Skip to content
cccskills
FreePublished on GitHub

process-today

Process the day into filed context — sweep today's activity (the inbound queue, CRM meetings and reminders, plus calendar, slack, and gmail when connected), extract what's worth keeping, and file it into the CRM and knowledge base. Use for "process today", "log today", "file today", "end-of-day wrap".

The English summary is being prepared. Showing the original description.

Works withSlackGmail

Run score Not tested

See how to install

Files included (1)

  • SKILL.md2.7 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Process Today

Runtime skill — a playbook the deployed @context agent runs for its owner, invoked in natural language. Not a coding-agent workflow; those live in .agents/skills/.

Turn today's raw activity into filed context. Unlike the read-only playbooks, this one writes — it ends in update_crm / update_knowledge calls, not just a summary. It still never acts on the outside world: no mail, no calendar changes, nothing leaves.

Procedure

  1. Anchor on now. "Today" is the start of the local day → now.
  2. Gather the day's raw material:
    • rundown — inbound updates from others. (It marks what it shows as briefed; do not acknowledge anything — that's the owner's call.)
    • query_crm — today's meetings and the reminders that came due today.
    • When connected: query_calendar for today's events; query_slack for today's threads the owner took part in; query_gmail for today's meaningful exchanges.
  3. Extract what has lasting value. From that material, pick out:
    • a new person → contact
    • a thing that happened, a decision made in a thread → note
    • a commitment with a date ("I'll send it Friday") → reminder with due_at
    • a follow-up that got scheduled → meeting
    • durable prose (a decision on a spec, how something now works) → the knowledge base, in the right spec sub-file Skip chit-chat, scheduling back-and-forth, and anything already on file.
  4. File it with update_crm / update_knowledge, deduping against what exists (an existing contact gets updated, not duplicated). Writes are additive — never flip reminder or ack status and never delete anything in this playbook.
  5. Report the digest. One line per item filed (what + where), then a short "left unfiled" line for material judged not worth keeping, so the owner can overrule.

Edge cases

  • Safe unattended. Scheduled runs work end to end: this playbook reads and files but never sends, so no approval gate fires.
  • A quiet day is a one-line report ("Nothing worth filing today.") — not an invented summary.
  • When unsure whether something is durable, file a note — cheap to ignore later, expensive to lose.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

The owner's morning brief — inbound updates awaiting acknowledgment (via the rundown tool), today's meetings and due-or-overdue reminders from the CRM and the real calendar, the emails worth seeing from Gmail, and the Slack threads that need their eyes — each source folded in when connected and stitched into one short digest. Use for "daily rundown", "what's on today", "morning brief", "catch me up".

The English summary is being prepared. Showing the original description.

agno-agi/context13Updated Jul 10, 2026

Run this repo's eval suite (python -m evals), diagnose every failing case, and fix in scope (agent instructions, or the eval case when its assertion was wrong) until all cases pass. Use whenever the user wants to run the evals, check for regressions, or fix a red eval suite ("run the evals", "why is a case failing", "make the eval suite green"). Targets the committed cases in evals/cases.py; for ad-hoc probing of one agent's live behavior use improve-agent instead.

The English summary is being prepared. Showing the original description.

agno-agi/context13Updated Jul 10, 2026

User-driven loop to change the context agent (or any agent in this repo) — add a source/tool/MCP server, add a capability (knowledge base, memory, sub-agent, scheduled task), refine its instructions, or fix a specific known bug, verifying each change against the live container. Use whenever the user names a concrete change ("add a Google Drive source", "make the daily rundown include the calendar", "the agent keeps doing Y, fix it"). For autonomous hardening with no specific change in mind use improve-agent.

The English summary is being prepared. Showing the original description.

agno-agi/context13Updated Jul 10, 2026

Autonomously harden the context agent (or any agent in this repo) — derive probes from the agent's own instructions, run them against the live container, judge the responses and tool calls, and edit the agent until it reliably does what it says it does. Use when the user wants to test, harden, stress-test, or improve an agent's reliability WITHOUT naming a specific change ("make sure context is solid", "harden this agent", "probe it for failure modes"). For a user-directed change use extend-agent; to run the committed eval suite use eval-and-improve.

The English summary is being prepared. Showing the original description.

agno-agi/context13Updated Jul 10, 2026

Sweep the knowledge base for what needs attention — stubs with no real content, specs whose status is stale, decisions that were made but never written down, and pages missing from the index — and return a short "what needs attention" list. Read-only, so it reports rather than fixing anything itself. Use for "what in my knowledge base needs attention", "review my knowledge base", "what's stale or unfiled", "knowledge base health check", "tidy up my knowledge".

The English summary is being prepared. Showing the original description.

agno-agi/context13Updated Jul 10, 2026

Brief the owner before a meeting or conversation with a person, company, or project — sweep what we already know (crm + knowledge, plus slack, calendar, and gmail when connected), anchor to any upcoming meeting with them, and for people or orgs we don't know, widen to a web search for public background. Use for "prep me for my meeting with X", "brief me on X before the call", "what do we know about X".

The English summary is being prepared. Showing the original description.

agno-agi/context13Updated Jul 10, 2026

See all skills by agno-agi

Report a problem with this skill