async-state-safety

This skill should be used when the user asks to change "worker lifecycle", "cancellation", "retrigger behavior", "state machine", "delivery receipts", "timeouts", or "race conditions". Enforces explicit async/state invariants and targeted race-safe verification.

Quality

84%

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

Quality

Content

78%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 tight, well-sequenced checklist skill with excellent token efficiency and organization. Its main gap is actionability: directives name what to do but give no runnable commands, test examples, or concrete templates for guards or transition matrices.

Suggestions

Add one concrete example per key directive — e.g., a sample terminal-state/transition-matrix table, a guard code snippet, and an example negative-path or idempotency test — so 'Add at least one negative-path test' becomes executable.

Make the verification steps concrete: name the actual commands or test-selection patterns for 'targeted tests' and specify what 'broad gate checks' means in this project.

Add a brief feedback loop after verification ('if a race check fails, fix the guard and re-run the targeted test before proceeding') to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is a lean checklist with zero padding and no explanation of concepts Claude already knows; every line is a directive ('Keep terminal transitions idempotent', 'Document why each race path converges safely'), matching the lean-and-efficient anchor.	5 / 5
Actionability	The checklists give specific, non-generic directives but stop short of executable detail — 'Run targeted tests for each touched race path', 'Run broad gate checks', and 'Add or update transition guards' include no commands, test invocations, or example guard/matrix patterns. This fits 'some concrete guidance but incomplete' rather than 2, since the guidance is specific in intent.	3 / 5
Workflow Clarity	The sections form a clear phase sequence (define invariants before coding -> analyze race windows -> implement -> verify -> hand off) with a pass-gate checkpoint ('Run broad gate checks after targeted checks pass'), but there is no explicit fix-and-retry feedback loop, fitting the 'most checkpoints present' anchor.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, and organized into clean labeled sections with no inlined material that belongs in a separate file and no bundle files to reference, so the simple-skill exception applies and the structure earns the top anchor.	5 / 5
	Total	17 / 20 Passed

Description

82%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, well-scoped 'use when' clause and distinctive natural trigger terms. Its only weakness is that the capability statement is terse and abstract rather than enumerating concrete actions.

Suggestions

Expand the capability statement into 2-3 concrete actions (e.g., 'Defines terminal states and transition guards, verifies idempotency and cancellation/timeout races with targeted tests') instead of the abstract 'enforces invariants and race-safe verification'.

Add common natural trigger variations users might say, such as 'retry', 'idempotency', or 'duplicate events'.

Dimension	Reasoning	Score
Specificity	The description names the domain (async/state) and two actions ('Enforces explicit async/state invariants and targeted race-safe verification'), but the 'what' is compact and abstract rather than a comprehensive list of concrete actions, matching the 1-2-concrete-actions anchor.	3 / 5
Completeness	It explicitly answers 'when' with a concrete trigger clause ('This skill should be used when the user asks to change...') and states 'what' ('Enforces explicit async/state invariants and targeted race-safe verification'), matching the both-what-and-when anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('worker lifecycle', 'cancellation', 'retrigger behavior', 'state machine', 'delivery receipts', 'timeouts', 'race conditions') that users would plausibly say, but a few natural variations like 'retry', 'idempotency', or 'backpressure' are missing, so it fits the 4 anchor rather than 5.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (race-regression prevention in async/stateful code) with distinct triggers like 'retrigger behavior', 'delivery receipts', and 'race conditions', giving minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: spacedriveapp/spacebot
Path: .agents/skills/async-state-safety/SKILL.md
Commit: 5c2ee47

Reviewed: 9 days 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.