CtrlK
BlogDocsLog inGet started
Tessl Logo

create-plan

Create a new plan file in .agents/plans/

50

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/create-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 actionable and well-structured with copy-paste-ready commands, but it lacks a post-creation validation step and carries some over-explanation in the architecture section. For a simple single-purpose skill it is solid, with minor tightening and a verification checkpoint needed to reach the top band.

Suggestions

Add an explicit validation step after creation, e.g., 'Verify the file exists at `.agents/plans/{id}-{slug}.md` and the frontmatter rendered correctly'.

Trim the Architecture Considerations section (or defer fully to the already-referenced `.agents/ARCHITECTURE.md`) to remove tangential explanation.

Replace placeholder slugs in the command examples with one fully worked end-to-end example to lift actionability to copy-paste-ready for a real case.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands and a clear task list, but the Architecture Considerations section and phrases like 'This is crucial' add explanation that could be trimmed.

3 / 5

Actionability

It provides three concrete, executable command forms (direct, heredoc, pipe) plus the output file format, with only minor gaps (placeholder slugs and an assumed `bun` runtime).

4 / 5

Workflow Clarity

The four-step sequence is clear, but there is no validation/verification checkpoint after file creation, which caps workflow clarity at 3 for a write operation.

3 / 5

Progressive Disclosure

The skill is self-contained with well-organized sections and clearly signaled external references; the duplicated architecture guidance is a minor organization gap keeping it from a 5.

4 / 5

Total

14

/

20

Passed

Description

50%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 is concrete and names a specific artifact path, but it is minimal — only one action and no "Use when" trigger guidance. It is clearly distinguishable via its path yet remains generic enough to risk overlap.

Suggestions

Add a 'Use when...' clause naming natural triggers (e.g., 'Use when the user wants to capture or create a new plan in .agents/plans/').

List a second concrete action (e.g., auto-generates a unique three-word ID and dated frontmatter) to lift specificity and trigger coverage.

Include a common synonym or variation (e.g., 'plan', 'new plan', 'planning task') to broaden natural trigger terms.

DimensionReasoningScore

Specificity

It names the domain (plan files) and one concrete action ("Create a new plan file") in a specific location (`.agents/plans/`), but coverage is a single action rather than several.

3 / 5

Completeness

It clearly states the "what" (create a plan file in `.agents/plans/`) but provides no "Use when..." trigger guidance, so per the rubric cap completeness stays at 3.

3 / 5

Trigger Term Quality

It includes relevant terms ("plan", "plan file", `.agents/plans/`) but lacks common synonyms or variations a user might naturally say beyond "plan".

3 / 5

Distinctiveness Conflict Risk

The `.agents/plans/` path gives it a specific niche, but the generic "create a plan" trigger could still overlap with broader planning skills.

3 / 5

Total

12

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
LibPDF-js/core
Reviewed

Table of Contents

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.