CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

handoff-coordinator

Clean transitions between agents and sessions. Use when preparing handoffs, serializing state, bridging context between agents, or coordinating multi-agent workflows.

Quality

77%

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 ./skills/handoff-coordinator/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 well-organized and actionable, with a Quick Start that matches the real script API and a clearly sequenced workflow. Its main defects are two dangling references to nonexistent bundle files and a token-costly ASCII diagram, plus verification steps that are named but not made executable.

Suggestions

Fix the dangling references: either add references/AGENT-TRANSITIONS.md and scripts/handoff_protocol.py to the bundle or remove them from the References and Scripts lists.

Replace the 25-line ASCII workflow diagram with a compact numbered sequence (source: save state → package; coordinator: validate → serialize → trigger; target: load → verify → continue) to reclaim tokens.

Make verification executable: show in the Quick Start how the target agent loads and verifies a package (e.g., coordinator.load_handoff(handoff_id)) and what to do if validation fails.

DimensionReasoningScore

Conciseness

The body is lean overall — no concept explanations Claude already knows, tight code examples, and compact tables. The single notable instance of over-explanation is the 25-line ASCII workflow diagram, which duplicates what a short numbered list would convey; that one padded block keeps it below 5.

4 / 5

Actionability

The Quick Start code is close to executable and matches the real API (HandoffCoordinator(project_dir), prepare_handoff(source_agent=, summary=), execute_handoff(package=, target_agent=)). Minor gaps: 'project_dir' is an undefined free variable, imports/setup are not shown, and no example covers the target side (loading/restoring a package).

4 / 5

Workflow Clarity

The workflow diagram lays out a clear three-role sequence (source → coordinator → target) with validation checkpoints named ('Validate state consistency', 'Verify state'). It is not 5 because verification steps are named but not elaborated into executable checks, and there is no explicit error-recovery loop; not 3 because checkpoints are present rather than missing or implicit.

4 / 5

Progressive Disclosure

Structure is good — an overview SKILL.md with clearly signaled one-level-deep References and Scripts sections — but 2 of the 6 referenced bundle files do not exist ('references/AGENT-TRANSITIONS.md' and 'scripts/handoff_protocol.py'), so following those pointers breaks navigation. Broken references are a more than minor organization gap, fitting the 'structure present but flawed' anchor.

3 / 5

Total

15

/

20

Passed

Description

75%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 solid description with an explicit and well-phrased 'Use when...' trigger clause covering several concrete actions. Its main weakness is the abstract capability statement, which states the goal ('clean transitions') without naming what the skill concretely does.

DimensionReasoningScore

Specificity

The trigger clause lists several concrete actions — 'preparing handoffs, serializing state, bridging context between agents, or coordinating multi-agent workflows' — but the capability statement 'Clean transitions between agents and sessions' is abstract, leaving minor gaps versus comprehensive coverage.

4 / 5

Completeness

Both what ('Clean transitions between agents and sessions') and an explicit 'Use when...' clause with four concrete triggers are present. It falls short of 5 because the what-clause is a single abstract phrase rather than concrete verb-object capabilities, and short of nothing below 4 since the when-guidance is fully explicit.

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'handoffs', 'agents', 'sessions', 'serializing state', 'bridging context', 'multi-agent workflows' are phrases users would naturally say. A few natural variations are missing (e.g., 'hand off work', 'context limit reached', 'session continuation').

4 / 5

Distinctiveness Conflict Risk

The multi-agent handoff/state-transfer niche is mostly distinct with clear triggers like 'serializing state' and 'bridging context between agents'. Minor overlap risk with closely related context-compaction or memory-management skills.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/Skrillz

Path

skills/handoff-coordinator/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.