agent-handoff-brief
Skill0 starsChanged 5 months agoMITView on GitHub
Use when handing work from one AI agent, developer, or session to another by summarizing current state, files touched, decisions made, blockers, verification, and next safe actions.
In this repository19 other files it gives its agents.
- api-doc-to-tool-specSkill
- architecture-rfc-reviewSkill
- bug-report-to-reproSkill
- changelog-to-upgrade-planSkill
- competitive-research-briefSkill
- customer-call-to-prdSkill
- database-migration-risk-reviewSkill
- dependency-upgrade-risk-reviewSkill
- incident-log-to-postmortemSkill
- messy-notes-to-decision-logSkill
- privacy-data-flow-mapSkill
- prompt-to-eval-rubricSkill
- repo-launch-readiness-reviewSkill
- roadmap-to-release-planSkill
- security-review-checklistSkill
- support-ticket-to-evalSkill
- telemetry-to-product-insightsSkill
- tool-permission-auditSkill
- workflow-automation-scoutSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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
- Distinctive: line 10
Create a compact handoff that lets another agent resume without redoing discovery.
- Distinctive: line 14
Use when work needs to continue across agents, sessions, context compaction, or developer handoff.
- Distinctive: line 15
Do not use when the task is already complete and no next actor needs evidence, files, or blockers.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Handoff Brief
Purpose
Create a compact handoff that lets another agent resume without redoing discovery.
Fit
- Use when work needs to continue across agents, sessions, context compaction, or developer handoff.
- Do not use when the task is already complete and no next actor needs evidence, files, or blockers.
Inputs
- Current task, conversation notes, file changes, commands run, or partial results.
- Known blockers, validation status, and user constraints.
- Repository path or artifact locations.
Workflow
- State the objective and current status.
- List files touched and decisions made.
- Record commands run and their outcomes.
- Capture blockers, risks, and unresolved questions.
- Recommend the next safe action.
Output
Produce Markdown with:
- Objective
- Current State
- Files And Artifacts
- Decisions
- Verification
- Blockers
- Next Actions
Validation
- The handoff distinguishes facts from plans.
- File paths and artifact names are precise.
- Verification status includes what was not tested.
- Next actions are ordered and reversible when possible.
- The receiving agent should not need the full prior chat to continue.
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
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.