CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tinystruct-patterns

Expert guidance for developing with the tinystruct Java framework. Use when working on the tinystruct codebase or any project built on tinystruct — including generating the bin/dispatcher and bin/dispatcher.cmd launcher scripts when a project lacks them, creating Application classes, @Action-mapped routes, unit tests, ActionRegistry, HTTP/CLI dual-mode handling, the built-in HTTP server, the event system, JSON with Builder/Builders, database persistence with AbstractData, POJO generation, Server-Sent Events (SSE), file uploads, and outbound HTTP networking.

Quality

85%

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

73%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 highly actionable, well-sequenced guide: workflows carry explicit verification steps and error-recovery mapping, and the reference bundle is verified, clearly signaled, and one level deep. Its weaknesses are token efficiency — the core principle is repeated four times and version-pinned details are inlined rather than isolated — plus a couple of fragment-style examples that are not copy-paste ready.

Suggestions

State the dual-mode/Mode.DEFAULT principle once (in 'Core Principle') and trim its restatements in 'Primary Development Tool: bin/dispatcher', 'How It Works', and Best Practice #1, which repeat the same transport-neutral argument.

Move version-pinned deep dives out of SKILL.md into references/ — the 1.7.37 static-file symlink analysis, the FileHandler rotation internals, and the MCP overloaded-method schema-merging semantics — keeping only version-stable guidance in the overview.

Wrap the SSE example in a complete Application class and split the two @Action("greet") signatures into separate snippets so every code example is unambiguously copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient framework-specific content, but the dual-mode/Mode.DEFAULT principle is restated four times ("Core Principle", "Primary Development Tool", "How It Works", Best Practice #1), and version-pinned details ("In 1.7.37, the working-directory/ancestor check…", "starting with SDK version 1.7.0", the pinned v1.7.37 GitHub link) sit outside any 'old patterns'/'deprecated' section. This is more than the 'minor instances that could be trimmed' of the 4 anchor, so it fits the 3 anchor ('mostly efficient but includes some unnecessary explanation or could be tightened').

3 / 5

Actionability

Nearly all guidance is executable: complete classes (MyService, MyCustomTool, MyMCPServer, the login action, the upload action, DatabaseOperator) and copy-paste commands ("bin/dispatcher greet/James --import com.example.MyService", the concrete java -cp generation command). Minor gaps hold it at 4 rather than 5: the SSE example is loose fragments outside any class ("String sessionId = getContext().getId();" with no surrounding method), and the first example presents two conflicting @Action("greet") methods inside one class as if it were a compilable whole.

4 / 5

Workflow Clarity

The launcher-generation workflow is a numbered four-step sequence with an explicit validation checkpoint ("**3. Verify.** From the project root run `bin/dispatcher --version`… the `VERSION` inside the script equals the jar's version"), the default dev loop embeds verification ("run it immediately via `bin/dispatcher <action>` to confirm it behaves correctly in CLI mode"), and the Red Flags & Anti-patterns table supplies symptom→fix error recovery (e.g. ClassNotFoundException rows with exact causes and fixes) — matching the 5 anchor's explicit validation steps plus feedback loops.

5 / 5

Progressive Disclosure

All six referenced guides (references/architecture.md, routing.md, data-handling.md, database.md, system-usage.md, testing.md) exist as real files, are exactly one level deep with no nested file references, and are clearly signaled with one-line descriptions in the Technical Reference section. However, deep-dive content that belongs in references is inlined in SKILL.md — the FileHandler rotation internals ("`%g` in the pattern is the rotation number, so `count=5` produces…"), the 1.7.37 static-file symlink security analysis, and the MCP overloaded-method schema-merging semantics — so the split is good but not ideal, fitting the 4 anchor ('most content is appropriately placed; minor organization gaps').

4 / 5

Total

16

/

20

Passed

Description

92%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: it concretely enumerates the skill's capabilities, gives an explicit 'Use when…' trigger clause, and is anchored to a uniquely named framework so conflict risk is minimal. The only weakness is a handful of natural trigger terms (MCP, logging, static files) absent from an otherwise comprehensive keyword set.

DimensionReasoningScore

Specificity

Enumerates a dozen-plus concrete actions — "generating the bin/dispatcher and bin/dispatcher.cmd launcher scripts", "creating Application classes, @Action-mapped routes, unit tests", "database persistence with AbstractData, POJO generation", "Server-Sent Events (SSE), file uploads, and outbound HTTP networking" — comprehensive coverage of the framework's capabilities, matching the 5 anchor rather than 4 (no minor gaps in the action list).

5 / 5

Completeness

Explicitly answers both questions: what — "Expert guidance for developing with the tinystruct Java framework… including generating the bin/dispatcher… launcher scripts when a project lacks them" — and when — "Use when working on the tinystruct codebase or any project built on tinystruct" with concrete trigger phrasing, a clear match for the 5 anchor; not 4, since the 'when' clause is fully explicit rather than merely serviceable.

5 / 5

Trigger Term Quality

The distinctive natural keyword "tinystruct" recurs in user-natural phrasings ("tinystruct codebase", "any project built on tinystruct") alongside concrete component terms (bin/dispatcher, @Action, SSE, file uploads), but a few natural trigger terms for topics the body covers — "MCP", "logging", "static files" — are missing from the description, fitting the 4 anchor ("good keyword coverage; a few natural terms missing") better than the comprehensive-coverage 5 anchor.

4 / 5

Distinctiveness Conflict Risk

"tinystruct" names a specific niche Java framework and every trigger phrase is scoped to it ("the tinystruct codebase", "any project built on tinystruct"), giving a clear niche with distinct triggers and minimal conflict risk with other skills — the 5 anchor.

5 / 5

Total

19

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

affaan-m/ECC

Path

skills/tinystruct-patterns/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.