Skip to content
cccskills
FreePublished on GitHub

codexkit-follow-up-draft-builder

Draft concise follow-up messages, nudges, reminders, and recap emails from open decisions, stale requests, or recent meetings. Use when the work is repetitive business writing with known context. Do not use for sensitive legal language, high-stakes negotiation, or board-level communication without review.

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

See how to install

Files included (2)

  • SKILL.md2.7 KB
  • agents/openai.yaml178 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Follow-Up Draft Builder

Purpose

Write short operational follow-ups that move work forward without overthinking.

When to use

  • someone needs a reminder, nudge, or recap
  • open decisions need a clean ask and due date
  • the task is routine communication, not persuasion strategy

When not to use

  • the message carries legal, HR, or regulatory risk
  • tone calibration matters more than speed

Inputs

  • source context or prior thread summary
  • target audience
  • goal of the message
  • preferred tone if known

Procedure

  1. Identify the ask, owner, and desired timing.
  2. Strip background detail down to only what the receiver needs.
  3. Draft the message with a clear subject or opening line.
  4. End with one explicit next step.
  5. Provide a shorter variant if the user likely needs chat or Slack format.

Output

  • follow-up message draft
  • optional short-form version

Definition of done

  • the request is clear in one read
  • the recipient knows what action is needed
  • the draft is brief enough to send with minor edits

Examples

  • "Write a reminder to finance for the missing close evidence."
  • "Draft a polite follow-up to the vendor on the contract intake questions."

Quality Criteria

  • Trigger conditions and input requirements are unambiguous
  • Each automated step produces a verifiable output
  • Error handling and fallback paths are defined
  • Manual override points are documented

Verification (4C)

CheckQuestion
CorrectnessDoes the workflow produce the expected output for the defined inputs?
CompletenessAre all trigger conditions, edge cases, and error paths handled?
Context-fitIs the automation appropriate for the frequency and criticality of this task?
ConsequenceIf this ran unattended and failed silently, what would the downstream impact be?

Edge Cases

  • Input format varies unexpectedly — Add a normalization step at entry. Alert the operator on format mismatches.
  • Downstream system is unavailable — Queue the output and retry with exponential backoff. Alert after N failures.
  • Partial execution completes — Ensure idempotency — re-running from the start produces the same result without duplication.

Changelog

  • v1.0.0 — Initial release

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

Design rigorous A/B test plans with hypothesis, sample size calculation, Minimum Detectable Effect (MDE), randomization strategy, and decision rules. Includes guardrail metrics and rollout playbook. Use when planning product experiments, conversion optimization, or data-driven feature decisions.

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

hoavdc/CodexKit25Updated Oct 11, 2026

Review REST and GraphQL API designs for consistency, usability, and best practices. Covers naming conventions, versioning strategy, error format, pagination, authentication patterns, and breaking change detection. Use when reviewing API specs, designing new APIs, or auditing existing endpoints.

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

hoavdc/CodexKit25Updated Oct 11, 2026

Write Architecture Decision Records (ADRs) following the Michael Nygard format. Captures context, options considered, decision rationale, and consequences. Use when making technology choices, framework selections, or any architectural decision that future developers need to understand.

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

hoavdc/CodexKit25Updated Oct 11, 2026

Assess organizational readiness for financial audits (internal or external). Map assertions to account balances, check evidence completeness, score readiness using a Red/Amber/Green framework, and generate a remediation timeline. Aligned with SOX, IFRS, and GAAP audit standards. Use before scheduled audits or when preparing for first-time compliance.

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

hoavdc/CodexKit25Updated Oct 11, 2026

Design safe recurring Codex automations with clear prompts, outputs, schedules, and gating rules.

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

hoavdc/CodexKit25Updated Oct 11, 2026

Refine Product Backlog Items to meet INVEST criteria. Write User Stories with Acceptance Criteria in Given/When/Then format, estimate with Story Points, and flag dependencies. Use before sprint planning when backlog items need grooming. Do not use to prioritize the backlog — that is the Product Owner's decision.

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

hoavdc/CodexKit25Updated Oct 11, 2026

See all skills by hoavdc

Report a problem with this skill