CtrlK
BlogDocsLog inGet started
Tessl Logo

session-handoff

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

97

1.02x
Quality

100%

Does it follow best practices?

Impact

89%

1.02x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

Preserving Context for a Paused Feature Branch

CREATE handoff workflow

Criteria
Without context
With context

Script used to create

100%

100%

Correct storage directory

100%

100%

Filename format

100%

100%

Current State Summary filled

100%

100%

Important Context filled

100%

100%

Immediate Next Steps filled

100%

100%

Decisions Made filled

100%

100%

No TODO placeholders

100%

100%

Validation script run

100%

100%

Quality threshold enforced

100%

100%

Report to user

100%

100%

79%

8%

Picking Up a Paused Data Pipeline Migration

RESUME handoff workflow

Criteria
Without context
With context

list_handoffs.py run

100%

100%

check_staleness.py run

100%

100%

Staleness level recorded

100%

100%

Chain predecessor read

20%

100%

Git branch verified

50%

37%

Assumptions validated

100%

100%

Starts with Next Step 1

58%

58%

Pending Work updated

0%

20%

New discoveries added

100%

100%

Blockers flagged

75%

62%

No secrets in notes

100%

100%

90%

Extending a Long-Running API Refactor

Handoff chaining and proactive suggestion

Criteria
Without context
With context

--continues-from flag used

100%

100%

Chain link in handoff

100%

100%

Predecessor marked superseded

100%

100%

Correct storage directory

100%

100%

Filename format correct

100%

100%

No TODO placeholders

100%

100%

Validation script run

100%

100%

Quality score 70+

100%

100%

Proactive suggestion documented

0%

0%

Priority sections completed

100%

100%

Repository
softaworks/agent-toolkit
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.