make-plan

Create a plan based on document research through an interactive, iterative process.

Quality

52%

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 ./.claude/skills/make-plan/SKILL.md

Quality

Content

67%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 concise and includes a useful verification feedback loop with a concrete output path, but its plan structure is underspecified and the workflow is presented as loose bullets rather than a tight numbered sequence. Specifying the plan format and tightening the step order would raise actionability and workflow clarity.

Suggestions

Specify the expected plan file structure (e.g. required headings or a template) so output is reproducible rather than implied by '.md file style'.

Reorder the 'You must' bullets into a numbered sequence with explicit checkpoints (research -> draft -> verify facts -> confirm with user -> finalize) to strengthen workflow clarity.

Tighten the opening paragraph by trimming evaluative filler like 'skeptical, thorough, and work collaboratively... high-quality technical specifications' to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is short and mostly efficient with a concrete output path, though phrases like 'skeptical, thorough, and work collaboratively... high-quality technical specifications' are mild over-explanation that keeps it just below the lean/efficient anchor.	4 / 5
Actionability	It provides a concrete output location ('.claude/plans/{plan_name_folder}') and actionable directives, but the actual plan structure and format remain unspecified, leaving guidance incomplete rather than fully executable.	3 / 5
Workflow Clarity	There is a clear sequence with an explicit validation checkpoint ('Only proceed once you've verified the facts yourself') and a verify-before-trust feedback loop, but steps are loose bullets rather than a numbered sequence with error-recovery detail, so it does not reach 5.	4 / 5
Progressive Disclosure	As a short single-file skill it is reasonably organized with a heading and grouped 'You must' bullets and needs no external references, but it lacks multiple clearly-signaled sections, keeping it just below the well-organized 5 anchor.	4 / 5
	Total	15 / 20 Passed

Description

37%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 states a clear purpose but is generic in its actions, lacks natural trigger terms, and omits any 'Use when' guidance, capping completeness and distinctiveness at the midpoint. Adding concrete capabilities and an explicit trigger clause would substantially improve it.

Suggestions

Add an explicit 'Use when...' trigger clause naming situations users would describe, e.g. 'Use when turning research findings into an implementation plan'.

Replace the generic 'create a plan' with concrete actions such as 'define a to-do list, verify facts by spawning research tasks, and write a plan to .claude/plans/'.

Include natural synonyms a user might say (e.g. 'implementation plan', 'technical spec', 'planning') to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The phrase 'Create a plan based on document research through an interactive, iterative process' names the domain (planning from research) but offers only one generic action ('create a plan') with the method described abstractly, sitting below the anchor that requires 1-2 concrete actions.	2 / 5
Completeness	It clearly states what the skill does ('create a plan based on document research') but provides no 'when' guidance, so per the missing-trigger cap it cannot exceed 3; it is not a 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	Only generic keywords like 'plan' and 'research' appear with no 'Use when...' clause or natural trigger phrases a user would actually say, matching the 'one or two generic keywords' anchor rather than the relevant-keyword anchor above.	2 / 5
Distinctiveness Conflict Risk	'Planning from document research' is a somewhat specific niche but 'make-plan' overlaps broadly with general planning skills, fitting the 'somewhat specific but could still overlap' anchor; it lacks the distinct triggers needed for a 4.	3 / 5
	Total	10 / 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: pymc-labs/pymc-marketing
Path: .claude/skills/make-plan/SKILL.md
Commit: 66d575d

Reviewed: 4 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.