Ready to supercharge your AI agents?

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

Get Started Free →

today — measured AI agent skill | DecimalAI

abaans/today

SkillScore73Maintained

The morning brief — one synthesis across all domains. Run at the start of the day or on demand.

by abaans

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

Automatic

Personal Assistant pack

decimalai skills pull abaans-today

Get this skill — curl · raw file

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

Raw file: /s/abaans-today/SKILL.md ↗ · machine-readable summary at /s/abaans-today.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

—-21% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	187%	0%
case-04	✗→✓	▲ Improved	-53%	0%
case-06	✗→✓	▲ Improved	3%	0%
case-08	✗→✓	▲ Improved	-31%	0%
case-11	✗→✓	▲ Improved	-68%	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/today/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

today

Produce today's brief across every active domain.

Reads

Each domain's data/*.json (run refresh-domain first if stale)
Each domain's inputs/goals.md (if present)
objects/ notes with open statuses (todo, doing, blocked, draft, in-progress)
Calendar connector, if available (read-only)

Writes

personal/outputs/brief-YYYY-MM-DD.md (typed doc, doc_kind: update)

Sections, in order

Today — calendar items, in local time.
Priorities — ranked, max 5, each citing its domain.
Blockers to chase — anything with status: blocked, plus drafts still unsent.
Deadlines (14d) — every object with due in the next 14 days.
Yesterday's wins — what moved to done since the last brief.

Rules

Never write to inputs/.
If two sources disagree (e.g. a goal contradicts a task status), flag the contradiction in the

brief instead of silently picking one.

Editable in place — the human may rewrite the brief after it's generated.

Want to see if abaans/today 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.