planner-feature

Create a plan for a feature, and the files required to continue working on it. Use when the user asks for research for a feature or a plan to run it.

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/plan-feature/SKILL.md

Quality

Content

32%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 well-structured as a self-contained overview with clear section titles, but it describes a hidden agent's behavior rather than giving executable guidance, and carries noticeable verbosity and no real workflow sequence.

Suggestions

Convert the descriptive "It should create..." statements into direct, imperative instructions ("Create README.md as the index...") with at least one concrete template or example per artifact.

Cut meta-commentary ("The hidden instructions emphasize", "The prompt also injects") and the rationale paragraphs for the writing standards to reduce padding.

Add a short sequenced workflow (explore repo -> draft context.md -> draft plan.md -> keep status.md current) with a validation checkpoint so the planning process is executable rather than described.

Dimension	Reasoning	Score
Conciseness	The body largely meta-describes another agent's behavior ("It acts as...", "The hidden instructions emphasize", "The prompt also injects") and explains rationale for its own standards, adding several padded sections that do not earn their tokens; it is noticeably verbose rather than mostly efficient.	2 / 5
Actionability	It names artifact categories and filenames to create but provides no concrete commands, templates, or executable steps, and is phrased as observation of a third-party agent ("It should usually create..."); this is high-level hints missing the specific steps to execute.	2 / 5
Workflow Clarity	There is no operation sequence; the body is organized by topic, and the only numbered list is a writing-quality checklist rather than a sequenced workflow, with no validation checkpoints, fitting a rough-structure-present-but-gaps-and-no-validation level.	2 / 5
Progressive Disclosure	With no bundle files present, the body is a self-contained overview broken into plainly titled sections ("What it is instructed to create", "Planning philosophy", "Writing standards") with good navigation and only minor organization gaps like the meta "If helpful" section.	4 / 5
	Total	10 / 20 Passed

Description

78%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 description clearly answers both what the skill does and when to use it, with reasonably natural trigger phrasing and a mostly distinct niche. It is slightly limited in specificity (only two concrete actions) and lacks synonym coverage in its trigger terms.

Suggestions

Add a third concrete action (e.g., "break a feature into milestones" or "identify the files to scaffold") to lift specificity toward the several-actions bar.

Broaden trigger terms with common synonyms such as "design", "spec", or "feature breakdown" to improve keyword coverage and reduce overlap with generic research skills.

Dimension	Reasoning	Score
Specificity	Names the feature-planning domain and two concrete actions ("Create a plan for a feature, and the files required to continue working on it"), matching the anchor for 1-2 concrete actions without comprehensive coverage; it does not reach the several-actions bar of 4.	3 / 5
Completeness	It explicitly states both what it does (create a plan and required files) and when to use it (research for a feature or a plan to run it), with concrete trigger phrases, matching the anchor that requires clear answers to both questions.	5 / 5
Trigger Term Quality	Natural trigger phrasing is present ("Use when the user asks for research for a feature or a plan to run it") covering several user-natural terms, but common synonyms like "design", "spec", or "break down" are missing, fitting good-but-not-comprehensive keyword coverage.	4 / 5
Distinctiveness Conflict Risk	The feature-planning niche is mostly distinct, but phrasing like "research for a feature" and "a plan to run it" leaves minor overlap with general research/planning skills; it does not present the unmistakable niche needed for a 5.	4 / 5
	Total	16 / 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: Agenta-AI/agenta
Path: .agents/skills/plan-feature/SKILL.md
Commit: e4008fa

Reviewed: 5 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.