plan-canvas

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or when feedback like "move this, change that" is easier pointed at than typed.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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 a clearly sequenced, validated review loop, but carries some promotional padding and keeps all content inline rather than progressively disclosing the larger examples and diagram material into reference files.

Suggestions

Trim the lavish-axi attribution and the six-harness enumeration in How It Works; keep one trigger example and drop the rest to tighten conciseness.

Move the Examples and Diagrams (Mermaid) sections into reference files such as EXAMPLES.md and DIAGRAMS.md with one-line pointers from SKILL.md to improve progressive disclosure.

Collapse the redundant live-reload guidance stated in both How It Works and Rules into a single statement.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and it does not explain basic concepts, but padding exists: the lavish-axi attribution and the paragraph enumerating six harnesses could be trimmed; not level 3 where every token earns its place.	2 / 3
Actionability	Provides copy-paste-ready commands (open, await, await --reply, end) with real example JSON output; fully executable, not the pseudocode or incomplete level 2.	3 / 3
Workflow Clarity	Sequences the loop (open, await, reply, end) with explicit state handling and feedback checkpoints such as approve means the plan is CONFIRMED so stop polling, and status ended means stop polling and do not reopen; not level 2 where checkpoints are implicit.	3 / 3
Progressive Disclosure	Well-organized into clear sections and free of nested references, but at about 145 lines everything is inline with no file-level split and no bundle files; the Examples and Diagrams sections could be hoisted out. Not level 3 which expects appropriately split, well-signaled one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 specific, uses natural trigger phrasing, explicitly covers both what and when, and occupies a distinct niche. Voice is third-person imperative, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions -- open plans and HTML artifacts, annotate elements, chat, approve or request changes -- matching the anchor for several specific concrete actions; not the level below which only names a domain and some actions.	3 / 3
Completeness	Explicitly answers both what (open/annotate/chat/approve-or-request-changes) and when, with an explicit Use-when trigger clause; not level 2 where when is only implied.	3 / 3
Trigger Term Quality	Includes natural phrasing users would say such as presenting a plan for review and the verbatim move-this-change-that, giving good coverage of how a user would request this; not level 2 which misses common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche of local browser-canvas review of plan and HTML artifacts with element-pointed feedback, with distinct triggers unlikely to fire for unrelated skills; not level 2 which could overlap with similar skills.	3 / 3
	Total	12 / 12 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: affaan-m/ECC
Commit: 754b8dd

Reviewed: 3 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.