CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

handoff

Compact the current conversation into a handoff document for another agent to pick up.

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary lean instruction skill: every token adds specific, non-inferable guidance and there is no padding. The only improvement opportunity is actionability — providing a skeleton or example of the handoff document's structure would make the output fully specified rather than leaving its organization to inference.

DimensionReasoningScore

Conciseness

Every sentence carries non-obvious, workflow- or machine-specific knowledge (exact save path pattern, the tmpfs wipe-on-reboot warning, the no-duplicate-artifacts rule) with zero padding or explanation of concepts Claude already knows. This matches the anchor-5 example of lean, token-efficient instruction; even the redaction examples scope the rule in a few tokens rather than over-explain.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: exact file path template `.claude/handoffs/YYYY-MM-DD-<topic>.md`, a required named section, a reference-by-path rule, and arg-handling semantics. The minor gap keeping it from anchor 5 is the absence of any template or example of the handoff document's structure beyond the one named section.

4 / 5

Workflow Clarity

This is a simple single-task skill and the single action is unambiguous: what to write, where to save it, what to include, what to avoid, and how arguments are interpreted. It is not a destructive or batch operation, so the validation cap does not apply; per the simple-skill exception, an unambiguous single action scores 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (none exist in the bundle), and is organized as discrete single-purpose instructions with nothing that belongs in a separate file. Per the simple-skill scoring note, this warrants 5; the content is easy to navigate at this size without headers or split files.

5 / 5

Total

19

/

20

Passed

Description

66%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.

The description is concise, specific, and states a clear single-purpose capability in appropriate third-person/imperative voice. Its main weakness is the absence of any 'when to use' trigger clause, which both caps completeness and limits trigger-term coverage. Adding an explicit "Use when..." clause with natural phrases (handoff, compact, continue in a fresh session) would resolve the lowest-scoring dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to hand off, compact, or summarize the session for another agent or a fresh session."

Include natural synonym phrases users would say ("handoff", "compact the conversation", "continue in a new session") to broaden trigger-term coverage.

Optionally mention the output artifact (a markdown handoff document) to sharpen distinctiveness against generic summarization skills.

DimensionReasoningScore

Specificity

"Compact the current conversation into a handoff document" states one concrete action that fully covers this single-purpose skill. It falls between anchor 3 (1-2 actions, not comprehensive) and anchor 5 (multiple actions): there are no coverage gaps, but only one action is listed.

4 / 5

Completeness

The 'what' is clear (compact the conversation into a handoff document), but there is no "Use when..." clause or equivalent trigger guidance — "for another agent to pick up" states purpose, not invocation timing. Per the guideline, a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural trigger terms are present ("compact", "handoff document", "another agent"), but common variations users might say are missing ("summarize the conversation", "session", "hand off"), matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves a distinct niche (conversation compaction into a handoff for another agent) with only minor overlap risk against a generic session-summarization skill. It lacks the explicit trigger phrases that would distinguish it further, so it does not reach anchor 5.

4 / 5

Total

15

/

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

tonykay/transcriber

Path

.agents/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.