tessl install https://github.com/softaworks/agent-toolkit --skill session-handoffgithub.com/softaworks/agent-toolkit
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.
Average Score
98%
Content
100%
Description
100%
Generated
Validations
Total score
13/16| Criteria | Score |
|---|---|
skill_md_line_count SKILL.md line count is 190 (<= 500) | |
frontmatter_valid YAML frontmatter is valid | |
name_field 'name' field is valid: 'session-handoff' | |
description_field 'description' field is valid (642 chars) | |
description_voice 'description' uses third person voice | |
description_trigger_hint Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | |
compatibility_field 'compatibility' field not present (optional) | |
allowed_tools_field 'allowed-tools' field not present (optional) | |
metadata_version 'metadata' field is not a dictionary | |
metadata_field 'metadata' field not present (optional) | |
license_field 'license' field is missing | |
frontmatter_unknown_keys No unknown frontmatter keys found | |
body_present SKILL.md body is present | |
body_examples Examples detected (code fence or 'Example' wording) | |
body_output_format Output/return/format terms detected | |
body_steps Step-by-step structure detected (ordered list) |
Content
Total score
12/12| Dimension | Score |
|---|---|
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 gets straight to actionable content. | 3/3 |
actionability Provides fully executable commands with concrete examples (e.g., `python scripts/create_handoff.py [task-slug]`), specific validation criteria, and clear checklists. Commands are copy-paste ready with real examples. | 3/3 |
workflow_clarity Both CREATE and RESUME workflows have clear numbered steps with explicit validation checkpoints (Step 3: Validate, staleness checks before resuming). Includes feedback loops ('Do not finalize a handoff with secrets detected or score below 70') and clear decision points. | 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 |
Overall Assessment
This is an exemplary skill document that demonstrates best practices across all dimensions. It provides clear mode selection, concrete executable commands, explicit validation steps with quality thresholds, and well-organized progressive disclosure to reference materials. The handoff chaining concept is explained concisely with a visual diagram.
Description
Total score
12/12| Dimension | Score |
|---|---|
specificity Lists multiple concrete actions: 'Creates comprehensive handoff documents', 'session transfers', 'save state', 'load handoff', 'resume from'. Also specifies concrete scenarios like 'multiple file edits, complex debugging, architecture decisions'. | 3/3 |
completeness Clearly answers WHAT (creates handoff documents for 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: 'handoff', 'memory', 'context save', 'save state', 'create handoff', 'I need to pause', 'context is getting full', 'load handoff', 'resume from', 'continue where we left off'. These are terms users would naturally say. | 3/3 |
distinctiveness_conflict_risk Highly distinctive niche focused specifically on AI agent context/session handoffs. The specific triggers like 'context window approaches capacity' and 'handoff documents' are unlikely to conflict with other skills. | 3/3 |
Overall Assessment
This is an excellent skill description that excels across all dimensions. It provides specific actions, comprehensive trigger terms that match natural user language, explicitly addresses both what and when, and occupies a clear niche that won't conflict with other skills. The description effectively solves the problem it addresses (context exhaustion) while being actionable for skill selection.