handoff-report

Structure substantive work reports with outcome-first ordering and evidence-pointed reasoning.

1.6k|141|Updated Dec 16, 2025
One-click install
npx skills add https://github.com/happier-dev/happier --skill handoff-report
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: handoff-report
Source: https://github.com/happier-dev/happier/tree/main/skills/handoff-report
Command: npx skills add https://github.com/happier-dev/happier --skill handoff-report

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reports on completed work often bury failures, mix verified facts with assumptions, and hide residual risk, causing readers to act on misread conclusions. This Skill enforces an output contract so any handoff report is auditable and actionable from the first paragraph.

Core Features & Use Cases

  • Outcome-first structure: The first sentence states what happened, what was found, or what is blocked, with failures and scope changes disclosed up front.
  • Evidence labeling: Every load-bearing statement is marked as observed, derived, or assumed, with file/line references, log excerpts, or commands backing each claim.
  • Residual risk section: Unverified items, next checks, and invalidating conditions are stated explicitly at the end.
  • Use Case: After finishing a debugging session or code review, produce a handoff report where a teammate who was away can act on the TLDR and audit every claim via cited evidence.

Quick Start

Write a handoff report for the work just completed, leading with the outcome, labeling each claim as observed, derived, or assumed, and ending with residual risks.

Frequently Asked Questions about handoff-report

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write a handoff report for completed engineering work?

Lead with the outcome in the first sentence, disclose failures and scope changes immediately, back each claim with file and line references or log excerpts, and close with residual risks. Label statements as observed, derived, or assumed so readers can audit the reasoning.

What is the difference between observed, derived, and assumed claims in a report?

Observed means you ran it, read it, or saw it directly. Derived means it follows from observations by stated reasoning, which you must spell out. Assumed means plausible but unverified, and must be marked explicitly rather than implied by tone.

When should a retrospective be included in a handoff report?

Include a retrospective only when the user explicitly requests one or an approved substantial program designates it. It should capture evidence-backed learning such as changed decisions, disproved assumptions, and promotion recommendations, not routine metrics.

Why should failures be reported first instead of at the end?

Failures, skipped steps, and scope changes are the most decision-relevant events, so they belong in the first block where the reader cannot miss them. Burying them mid-report risks the reader acting before encountering the caveat that should have informed the decision.

When should a lesson from one incident be promoted into a reusable rule?

Promote a lesson into a skill or repository doctrine only when it reflects a stable repository property, repeats across materially distinct work, or the user explicitly approves it. A single incident normally remains a local lesson.