agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/session-handoff/SKILL.md

session-handoff

Skill3 starsChanged 6 months agoMITView on GitHub

Write a start-here handoff document at the end of a work session capturing state, decisions, next steps, and gotchas, so the next session (or the next person) resumes in minutes instead of re-deriving everything. Use when the user says "wrap up", "handoff", "end of session", "write a handoff note", or "where did we leave off" at the start of a new session.

143 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ascii-diagram, research-fleet and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SethGammonSkill

    ascii-diagram

    Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

    Also in 4 projects that use this

  • SethGammonSkill

    research-fleet

    Parallel research using Fleet wave mechanics. Spawns multiple scout agents, each investigating a different angle of the same question. Findings are compressed between waves. Produces a unified research brief from multiple independent perspectives.

    Also in 3 projects that use this

  • vicoa-aiSkill

    live-preview

    Start a local app in the current user project, expose it through a tunnel, and return preview details in structured Markdown. Use when the user asks for a preview URL, public URL, shareable localhost, mobile/web preview, or tunnel setup.

    Also in 4 projects that use this

  • botlearn-aiSkill

    doc-gen

    Also in 4 projects that use this

  • flyingobsidianSkill

    terminology

    Read a codebase, find terminology, create/update definitions into a markdown document.

    Also in 3 projects that use this

  • Dizzy-TenSkill

    bug-diagnosis

    Diagnose bugs and product issues without modifying code. Use when the user explicitly invokes $bug-diagnosis or asks for diagnosis, root-cause analysis, issue classification, or fix strategy for code bugs, failing tests, configuration/dependency problems, deployment issues, performance regressions, data anomalies, or frontend/user-experience problems described through screenshots, annotations, logs, errors, or natural-language reports. Prioritize analysis and recommendations only; do not edit files.

    Also in 3 projects that use this

  • +1 more from SethGammon

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 121 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    What was accomplished: only things actually finished and verified.

    line 14
  2. Very specific:

    Default target: START_HERE.md in the project root (or append a dated section to an existing one, newest at the top).

    line 23
  3. Very specific:

    When a new session starts with "where did we leave off": read START_HERE.md, confirm the state still matches reality (files may have …

    line 51
  4. Distinctive:

    Never include secrets, tokens, or credentials, even ones seen during the session.

    line 56
  5. Distinctive:

    No em dashes in any output.

    line 57

“Common” is measured: kept by at least 6 in 10 of the 121 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Session Handoff

Context dies between sessions. The next session re-reads files, re-discovers decisions, and re-hits the same trap that cost an hour last time. This skill freezes the session's working state into one document built to be read cold.

Step 1: Mine the session

Extract from the current conversation, not from memory of what should have happened:

  • What was accomplished: only things actually finished and verified. Half-done work is listed as half-done.
  • Decisions made and why: especially decisions that reversed an earlier approach. The "why" is the part the next session cannot reconstruct.
  • What is in progress: exact state, which file, which step.
  • Next steps: concrete and ordered, with the first one precise enough to start typing immediately.
  • Gotchas: everything that failed and how it was fixed, environment quirks, commands that need specific flags, things that look broken but are fine.
  • Key paths and commands: the files that matter and the exact commands to run (build, test, deploy, resume).

Step 2: Write the handoff

Default target: START_HERE.md in the project root (or append a dated section to an existing one, newest at the top). Format:

# Start Here: <date>

## TL;DR
Two sentences: where the project is, and the single next action.

## Done this session
## In progress
Exact state, file, and step for each item.

## Next steps (in order)
1. The first one must be executable immediately, with the exact command or file.

## Decisions and why
## Gotchas
What burned time this session, so it does not burn time again.

## Key paths and commands

Step 3: Verify readability cold

Reread the document as someone with zero context: no session shorthand, no "the fix we discussed", no codenames invented mid-conversation. Every reference names its file. If a next step depends on a decision, the decision is in the document too.

On resume

When a new session starts with "where did we leave off": read START_HERE.md, confirm the state still matches reality (files may have changed since), and start on next step 1. Flag divergence instead of following a stale plan.

Rules

  • Facts only. If tests were not run, the handoff says so.
  • Never include secrets, tokens, or credentials, even ones seen during the session.
  • No em dashes in any output.

Output

A START_HERE.md (or dated section) that gets the next session productive in minutes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.