Name: handoff
Rating: 68 (1 reviews)
Author: alirezarezvani

handoff

Compact the current conversation into a handoff document for another agent to pick up. Save to a user-configured location (OS temp, home folder, or per-project .handoff/), redact secrets before write, suggest skills for the next session, and auto-load the latest handoff on the next SessionStart. First-run setup asks where to save so the project folder never gets cluttered. Use when the user says 'hand this off', 'handoff doc', 'summarize this for a new session', 'compact this conversation', 'I'm ending this session', 'pick this up later', or any variation signaling intent to pass work to a fresh agent. Also trigger on implicit signals: the user announcing they're switching machines, ending the day mid-task, or context is growing long without a natural stopping point.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is handoff in alirezarezvani/claude-skills

Quality

Content

67%Weight 40%Scale 1-5

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

A well-organized, mostly actionable body with real validation hooks, undermined by a broken bundle: all referenced reference files, scripts, and the example asset are missing, so the progressive-disclosure contract the overview promises cannot be fulfilled.

Suggestions

Ship the referenced bundle files — references/configuration.md, references/handoff_structure.md, references/handoff_prompt.md, references/deduplication_discipline.md, references/redaction_checklist.md, assets/example_handoff.md, and the seven scripts/*.py (setup.py, handoff_template_generator.py, redaction_linter.py, handoff_self_check.py, skill_recommender.py, cleanup.py, config_loader.py) — currently the bundle contains only SKILL.md and every link is a dead end.

Add one explicit numbered workflow section (walk checklist → generate scaffold → fill from conversation → run handoff_self_check.py → run redaction_linter.py → save; on linter failure, fix and re-run) so the validation feedback loop is visible in a single place rather than distributed across sections.

Give the concrete command-line invocations for the main generate, self-check, and linter steps (not just the --refresh variant) so the full pipeline is copy-paste runnable from the body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and tight sections, but carries minor personality/rationale padding ('Matt's no-duplication discipline made concrete', 'Matt-voice persona') and slight redundancy between the intro save-location line and the Output Path section.	4 / 5
Actionability	Provides concrete commands (`mktemp -t handoff-XXXXXX.md`, the `--refresh` invocation) and a tools table with flags, but the main generate, self-check, and linter invocations are described narratively rather than as copy-paste command lines.	4 / 5
Workflow Clarity	A clear sequence is narrated in Example 1 and validation checkpoints exist (handoff_self_check 'Run before the linter', redaction_linter blocks save in strict mode), but no single numbered workflow section ties the steps and the linter fix→retry feedback loop together.	4 / 5
Progressive Disclosure	SKILL.md is well-structured as an overview with clearly signaled one-level references, but the actual bundle contains only SKILL.md — none of the five referenced references/.md, the seven scripts/.py, nor assets/example_handoff.md exist, so every 'See [references/…]' link is a dead end and navigation is impossible.	2 / 5
	Total	14 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

An excellent description: concrete multi-action capability statement paired with explicit natural-language triggers and implicit-signal guidance, all in a distinct niche. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Compact the current conversation into a handoff document', 'redact secrets before write', 'suggest skills for the next session', 'auto-load the latest handoff on the next SessionStart' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both 'what' (compact→handoff doc, save to configured location, redact, suggest skills, auto-load) and 'when' via a 'Use when the user says…' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers including 'hand this off', 'handoff doc', 'summarize this for a new session', 'compact this conversation', 'I'm ending this session', 'pick this off later' plus implicit signals and a catch-all 'any variation signaling intent to pass work to a fresh agent'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (handoff docs for a fresh agent pickup) with handoff-specific triggers and implicit end-of-session signals, giving minimal overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 5 missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	13 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/handoff/SKILL.md
Commit: 19392f7

Reviewed: ~3 hours ago

Table of Contents

Discovery Implementation Validation

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.