programming

MUST USE for ANY work on .py .pyi .rs .ts .tsx .mts .cts .go files. One philosophy: strict types, modern stacks (Pydantic v2 / serde+thiserror / Zod / gin+sqlc+pgx+slog), modern toolchains (uv+basedpyright+ruff / cargo+clippy+miri / Bun+Biome+tsc / gofumpt+golangci-lint v2+nilaway+go-race), parse-don't-validate, exhaustive match, typed errors, no any/unwrap/panic, 250 LOC ceiling, TDD, consumer-routed logging. Routes to references/{python,rust,typescript,rust-ub,go}/ + references/logging.md. Triggers: write/edit Python/Rust/TypeScript/Go code, new project, gin server, bubbletea TUI, CJK IME, connect-go RPC, sqlc pgx, branded ids, exhaustive match, unsafe Rust, miri, oversized file, refactor, TDD, e2e test, logging, log levels, structured logging, observability, arena, allocator, bumpalo, const fn, const generics, comptime, zero-alloc, bitfield, repr, scopeguard, errdefer, Zig-like, zerocopy, packed struct.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 well-structured index skill with strong workflow clarity and concrete executable guidance, backed by a real, well-organized reference bundle. Its main weakness is conciseness: substantial inline philosophy and tables that, for a self-described index, could be trimmed or referenced out.

Suggestions

Move the full TDD discipline (red/green/refactor order, test pyramid, Given/When/Then, mock priority, anti-patterns table) into a references/tdd.md file and keep only the axiom + a one-line pointer in the body, to tighten conciseness.

Relocate the large 'Modern ecosystem' and 'Modern toolchain' library tables into references/ (e.g. a shared stacks.md) and summarize the canonical-pick rule inline, reducing body length while preserving navigation.

Trim repeated rhetorical emphasis ('NON-NEGOTIABLE', 'NO EXCEPTIONS', 'NEVER') to one statement per rule; the redundancy adds tokens without adding guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but for a skill that declares itself 'an index' it inlines lengthy sections (the full TDD discipline, the anti-patterns table, the ecosystem and toolchain tables) that could be tightened or moved to references, and leans on heavy rhetorical emphasis ('NON-NEGOTIABLE', 'NO EXCEPTIONS').	3 / 5
Actionability	Provides concrete executable commands (the awk pure-LOC measure, per-language check-no-excuse-rules scripts, exact CI gate commands) and precise file-path jump tables; minor gaps because language code examples are deferred to references rather than shown inline.	4 / 5
Workflow Clarity	PHASE 0 language gate and the four-step MANDATORY POST-WRITE REVIEW LOOP are clearly sequenced with explicit validation (measure → interpret against a verdict table → 11-point self-review checklist) and feedback loops (fix-before-done; load refactor/remove-ai-slops skills when issues surface).	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references via per-language jump tables (README → on-demand files), and all referenced paths verified to exist; minor organization gap from the sizable inline philosophy/tables that could live in references.	4 / 5
	Total	16 / 20 Passed

Description

91%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 dense, highly specific description that clearly answers both what and when, with a comprehensive explicit trigger list and file extensions. Its only weakness is the generic skill name and broad file-extension triggers that invite minor overlap with other code-related skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete items (strict types, parse-don't-validate, exhaustive match, typed errors, 250 LOC ceiling, TDD, write/edit code, refactor) but the bulk is philosophy/constraints rather than discrete actions, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states what ('MUST USE for ANY work on .py .pyi .rs .ts ... files', the philosophy, and routing to references/) and when (the 'Triggers:' clause), answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit 'Triggers:' clause enumerates comprehensive natural terms plus file extensions (.py .pyi .rs .ts .tsx .mts .cts .go) and synonyms (logging/log levels/structured logging/observability, unsafe Rust/miri).	5 / 5
Distinctiveness Conflict Risk	Has a specific niche (strict-typed modern-stack programming across four named languages) with distinctive triggers (bubbletea TUI, CJK IME, connect-go, miri, bumpalo, zerocopy), but the generic name 'programming' plus broad file-extension triggers create minor overlap risk with other code skills.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 60 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: code-yeongyu/lazycodex
Path: plugins/omo/skills/programming/SKILL.md
Commit: 10f9558

Reviewed: 10 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.