plan-writing

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.

Quality

58%

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-writing/SKILL.md

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-organized and mostly lean, with good concrete examples, but it suffers from redundant sections, a placeholder plan template that contradicts its own no-template rule, and dangling references to script files that are not bundled. Tightening repetition and resolving the broken script references would materially improve it.

Suggestions

Collapse the overlapping "Task Breakdown Principles", "Planning Principles", and "Best Practices" sections into a single consolidated set to remove redundancy.

Either provide the referenced scripts (ux_audit.py, accessibility_checker.py, api_validator.py, security_scan.py, mobile_audit.py, schema_validator.py) in a scripts/ bundle or remove the script matrix, since the files do not exist.

Reconcile the "NO fixed templates" rule with the inline "Plan Structure" code block — either drop the fixed template or reframe it as an illustrative skeleton rather than a template to fill in.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the same guidance recurs across "Task Breakdown Principles", "Planning Principles", and "Best Practices (Quick Reference)" (small tasks, be specific, verify), adding redundant tokens that could be tightened.	2 / 3
Actionability	Concrete examples appear in the tables ("Run `npx create-next-app`", "Install next-auth, create `/api/auth/[...nextauth].ts`"), but the script table references files (ux_audit.py, api_validator.py, security_scan.py, etc.) that do not exist in the bundle, and the "Plan Structure" block is a placeholder template despite the "NO fixed templates" rule.	2 / 3
Workflow Clarity	A clear sequence is implied (goal → tasks → done-when) and verification is repeatedly emphasized ("Verification is always LAST", per-task "Verify:" slots), but the actual production workflow is a set of principles rather than an explicit numbered sequence with checkpoints.	2 / 3
Progressive Disclosure	The skill is organized into labeled sections, but it is a single ~150-line file with no bundle files present while the body references nonexistent scripts, so the references are broken and content that could be split out (the project-type script matrix) is inline.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 cleanly answers both what and when with an explicit trigger clause, but its triggers are somewhat generic and the stated capabilities are plan components rather than concrete actions, limiting distinctiveness. Strengthening trigger specificity would raise the score.

Suggestions

Replace the broad trigger "any multi-step work" with more distinctive, user-natural phrases such as "when breaking a feature into a task list" or "when planning a refactor across multiple files" to reduce conflict risk.

Reframe capabilities as concrete actions (e.g., "Breaks work into 5–10 verifiable tasks with dependencies and done-criteria") rather than naming plan elements.

Add common keyword variations users would actually say ("task list", "plan the work", "break this down") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("Structured task planning") and its components ("clear breakdowns, dependencies, and verification criteria"), but these are plan elements rather than concrete actions Claude performs, so it stops short of listing multiple specific concrete actions (score 3).	2 / 3
Completeness	It explicitly answers both what ("Structured task planning with clear breakdowns, dependencies, and verification criteria") and when ("Use when implementing features, refactoring, or any multi-step work") with an explicit trigger clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	"Use when implementing features, refactoring, or any multi-step work" offers some natural triggers, but coverage is thin and "any multi-step work" is overly generic, missing common variations a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	"Structured task planning" is a recognizable niche, but the trigger "any multi-step work" is broad enough to overlap with many coding skills, so it could still fire for the wrong skill rather than having a clearly distinct trigger set.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/plan-writing/SKILL.md
Commit: 04514f0

Reviewed: about 12 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.