create-plan

Create a new plan file in .agents/plans/

Quality

57%

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 ./.opencode/skills/create-plan/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete, executable commands and a clear section structure, but it includes tangential architecture explanation, lacks validation steps in its workflow, and references a script that is not bundled.

Suggestions

Trim or relocate the "Architecture Considerations" section so the body stays focused on the plan-creation task.

Add a validation step (e.g., confirm the file was created and frontmatter is well-formed) to the workflow.

Bundle `scripts/create-plan.ts` under a `scripts/` directory or document its expected location so the reference resolves.

Dimension	Reasoning	Score
Conciseness	The usage commands are lean, but the "Architecture Considerations" section explains PDF API layers (COS objects, gradient examples) that are tangential to creating a plan file and could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (`bun scripts/create-plan.ts "<slug>" "content"`, heredoc, and pipe variants) with concrete examples.	3 / 3
Workflow Clarity	The task steps are numbered and sequenced (read ARCHITECTURE.md, determine slug, gather content, create file), but there are no validation checkpoints and the link between the task list and the script options is loose.	2 / 3
Progressive Disclosure	Sections are clearly organized, but no bundle files are present and the referenced `scripts/create-plan.ts` is not bundled, so navigation to supporting material is not verifiable.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 concrete and names a specific action and location, but it lacks any trigger/usage clause and only conveys a single action, leaving it at the mid-level across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to record a feature plan or roadmap in .agents/plans/."

Expand the action list to mention concrete capabilities like generating a unique ID, formatting the title, and dating the file.

Include natural keyword variations ("plan", "planning", "roadmap", "feature plan") to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	"Create a new plan file in .agents/plans/" names one concrete action and a specific location, but lists only a single action rather than multiple specific concrete actions.	2 / 3
Completeness	It clearly answers what the skill does (create a plan file) but omits any explicit "Use when..." trigger guidance, so completeness is capped at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	"plan file" is a relevant natural keyword, but coverage is thin with no common variations (e.g., "planning", "roadmap") and no trigger phrasing users would naturally say.	2 / 3
Distinctiveness Conflict Risk	The niche (plan files in a specific directory) is somewhat specific, but "plan" is broad enough that it could overlap with other planning-related skills.	2 / 3
	Total	8 / 12 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
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: LibPDF-js/core
Path: .opencode/skills/create-plan/SKILL.md
Commit: 36bf165

Reviewed: 2 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.