CtrlK
BlogDocsLog inGet started
Tessl Logo

orca-handoff

Perform a full ownership handoff to another agent through Orca. Defines the handoff contract and task brief, then routes workspace and terminal mechanics to Orca's version-matched `orca-cli` guide. Use for handoff, hand off, handover, delegation, or giving work to another agent without supervision. Do not use when the user asks to monitor completion, wait for results, coordinate multiple workers, or manage ask/reply flows.

76

Quality

93%

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 efficient, well-structured instruction-only skill: it owns the durable ownership contract and task-brief requirements while correctly delegating version-volatile mechanics to the loaded orca-cli guide, with explicit validation checkpoints and failure handling. Its only deduction is that end-to-end executability depends on that external guide and an `ORCA` placeholder rather than commands that are copy-paste ready within the file.

DimensionReasoningScore

Conciseness

The body is lean and sectioned with no explanation of concepts Claude already knows; even single-sentence rules like "Model or effort selection does not make a handoff supervised." earn their place. Every token carries skill-specific contract or routing information, matching the lean-and-efficient anchor rather than the minor-trimming anchor of 4.

5 / 5

Actionability

Concrete commands are provided ("ORCA skills get orca-cli", "ORCA status --json", "ORCA open --json") and the task-brief contract names six required fields with "Include exact paths, commands, identifiers". However, the core handoff commands are deferred to the external version-matched guide and `ORCA` is a placeholder requiring substitution (explicitly justified flexibility), so guidance is mostly-but-not-fully executable — anchor 4, not 3 (far beyond hints/pseudocode) and not 5 (not copy-paste ready end-to-end).

4 / 5

Workflow Clarity

A clear sequence runs from the role-classification table through loading the guide and confirming the runtime, with an explicit checkpoint ("Any other status failure is blocking. Report it and stop.") and error-recovery paths ("If the handoff was not accepted, report the exact state and error returned by Orca"). This matches the explicit-validation-with-recovery anchor rather than the minor-gaps anchor of 4.

5 / 5

Progressive Disclosure

No bundle files exist, and the single SKILL.md is well-organized under clear headers while appropriately externalizing all version-specific mechanics one level deep to the runtime-loaded orca-cli guide ("Follow the loaded guide's Full Handoffs section"). Nothing that belongs in a separate file is inlined, matching the well-signaled one-level-deep structure of the top anchor rather than the minor-organization-gaps anchor of 4.

5 / 5

Total

19

/

20

Passed

Description

95%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: third-person, concrete about what it does, with comprehensive natural trigger synonyms and an explicit negative-trigger clause that sharply reduces conflict risk with orchestration skills. The only soft spot is that capability specificity is process-level rather than exhaustive, leaving a small gap to the top anchor.

DimensionReasoningScore

Specificity

Quotes several concrete actions — "Perform a full ownership handoff", "Defines the handoff contract and task brief", "routes workspace and terminal mechanics to Orca's version-matched orca-cli guide" — in third person, with only minor gaps in coverage. It lists multiple specific actions but stops short of the fully comprehensive anchor, so 4 rather than 5, and is well above the 1-2-action anchor.

4 / 5

Completeness

It explicitly answers what ("Perform a full ownership handoff... Defines the handoff contract and task brief, then routes workspace and terminal mechanics") and when ("Use for handoff, hand off, handover, delegation...") with concrete trigger phrases, plus negative triggers ("Do not use when the user asks to monitor completion..."). This clearly matches the top anchor; not 4 because the 'when' is fully explicit, not merely present.

5 / 5

Trigger Term Quality

"Use for handoff, hand off, handover, delegation, or giving work to another agent without supervision" covers natural synonym variants and a plain-language phrase users would actually say. No common variation is missing, matching the comprehensive-coverage anchor rather than the 'a few natural terms missing' anchor.

5 / 5

Distinctiveness Conflict Risk

The do-not-use clause ("monitor completion, wait for results, coordinate multiple workers, or manage ask/reply flows") explicitly carves the skill out from coordination/monitoring skills, giving it a clear niche with minimal conflict risk. It matches the distinct-triggers anchor, not the minor-overlap anchor of 4.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
choegyumin/agent-skills
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.