CtrlK
BlogDocsLog inGet started
Tessl Logo

create-plan

Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.

64

Quality

77%

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 ./bundled/skills/create-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

90%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.

This is a tight, actionable instruction skill with a clear workflow and copy-paste template that respects the context budget. The main gap is the absence of an explicit validation/assumption-checking checkpoint within the plan-creation flow.

Suggestions

Add an explicit validation checkpoint between scanning and plan creation (e.g., 'Confirm assumptions against README/test config before drafting action items') to strengthen the feedback loop.

Consider splitting the plan template and checklist-item guidance into a short referenced file (e.g., references/plan-template.md) to push progressive disclosure toward a 5.

Tighten the 'Checklist item guidance' section by merging the Good/Avoid lists into fewer lines, since several points already overlap with the workflow steps above.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it gives a workflow, template, and guidance with no padded explanations of what planning or coding tasks are, so every token earns its place.

5 / 5

Actionability

It provides a concrete, copy-paste-ready plan template, verb-first item rules, specific file pointers (README.md, docs/, CONTRIBUTING.md), and named validation commands ('Run npm test'), giving fully executable guidance for the common cases.

5 / 5

Workflow Clarity

The four-step sequence (Scan → Ask → Create → Output) is clear and the read-only constraint acts as a safeguard, but there is no explicit validation checkpoint or feedback loop confirming assumptions before the plan is emitted, leaving minor validation gaps.

4 / 5

Progressive Disclosure

The content is self-contained with well-organized section headers and no nested references (no bundle files exist), but at roughly 75 lines it slightly exceeds the simple-skill threshold and lacks the one-level-deep reference signaling that would mark a 5.

4 / 5

Total

18

/

20

Passed

Description

65%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 cleanly answers both what and when using third person and a natural trigger phrase, but its action vocabulary is thin and trigger coverage lacks synonyms. It is solid and usable but not comprehensive.

Suggestions

Expand specificity by listing a couple of concrete plan elements the skill produces (e.g., scope, ordered action items, open questions) instead of just 'a concise plan'.

Broaden trigger coverage with natural synonyms users might say, such as 'breakdown', 'roadmap', 'step-by-step plan', or 'implementation plan'.

Consider adding a brief scoping note (e.g., 'for coding tasks') paired with the trigger to reduce overlap with general planning skills.

DimensionReasoningScore

Specificity

The description names the domain ('plan related to a coding task') but offers only a single generic action ('Create a concise plan'), matching the anchor that names the domain with minimal actions rather than listing multiple concrete actions.

2 / 5

Completeness

It states both what ('Create a concise plan') and when ('Use when a user explicitly asks for a plan related to a coding task'), but the 'when' clause is somewhat narrow and could be more explicit about additional trigger variations.

4 / 5

Trigger Term Quality

'asks for a plan' is a natural user utterance and 'coding task' is relevant, giving good keyword coverage; it falls just short of comprehensive because it omits synonyms like 'breakdown', 'roadmap', or 'estimate'.

4 / 5

Distinctiveness Conflict Risk

'plan related to a coding task' carves out a mostly distinct niche with only minor overlap risk against other planning or scaffolding skills, fitting the 'mostly distinct' anchor rather than the fully distinct 5.

4 / 5

Total

14

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-Skills
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.