md ↗ · machine-readable summary at /s/abaans-weekly-review.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 7d ago

—-32% tokens0% turns77% of whole cases pass with skill (17/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	345%	0%
case-05	✗→✓	▲ Improved	181%	0%
case-07	✗→✓	▲ Improved	-49%	0%
case-08	✗→✓	▲ Improved	-37%	0%
case-09	✗→✓	▲ 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 — 8/1/2026

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

abaans / agent-spine

toolbox/weekly-review/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

weekly-review

Reads

The week's daily briefs in personal/outputs/brief-*.md
All objects/ notes, every domain
memory/ for context on ongoing threads

Writes

personal/outputs/review-YYYY-Www.md (typed doc, doc_kind: update)

Steps

Closed — everything that hit done/sent/delivered this week, grouped by domain.
Open loops — objects with next_action set, status: blocked, or status: draft

older than 7 days. Each gets a one-line "what unblocks it".

Drift — projects untouched for 14+ days. Ask: still real, or should it be on-hold?
Needs review — list every status: needs-review note; propose a classification for each.
Next week's three — propose the top three priorities. The human confirms or edits.

Rules

Never write to inputs/.
Propose status changes to objects/; apply them only to frontmatter, never rewrite bodies.

Want to see if abaans/weekly-review would activate on your phrasing? Try it before you install — no LLM call, no signup.

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