CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

handoff

Compact the current conversation into a handoff document for another agent to pick up. References existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) by path or URL instead of duplicating them. Use when user wants to hand off the conversation to a fresh agent or starts a new session that picks up prior work.

63

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./engineering/handoff/skills/handoff/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

The body is concise, actionable, and faithful to its no-duplication discipline, with a concrete mktemp workflow and a clear section template. Its main defect is navigation: most of the bundle's reference content is never linked from SKILL.md, so progressive disclosure breaks down at the entry point, and the workflow ordering (especially when to use the companion scripts) is implicit.

Suggestions

Link the three orphaned reference files from the body — e.g., under Sections, point each bullet (structure, dedup rule, skill matching) to its corresponding references/*.md so the ~480 lines of existing detail are discoverable from the entry point.

State when in the workflow to run the companion scripts (e.g., 'generate scaffold with scripts/handoff_template_generator.py, then pre-flight the draft with scripts/artifact_deduplicator.py') instead of deferring all sequencing to references/companion_tooling.md.

Remove the trailing Version/Derived footer and trim the provenance blockquote — both duplicate frontmatter metadata — and add a one-line example of an inlined artifact reference (e.g., 'See docs/adr-007.md for the caching decision') to make the no-duplication rule concrete.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no concept explanations, and instructions like "Do not duplicate content already captured in other artifacts... Reference them by path or URL instead" earn their tokens. Minor trimmable overhead remains: the provenance blockquote and the trailing "**Version:** 1.0.0 / **Derived:**" footer duplicate metadata already in the frontmatter, and version numbers outside a deprecated section are penalized, so it sits at anchor 4 rather than 5.

4 / 5

Actionability

Gives a copy-paste-ready command ("Save it to a path produced by `mktemp -t handoff-XXXXXX.md` (read the file before you write to it)") and a concrete five-section output structure. Minor gaps keep it from anchor 5: no example of what an artifact-reference line should look like and no example handoff snippet, though as an instruction-only skill the guidance is otherwise actionable.

4 / 5

Workflow Clarity

The write path is concrete with a built-in checkpoint (mktemp → read before writing), and the output structure is fully specified, so the core action is unambiguous. However, the steps are presented in scattered prose rather than a sequence, and the body never says when in the flow to invoke the companion tools (that sequencing lives only in references/companion_tooling.md), fitting anchor 4's 'clear sequence with most checkpoints present; minor gaps' better than the simple-skill 5.

4 / 5

Progressive Disclosure

The body itself is a well-organized, one-level-deep overview that clearly signals references/companion_tooling.md, but scored against the actual bundle, three of the four reference files (deduplication_discipline.md, handoff_structure.md, next_session_skill_matching.md — ~480 lines of content elaborating the very sections the body lists) are referenced nowhere in SKILL.md and are undiscoverable from the entry point. That is more than a minor organization gap, so anchor 3 fits better than anchor 4.

3 / 5

Total

15

/

20

Passed

Description

78%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.

A strong description with an explicit and concrete 'Use when' trigger clause and natural trigger phrasing. Its only weakness is specificity: it names two concrete actions but leaves out capabilities the skill actually performs (skill suggestion, tailoring to the next session's focus).

DimensionReasoningScore

Specificity

Names the domain and two concrete actions — "Compact the current conversation into a handoff document" and "References existing artifacts (PRDs, plans, ADRs, issues, commits, diffs) by path or URL instead of duplicating them" — but omits other capabilities the skill performs (suggesting skills for the next session, tailoring to the user's stated focus), so coverage is not comprehensive. Anchor 4 requires several specific actions; only two are listed, so it stays at 3 rather than 4.

3 / 5

Completeness

Explicitly answers both questions: the 'what' is "Compact the current conversation into a handoff document for another agent to pick up" and the 'when' is a concrete "Use when user wants to hand off the conversation to a fresh agent or starts a new session that picks up prior work" clause with specific trigger phrases. This matches anchor 5; it exceeds anchor 4, where the 'when' is present but could be more explicit.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say: "hand off the conversation", "a fresh agent", "starts a new session that picks up prior work", plus artifact names (PRDs, ADRs, commits, diffs). A few natural synonyms are missing (e.g., "continue where I left off", "transfer context"), which fits anchor 4 rather than 5's comprehensive synonym coverage, and it is clearly above anchor 3's 'some relevant keywords but missing common variations'.

4 / 5

Distinctiveness Conflict Risk

Session-continuity handoff is a fairly distinct niche with distinct triggers ("hand off", "new session that picks up prior work"), so it is mostly distinguishable from other skills. Minor overlap risk remains with generic conversation-summarization or compaction skills, keeping it at anchor 4 rather than 5's 'minimal conflict risk'.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

alirezarezvani/claude-skills

Path

engineering/handoff/skills/handoff/SKILL.md

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.