iii-state-reactions
Registers state-type triggers that automatically fire functions when key-value state is created, updated, or deleted within a scope. Use when building reactive side effects, change watchers, audit logs, cache invalidation, notification dispatchers, or any observer pattern where data changes should trigger downstream processing.
80
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/iii-state-reactions/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates what the skill does (registers state-type triggers for key-value state changes) and when to use it (with an explicit 'Use when' clause covering multiple concrete scenarios). The trigger terms are well-chosen, covering both technical patterns (observer pattern, cache invalidation) and practical use cases (audit logs, notification dispatchers), making it easy for Claude to match against user requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'registers state-type triggers', 'automatically fire functions when key-value state is created, updated, or deleted within a scope'. These are concrete, well-defined operations. | 3 / 3 |
Completeness | Clearly answers both 'what' (registers state-type triggers that fire functions on key-value state changes) and 'when' (explicit 'Use when' clause listing reactive side effects, change watchers, audit logs, cache invalidation, notification dispatchers, observer pattern scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'state triggers', 'change watchers', 'audit logs', 'cache invalidation', 'notification dispatchers', 'observer pattern', 'reactive side effects', 'key-value state'. Good coverage of both conceptual and practical terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche focused on state-change triggers and observer patterns for key-value state within scopes. The combination of 'state-type triggers', 'key-value state', and 'created/updated/deleted' events makes this clearly distinguishable from general event handling or other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is well-structured with clear architecture visualization, good use of tables, and appropriate cross-references to related skills. Its main weaknesses are the lack of any inline executable code (all deferred to missing reference files) and some redundancy in the boundary/usage sections. Adding a minimal inline example and validation guidance would significantly improve it.
Suggestions
Add at least one minimal inline code example showing a complete registerTrigger + registerFunction setup, so the skill is actionable without relying on external reference files.
Add validation/debugging guidance — e.g., how to verify a trigger is registered correctly, what happens when condition_function_id returns falsy, or how to troubleshoot reactions that don't fire.
Consolidate the 'When to Use', 'Boundaries', and 'Pattern Boundaries' sections into a single section to reduce redundancy and save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy — the 'When to Use' and 'Boundaries' sections at the bottom repeat information already conveyed in 'Pattern Boundaries', and some sections like 'Common Patterns' list items that could be more tightly integrated. The 'Comparable to' line and architecture diagram are good, but the overall structure has padding. | 2 / 3 |
Actionability | The skill provides concrete API patterns and parameter names (registerTrigger, payload fields, config options) but lacks any inline executable code examples. All working code is deferred to reference files which are not provided in the bundle, so a reader cannot copy-paste anything directly from the skill itself. | 2 / 3 |
Workflow Clarity | The architecture section provides a clear event flow sequence, and the 'Adapting This Pattern' section gives step-like guidance. However, there are no explicit validation checkpoints or error-handling/feedback loops for when triggers fail to fire or conditions don't match, which matters for reactive side-effect patterns. | 2 / 3 |
Progressive Disclosure | The skill references multiple external files (state-reactions.js/py/rs, iii-config.yaml) with clear one-level-deep links, which is good structure. However, since no bundle files are provided, these references are unverifiable. The inline content itself could benefit from at least a minimal code snippet rather than deferring all executable content to external files. | 2 / 3 |
Total | 8 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- iii-hq/iii
- Commit
d51a06d
- 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.