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

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that excels across all dimensions. It provides specific capabilities, comprehensive trigger conditions with natural user phrases, and addresses a clearly distinct use case (AI agent session continuity). The description effectively communicates both what the skill does and precisely when Claude should select it.

DimensionReasoningScore

Specificity

Lists specific concrete actions: 'Creates comprehensive handoff documents', 'seamless AI agent session transfers', 'enabling fresh agents to continue'. Also describes specific scenarios like 'multiple file edits, complex debugging, architecture decisions'.

3 / 3

Completeness

Clearly answers both what ('Creates comprehensive handoff documents for seamless AI agent session transfers') and when with explicit 'Triggered when:' clause listing 6 specific trigger conditions plus proactive suggestion scenarios.

3 / 3

Trigger Term Quality

Excellent coverage of natural user phrases: 'save state', 'create handoff', 'I need to pause', 'context is getting full', 'load handoff', 'resume from', 'continue where we left off'. These are realistic phrases users would actually say.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche focused specifically on AI agent context/session management. The specific triggers like 'context window approaches capacity' and 'handoff' terminology clearly distinguish it from general documentation or file management skills.

3 / 3

Total

12

/

12

Passed

Implementation

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is an exemplary skill document that efficiently guides Claude through creating and resuming handoff documents. It excels in all dimensions: concise without sacrificing clarity, fully actionable with executable commands, clear multi-step workflows with validation gates, and well-organized progressive disclosure to reference materials.

DimensionReasoningScore

Conciseness

The content is lean and efficient, assuming Claude's competence. No unnecessary explanations of basic concepts, every section serves a clear purpose, and the document uses tables and lists effectively to minimize verbosity.

3 / 3

Actionability

Provides fully executable commands with concrete examples (e.g., `python scripts/create_handoff.py implementing-user-auth`), clear flag usage, and specific validation criteria. The workflows are copy-paste ready with real command patterns.

3 / 3

Workflow Clarity

Both CREATE and RESUME workflows have clear numbered steps with explicit validation checkpoints (Step 3: Validate, staleness checks before loading). Includes feedback loops ('Do not finalize a handoff with secrets detected or score below 70') and clear decision points for error recovery.

3 / 3

Progressive Disclosure

Excellent structure with clear overview, mode selection upfront, and well-signaled one-level-deep references to templates and checklists. The Resources section provides a clean navigation table for scripts and reference files.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
softaworks/agent-toolkit
Reviewed

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.