Name: agent-code-goal-planner
Rating: 58.599999999999994 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-code-goal-planner

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

2.28x

Quality

39%

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

The canonical home for this skill is agent-code-goal-planner in ruvnet/claude-flow

Quality

Content

50%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.

The body is rich with concrete SPARC/claude-flow commands and templates, making it reasonably actionable, but it is padded by repeated restatements of the same five-phase model and lacks validation checkpoints and external file decomposition. Consolidating duplicates and adding explicit verification steps would materially improve it.

Suggestions

Eliminate the repeated restatements of the SPARC five-phase sequence; define the phases once and reference that section instead of re-deriving them in 'SPARC-GOAP Synergy', 'Goal Achievement Pattern', and 'Complete Feature Implementation'.

Add explicit validation/verification checkpoints (e.g. 'run tests; only proceed when green') to the deployment, migration, and TDD workflows to satisfy the feedback-loop requirement.

Move the full yaml planning templates, SPARC mode catalog, and MCP tool reference into separate reference files and link to them from a concise overview in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~440-line body restates the SPARC five-phase sequence at least four times (phases list, yaml plan, 'SPARC-GOAP Synergy', 'Goal Achievement Pattern', 'Complete Feature Implementation') and explains concepts Claude already knows, which is noticeably verbose with several padded sections.	2 / 5
Actionability	It provides concrete, mostly executable commands ('npx claude-flow sparc run spec-pseudocode "..."') and yaml/bash templates that are copy-pasteable, with only minor gaps such as the SPARCGoalPlanner class referencing undefined methods.	4 / 5
Workflow Clarity	The SPARC phases are clearly sequenced 1-5 with milestones, preconditions, and success criteria, but there are no explicit validate-then-proceed feedback loops for deployment/migration operations, which caps workflow clarity at 3 per the batch/destructive guidance.	3 / 5
Progressive Disclosure	There are no bundle files and all content — full yaml planning templates, the SPARC mode catalog, and MCP tool reference — is inlined into one monolithic SKILL.md; section headers provide some structure, but content that belongs in separate files is inline.	3 / 5
	Total	12 / 20 Passed

Description

28%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.

The frontmatter description is meta/invocation text rather than a capability statement: it tells how to invoke the skill but not what it concretely does or when to use it. It lacks trigger phrases, concrete actions, and an explicit 'Use when' clause.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Breaks complex coding objectives into testable milestones with success criteria and dependency maps'.

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say, such as 'plan a feature', 'break down a task', or 'milestones for a coding goal'.

Remove the invocation meta-language ('invoke with $agent-code-goal-planner') from the description; keep the description focused on capability and triggers.

Dimension	Reasoning	Score
Specificity	The effective frontmatter description 'Agent skill for code-goal-planner - invoke with $agent-code-goal-planner' names the domain but provides no concrete actions, only invocation meta-language; it does not reach the 1-2 concrete actions needed for a 3.	2 / 5
Completeness	It offers only a vague 'what' (an agent skill wrapper) and entirely lacks a 'Use when...' trigger clause, matching the anchor for a vague 'what' and no 'when'.	2 / 5
Trigger Term Quality	Keywords are limited to the skill name 'code-goal-planner' and 'invoke'; these are not natural phrases a user would say when needing planning help, missing common variations like 'plan a feature' or 'break down a task'.	2 / 5
Distinctiveness Conflict Risk	Tying the description to the specific named skill 'code-goal-planner' gives it some distinctiveness, but the surrounding meta-language is generic enough to overlap with other agent-skill wrappers.	3 / 5
	Total	9 / 20 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: fa13ee4

Reviewed: about 8 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.