agentleFS
Sign inStart free
nelantonenelantone/cognivia/.agents/skills/session-handoff/SKILL.md

session-handoff

Skill1 starsChanged 3 months agoMITView on GitHub

Create a concise factual handoff for work continuing in another session, tool, or agent. Use when the user requests a handoff, work pauses with useful state, or a blocked task needs an exact next action. Do not use automatically for trivial completed work, as an implementation plan, or to transfer edit or Git authorization.

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 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

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 121 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the user asks for a handoff or when paused or blocked work has verified state worth preserving for a later session.

    line 15
  2. Distinctive:

    Do not generate a handoff automatically for every task.

    line 20
  3. Distinctive:

    Write a handoff file only when the user authorizes a specific path.

    line 42
  4. Distinctive:

    Never include secrets, environment values, private URLs, large logs, command transcripts, or full diffs.

    line 52
  5. Distinctive:

    Never claim a file, commit, test, browser check, merge, or push exists without current evidence.

    line 54
  6. Distinctive:

    Never imply that a handoff transfers edit, commit, push, merge, deletion, or provider-call authorization.

    line 56
  7. Distinctive:

    Do not modify product files while generating a handoff.

    line 58
  8. Distinctive:

    Verify named files, commits, and paths exist.

    line 63
  9. Distinctive:

    Ensure known failures and unverified assumptions are visible.

    line 65

“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

Purpose

Transfer verified project state without forcing the next session to reconstruct completed work or trust unsupported claims.

Trigger

Use when the user asks for a handoff or when paused or blocked work has verified state worth preserving for a later session.

Do not trigger

Do not generate a handoff automatically for every task. Do not use it as a task brief, commit review, architecture audit, or authorization mechanism.

Inputs

  • Objective and current status.
  • Current branch, staged, unstaged, and untracked state.
  • Completed work and files changed.
  • Validation actually run and manual evidence actually collected.
  • Known issues, risks, assumptions, and remaining work.
  • Exact next action and prior authorization state.

Workflow

  1. Inspect current Git state and relevant diffs before describing them.
  2. Separate completed work, remaining work, known issues, and open decisions.
  3. Record validation by command and result; identify failed, skipped, and unavailable checks.
  4. Distinguish automated, manual, browser, provider, and documentation evidence.
  5. State prior authorization only as historical context; require the receiving session to obtain its own authorization for state-changing work.
  6. End with one exact next action.
  7. Write a handoff file only when the user authorizes a specific path.

Outputs

Return a handoff using the session handoff format. Keep it compact enough to paste into a new session.

Safety

  • Never include secrets, environment values, private URLs, large logs, command transcripts, or full diffs.
  • Never claim a file, commit, test, browser check, merge, or push exists without current evidence.
  • Never imply that a handoff transfers edit, commit, push, merge, deletion, or provider-call authorization.
  • Do not modify product files while generating a handoff.

Validation

  • Recheck branch and status immediately before finalizing the handoff.
  • Verify named files, commits, and paths exist.
  • Match validation claims to captured results from the current session.
  • Ensure known failures and unverified assumptions are visible.
  • Confirm the next action is specific and within remaining scope.

References

  • AGENTS.md — evidence, security, and authorization rules.
  • docs/AGENT_HANDOFF.md — temporary legacy compatibility guidance.
  • Session handoff format — canonical output structure.

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.

Check your setup, free