create-plan

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

Quality

72%

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 ./SKILLs/create-plan/SKILL.md

Quality

Content

82%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.

A well-crafted, self-contained instruction skill: the workflow is unambiguous, the template is directly usable, and calibration guidance (good vs. bad checklist items) adds real value per token. The only meaningful gaps are the absence of one worked example of a completed plan and a final output-conformance check in the workflow.

Suggestions

Add one short filled-in example plan to make the template fully concrete and lift actionability to anchor 5.

Fold the "Checklist item guidance" section into step 3 (or trim it to just the good examples) to remove partial duplication and tighten progressive disclosure.

Add a final step instructing Claude to verify the output matches the template before responding (e.g. checklist length, no preface), closing the workflow's self-check gap.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: tight imperatives like "Ask at most 1–2 questions", "default 6–10 items", and "Verb-first: 'Add…', 'Refactor…', 'Verify…', 'Ship…'" with no padding and no explanation of concepts Claude already knows. It matches anchor 5 (every token earns its place) and sits clearly above anchor 4, which would require noticeable over-explanation to trim.	5 / 5
Actionability	A copy-paste-ready plan template with exact sections, concrete item counts (6–10 items, max 3 open questions), and concrete good/bad item examples ("Run npm test", vs. "handle backend") make the guidance highly executable. It falls short of anchor 5 only because there is no worked example of a filled-in plan; the template is structure without a completed instance.	4 / 5
Workflow Clarity	Four numbered steps are clearly sequenced (scan → ask only if blocking → build plan → output only the plan), with an explicit decision rule in step 2 and the read-only constraint stated up front. It misses anchor 5 because there is no final self-check that the output conforms to the template; the workflow is read-only and non-destructive, so the destructive-operation cap does not apply.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed: everything is appropriately inline under clear headers (Goal, Minimal workflow, Plan template, Checklist item guidance), and the template is short enough to belong in SKILL.md. It scores anchor 4 rather than 5 because the body exceeds the under-50-line simple-skill threshold and the Checklist item guidance section partially duplicates step 3's detail rather than being fully consolidated.	4 / 5
	Total	17 / 20 Passed

Description

62%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 correctly uses third person, states what and when, and includes an explicit trigger condition. Its main weakness is thin coverage: it names only one action and one trigger phrase, where stronger descriptions enumerate concrete outputs and multiple natural phrasings users would say.

Suggestions

Enumerate the concrete outputs in the what-clause, e.g. "Create a concise plan with scope, an ordered action-item checklist, and open questions" — this moves specificity toward anchor 4-5.

Add natural trigger variations users would say, such as "make a plan", "plan this out", "give me a roadmap", or "break this down into steps", to raise trigger term coverage.

Clarify the boundary against related skills (e.g. it is read-only and delivers a plan, not implementation) to further reduce overlap risk with general planning skills.

Dimension	Reasoning	Score
Specificity	"Create a concise plan" names the domain (planning for coding tasks) and one concrete action, but does not list the specific outputs the skill actually produces (scope section, action-item checklist, open questions). It matches anchor 3 (names domain and 1-2 concrete actions, not comprehensive) rather than 4, which requires several listed actions.	3 / 5
Completeness	Both what ("Create a concise plan") and when ("Use when a user explicitly asks for a plan related to a coding task") are explicitly present, so it clears anchor 4. It falls short of anchor 5 because the when-clause is a single trigger phrase rather than the multiple concrete trigger phrasings seen in the top anchor.	4 / 5
Trigger Term Quality	"asks for a plan" and "coding task" are natural trigger phrases, but common variations users say ("make a plan", "plan this out", "roadmap", "break this down") are missing. This sits at anchor 3 (some relevant keywords, missing common variations) rather than 4, which requires good coverage with only a few gaps.	3 / 5
Distinctiveness Conflict Risk	The qualifier "explicitly asks for a plan related to a coding task" carves a clear niche and reduces false triggers, leaving only minor overlap risk with general planning or roadmap-style skills. It is mostly distinct (anchor 4) but not a fully unambiguous niche like the anchor-5 example with a distinct file-type trigger.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/create-plan/SKILL.md
Commit: 791a352

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.