agent-coder

Agent skill for coder - invoke with $agent-coder

1.12x

Quality

—

Does it follow best practices?

Impact

79%

1.12x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

35%

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 contains useful code examples, but it is over-long and padded with generic best-practice advice Claude already knows, and its examples are often illustrative rather than copy-paste executable. Workflow steps lack validation/feedback checkpoints and there is no progressive disclosure to supporting files.

Suggestions

Cut generic principle explanations (SOLID/DRY/KISS/YAGNI, function-size and coverage rules of thumb) and keep only the non-obvious guidance and executable examples.

Make code examples complete and runnable — replace `// Implementation` stubs and the floating `constructor`, fix the `.$heavy-module` and `$authorization` typos, and either remove the non-executable `mcp__claude-flow__*` pseudo-syntax or show the real tool-call form.

Add a validation/feedback loop to the implementation process (e.g. run lint/tests, fix failures, re-run until green) so the workflow has explicit checkpoints before handoff.

Dimension	Reasoning	Score
Conciseness	The ~265-line body spends heavy space explaining concepts Claude already knows (SOLID/DRY/KISS/YAGNI, "keep functions <20 lines", ">80% coverage", "write self-documenting code", "Good code is written for humans to read"), which is the verbose/padded-with-unnecessary-context anchor.	1 / 3
Actionability	It provides real TypeScript snippets and an implementation process, but many examples are illustrative rather than executable (`// Implementation` stubs, an empty `UserService` class, a floating `constructor`, non-standard `mcp__claude-flow__memory_usage { ... }` pseudo-syntax, and typos like `import('.$heavy-module')` and `$authorization`), fitting the incomplete/pseudocode anchor.	2 / 3
Workflow Clarity	The "Implementation Process" lists sequenced phases (Understand, Design, TDD, Incremental) but has no validation checkpoints or fix/retry feedback loops — the TDD step shows test-then-implement with no re-validate-on-failure cycle, matching the steps-present-but-checkpoints-missing anchor.	2 / 3
Progressive Disclosure	It is a single monolithic file with no bundle files (references/scripts/assets absent) and no navigation to separate materials, yet it is organized into clear sections; content like MCP integration, design patterns, and code style is inline that could be split, matching the some-structure-but-could-be-split anchor.	2 / 3
	Total	7 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is essentially a label-plus-invocation-string rather than a capability statement: it conveys no concrete actions, no natural trigger terms, no use-when guidance, and no distinguishing niche. It fails every dimension and reads as plumbing metadata, not a skill description.

Suggestions

Rewrite as a third-person capability statement listing concrete actions, e.g. "Writes, refactors, and optimizes production code; designs APIs and adds tests."

Add an explicit trigger clause: "Use when the user asks to implement a feature, refactor code, optimize performance, or design an API."

Replace the invocation syntax "$agent-coder" with natural user-facing terms so it triggers on real requests instead of internal plumbing.

Dimension	Reasoning	Score
Specificity	The description "Agent skill for coder - invoke with $agent-coder" names only a vague domain ("coder") and an invocation token; it lists no concrete actions like writing, refactoring, or optimizing code, matching the vague/no-actions anchor.	1 / 3
Completeness	It gives an extremely weak "what" ("Agent skill for coder") and entirely omits any "when to use it" / "Use when..." trigger clause, so both what and when are missing or very weak.	1 / 3
Trigger Term Quality	The only keywords are the technical invocation syntax "$agent-coder" and the bare label "coder"; it omits natural terms a user would say such as "write code", "implement", "refactor", or "fix a bug", fitting the no-natural-keywords anchor.	1 / 3
Distinctiveness Conflict Risk	"Agent skill for coder" is generic and would overlap with any number of coding-related skills; nothing in the description carves out a clear niche that prevents it from triggering for the wrong skill.	1 / 3
	Total	4 / 12 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: ruvnet/ruflo
Commit: 1a88796

Reviewed: 3 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.