agentleFS
assisjpassisjp/specflow/skills/productivity/session-handoff/SKILL.md

session-handoff

Skill17 starsChanged 3 months agoMITView on GitHub

Save a concise session checkpoint so another session or tool can resume after the user closes the chat. Record scope, authorization, source state, checks and next action; retain the last usable checkpoint until safely superseded.

Files
SKILL.md

Session Handoff

Save a concise checkpoint so the user can close this chat and another session can resume. Do not require another interview to summarize known state. Retain the last usable checkpoint until it is superseded or the receiving session confirms a durable continuation (ADR 0010).

Save safely

Use the project's handoff location; otherwise .scratch/handoffs/<short-slug>.md. Ensure that default is ignored before writing sensitive session state. If changing .gitignore is outside scope, use an authorized task-local location and report it. Exclude secrets and unnecessary personal data. Never delete another session's checkpoint or assume reading it authorizes deletion.

Reference durable specs, tickets, glossary and ADRs rather than copying them. Short reasons and temporary debugging hypotheses can remain in a handoff; promote only decisions that satisfy domain-modeling's ADR criteria. Do not create an ADR for every “why”.

Contents

# Handoff — <topic>

- Recorded: <date/time>
- State: active checkpoint; supersedes <path, if any>
- Objective and accepted scope: <including later corrections>
- Authorization/constraints: <execution environment, browser, publication, production>
- Checkout/worktree: <exact path>
- Git: <branch, measured HEAD, dirty paths, measured upstream state or unknown>
- Unsaved/uncommitted work: <where its actual contents survive; patch/commit if available>
- Completed: <outcomes, not a transcript>
- Remaining/blockers: <facts, uncertainties and temporary hypotheses>
- Checks/evidence: <command, result, source identity and environment; unrun items>
- Owned active processes/remote actions: <IDs, state, pending migrations/deploys,
  temporary recovery controls, or none>
- Sources: <spec/ticket/decision/evidence paths or URLs>
- Next action: <one concrete continuation and dependencies>

A dirty-file list and HEAD do not preserve the dirty contents on another machine. Say whether the handoff requires the same checkout; reference a saved patch/commit only if it actually exists. Do not claim source portability from path references alone. Record remote state only when measured, otherwise mark it unknown.

For an active review-loop, also record its mode (review-only or review-and-fix), base and reviewed snapshot, round budget consumed/remaining, ledger location or unresolved IDs, reviewer/task state, and the exact delta or evidence needed next. A prior approval does not certify a later candidate.

For a takeover or pr-maintenance handoff, also record the source PR/branch/worktree, observed head/base SHAs and time, disposition, contributor/ownership constraints, active monitor state, and whether the next session may modify or only assess the candidate.

Resume and retention

The receiving session first verifies checkout/source state and constraints, then reuses still-valid decisions and checks. Stale status must be reconciled with reality; a checkpoint is not authority to repeat a deployment or widen permissions. Do not rerun green checks for unchanged inputs merely because the session changed.

Report the saved path and the next action so the user can close the chat. Mark a checkpoint superseded only when a successor exists or continuation is durably recorded. Deletion/retention follows the user's or project's policy; never remove the last usable checkpoint merely because it was read. Default to retaining it without placing transient state in a feature PR.

Download now (ZIP)

  • Other versions131 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 131

    1. rohitg00/pro-workflow★ 2.9ksame name
    2. SethGammon/Citadel★ 927same name
    3. OneWave-AI/claude-skills★ 378same name
    4. ai-analyst-lab/ai-analyst★ 304same name
    5. entireio/skills★ 223same name
    6. Innei/SKILL★ 91same name
    7. yuzushi-dev/session-handoff★ 67same name
    8. Hive-Academy/ptah-extension★ 31same name
    9. aktsmm/Agent-Skills★ 26same name
    10. upex-galaxy/agentic-qa-boilerplate★ 26same name

    121 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use ascii-diagram, research-fleet and 10 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
  • In this repository14 other files it gives its agents.

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.