plan-generator

Automatically generates a Markdown final-exam review plan or lab experiment schedule when you provide a date range, tasks/items, and available daily hours (via interactive prompts or a one-time JSON input).

Quality

67%

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 ./scientific-skills/Other/plan-generator/SKILL.md

Quality

Content

62%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 skill is highly actionable with verified executable commands and complete JSON examples, and it is well-structured with real one-level-deep script references. Its main weakness is verbosity: duplicated shortcuts and generic policy/safety sections pad the body with content Claude already knows.

Suggestions

Collapse the duplicate 'Validation Shortcut' and 'Quick Validation' --help blocks into one and remove the redundant 'Deterministic Output Rules'/'Completion Checklist' sections that restate general principles.

Fix the output-name discrepancy: the script writes plan_{type}.md (e.g. plan_review.md) and prints 'Plan saved to ...', but the body's Output Contract and Expected output format claim plan_generator_result.md and 'Result file: ...' — align these with the actual script behavior.

Merge the field descriptions in 'Example Usage' and 'Implementation Details' into a single schema section to avoid restating the same item fields twice.

Dimension	Reasoning	Score
Conciseness	The ~210-line body is noticeably verbose: it repeats the --help shortcut twice, restates input fields across 'Example Usage' and 'Implementation Details', and includes generic policy sections ('Validation and Safety Rules', 'Deterministic Output Rules', 'Completion Checklist') that restate principles Claude already knows rather than skill-specific facts.	2 / 5
Actionability	Fully executable guidance: real commands ('python scripts/plan_generator.py --json input.json'), complete copy-paste JSON examples for both plan types, and a verified script path covering the common cases.	5 / 5
Workflow Clarity	A clear sequenced 'Recommended Workflow' with an implicit validation step and a 'Failure Handling' section give good checkpoints; it stops just short of an explicit validate-fix-retry loop tied to the script's own validation, and the batch operation cap is borderline but the documented failure handling lifts it above 3.	4 / 5
Progressive Disclosure	Good section structure with well-signaled one-level-deep references to the real script bundle (scripts/plan_generator.py, scripts/validate_skill.py); no nested references and content is appropriately split, though some inline policy text could itself be trimmed rather than expanded.	4 / 5
	Total	15 / 20 Passed

Description

72%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.

A concise, third-person description that states a clear niche and concrete inputs, answering both what it does and when to use it. It is held back only by limited natural-synonym trigger terms and a slightly input-oriented rather than situation-oriented 'when' clause.

Suggestions

Add a situation-oriented trigger phrase such as 'Use when you need a study schedule or exam revision plan across a date range' to strengthen the 'when' clause.

Include a few natural synonyms users would say ('study schedule', 'exam timetable', 'revision planner') to broaden trigger coverage.

Optionally mention dependency and resource handling, since those are advertised in the body but absent from the description.

Dimension	Reasoning	Score
Specificity	Names the domain (review plan / lab schedule) and several concrete actions ('generates a Markdown...plan or...schedule', 'date range, tasks/items, and available daily hours', 'interactive prompts or...JSON input'); minor coverage gaps (no mention of dependencies/resource handling that the body advertises).	4 / 5
Completeness	Clearly answers 'what' (generates a Markdown review plan or lab schedule) and gives an explicit 'when' ('when you provide a date range, tasks/items, and available daily hours'); the 'when' is concrete but framed as inputs rather than a user-situation trigger phrase.	4 / 5
Trigger Term Quality	Includes relevant terms ('final-exam review plan', 'lab experiment schedule', 'Markdown', 'date range', 'daily hours') but lacks common synonyms users would naturally say (e.g. 'study schedule', 'exam timetable', 'revision planner') and any file-extension terms.	3 / 5
Distinctiveness Conflict Risk	Narrow niche (final-exam review plans and lab experiment scheduling) with distinct trigger conditions; minimal overlap risk with other generic skills.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/plan-generator/SKILL.md
Commit: 63c61d3

Reviewed: 9 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.