agent-code-goal-planner

Agent skill for code-goal-planner - invoke with $agent-code-goal-planner

2.28x

Quality

21%

Does it follow best practices?

Impact

89%

2.28x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-code-goal-planner/SKILL.md

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 a verbose, repetitive monolith that mixes a few concrete claude-flow commands with substantial pseudocode and conceptual padding, and relies on no external references. It needs drastic trimming, real executable examples, and explicit validation checkpoints to move out of the lower band.

Suggestions

Collapse the five restatements of the SPARC phases into one concise sequence and cut generic explanations of metrics/concepts Claude already knows.

Replace illustrative pseudocode (the SPARCGoalPlanner class, MCP blocks) with minimal runnable commands, or explicitly label them as templates.

Add explicit validation checkpoints to the workflow (e.g., 'run sparc verify; only proceed when goals pass; otherwise revise the plan').

Dimension	Reasoning	Score
Conciseness	The ~440-line body is heavily padded: the SPARC phases are restated five times (phase list, YAML sparc_phases, mode list, 'How SPARC Enhances GOAP', and the SPARCGoalPlanner class), and it explains concepts Claude already knows (test coverage, cyclomatic complexity, CI/CD metrics), matching the 'verbose; explains concepts Claude knows' anchor.	1 / 3
Actionability	It includes concrete executable commands (e.g., 'npx claude-flow sparc run spec-pseudocode "..."'), but much of the guidance is illustrative rather than runnable — the SPARCGoalPlanner class calls undefined methods (executeSPARC, aStarSearch) and the mcp__claude-flow blocks are not valid executable syntax — so it is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The SPARC phases and the numbered 'Complete Feature Implementation' example provide a sequence, and each phase lists success_criteria, but there is no explicit validate-then-proceed gating or fix-and-retry feedback loop, so checkpoints are only implicit.	2 / 3
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ are absent) and no external file references; everything is inline in one 440-line file that is organized into sections but holds detailed YAML plans, mode references, and metrics that would be better split out, fitting 'content that should be separate is inline'.	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 actual frontmatter description is a non-functional placeholder that conveys no capability or trigger guidance; the substantive description is stranded in the body inside a stray second '---' block, which is itself a structural defect. Triggering and discovery will fail on the frontmatter alone.

Suggestions

Replace the placeholder frontmatter description with the substantive one currently buried in the body (e.g., 'Creates code-centric GOAP plans... Use when breaking down complex coding tasks into testable milestones...').

Add an explicit 'Use when...' clause naming natural user triggers such as 'plan a feature', 'break down a coding task', or 'milestones with success criteria'.

Remove the duplicate second '---' block from the body so the real description lives only in the frontmatter.

Dimension	Reasoning	Score
Specificity	The frontmatter description is only "Agent skill for code-goal-planner - invoke with $agent-code-goal-planner", which names no concrete actions or capabilities — it states only that an agent exists and how to invoke it, matching the 'vague or no actions' anchor.	1 / 3
Completeness	It answers neither 'what does this do' (no capability described beyond 'agent skill') nor 'when should Claude use it' (no 'Use when...' trigger), so both what and when are missing.	1 / 3
Trigger Term Quality	The only keyword is the coined technical term "code-goal-planner" / "$agent-code-goal-planner", which a user would not naturally say; there are no natural trigger terms like 'plan', 'milestones', or 'break down tasks'.	1 / 3
Distinctiveness Conflict Risk	The coined name "code-goal-planner" gives it a narrow niche unlikely to collide with other skills, but the generic template phrasing ('Agent skill for X - invoke with $X') provides no behavioral signal to distinguish it, so it only partially clears the bar.	2 / 3
	Total	5 / 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
Path: .agents/skills/agent-code-goal-planner/SKILL.md
Commit: 26c35b5

Reviewed: about 6 hours 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.