plan-harder

Use when user specfically says 'plan harder'.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

57%

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

The content is a clear, well-structured phased planning workflow with good examples and a usable template, but it leans on some boilerplate and leaves a few steps abstract rather than executable. It is a solid single-file skill whose main weakness is the absence of explicit validation checkpoints on the produced plan.

Suggestions

Add an explicit validation checkpoint in Phase 3, e.g. "Confirm the saved plan file exists at the generated path before proceeding to Phase 4."

Make Phase 5's subagent review concrete by specifying the tool/delegation call and what context to pass, instead of "Provide the plan file location to a subagent".

Trim the boilerplate Plan Template to the essential fields, or move the full template into a referenced file, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with well-organized phases, but the Plan Template block is a long boilerplate scaffold and some lines ("Save the file", "Address them proactively") add little beyond what Claude already knows, so it could be tightened rather than being fully lean.	2 / 3
Actionability	It gives concrete guidance via the Bad/Good task examples and a full plan template with file paths and acceptance criteria, but key steps like "Save the file" lack an executable command or path and Phase 5's subagent review is described abstractly without a concrete invocation, leaving it incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The phases are clearly sequenced 0–5 and include a feedback loop in Phase 4 (gotchas → revise) and Phase 5 (review → incorporate), but there are no explicit validation checkpoints for the plan output itself and no deterministic pass/fail gate, so sequence is present yet checkpoints are implicit.	2 / 3
Progressive Disclosure	For a sub-50-line-equivalent self-contained skill with no external bundle files (no references/, scripts/, or assets/ dirs exist), the body is well-organized into clearly headed sections with one inline template, which per the simple-skills scoring note earns a 3 for progressive disclosure.	3 / 3
	Total	9 / 12 Passed

Description

27%

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 a near-empty trigger clause that omits the skill's actual purpose — creating detailed, phased implementation plans — and even contains a typo ("specfically"). It only signals when to invoke the skill, not what it does, leaving Claude unable to assess relevance by capability.

Suggestions

State the concrete capability first, e.g. "Create detailed, phased implementation plans with sprints and atomic tasks for bugs, features, or tasks."

Keep the explicit trigger but combine it with the capability, e.g. "...Use when the user specifically asks to 'plan harder' or wants a detailed, phased implementation plan."

Fix the typo "specfically" → "specifically" and add common trigger variations like "make a plan", "break this into sprints", or "phased plan".

Dimension	Reasoning	Score
Specificity	The description states only "Use when user specfically says 'plan harder'" — it gives no concrete actions or capabilities whatsoever, just a trigger phrase, matching the vague/abstract anchor for score 1.	1 / 3
Completeness	It answers only the "when" via a trigger clause; the "what does this do" (create phased implementation plans) is entirely missing from the description, so it fails to answer both what AND when, capping it at the lowest anchor.	1 / 3
Trigger Term Quality	"plan harder" is a natural phrase a user might actually say, so there is one relevant keyword, but coverage is extremely thin with no common variations or related terms, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The literal phrase trigger "plan harder" is fairly distinctive and unlikely to fire for unrelated skills, but with no described capability it gives Claude nothing to distinguish the skill's purpose, so it sits between a clear niche and a generic description.	2 / 3
	Total	6 / 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: am-will/codex-skills
Commit: e343715

Reviewed: 14 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.