plannotator

Interactive plan and diff review for AI coding agents. Visual browser UI for annotating agent plans — approve or request changes with structured feedback. Supports code review, image annotation, and auto-save to Obsidian/Bear Notes.

1.33x

Quality

72%

Does it follow best practices?

Impact

100%

1.33x

Average score across 3 eval scenarios

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent-skills/plannotator/SKILL.md

Quality

Discovery

67%

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 excels at specificity and carves out a clear, distinctive niche for interactive AI agent plan review with specific integrations. However, it lacks an explicit 'Use when...' clause which limits Claude's ability to know exactly when to select this skill, and could benefit from more natural trigger terms users might actually say.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to review, approve, or provide feedback on AI agent plans or code changes.'

Include more natural trigger variations like 'review agent output', 'approve changes', 'annotate code', 'visual diff review' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'annotating agent plans', 'approve or request changes with structured feedback', 'code review', 'image annotation', 'auto-save to Obsidian/Bear Notes'. These are concrete, actionable capabilities.	3 / 3
Completeness	Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The when is only implied through the feature descriptions.	2 / 3
Trigger Term Quality	Contains some relevant keywords like 'plan', 'diff review', 'AI coding agents', 'code review', 'Obsidian', 'Bear Notes', but missing common variations users might say like 'review changes', 'approve plan', 'agent feedback', or 'visual diff'.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive niche combining 'AI coding agents', 'plan review', 'browser UI', and specific integrations (Obsidian/Bear Notes). Unlikely to conflict with generic code review or document skills.	3 / 3
	Total	10 / 12 Passed

Implementation

77%

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

This skill provides highly actionable, executable guidance for integrating plannotator with multiple AI coding tools. The workflow clarity is strong with explicit steps and validation checkpoints. However, the document is significantly longer than necessary—the Obsidian integration alone could be a separate reference file, and many 'What it does' explanations are redundant given the clear command examples.

Suggestions

Move the Obsidian Integration Setup section (Pattern 9) to a separate OBSIDIAN.md file and link to it from the main skill

Remove 'What it does' bullet lists where the bash commands are self-explanatory (e.g., Pattern 1 install flags)

Consolidate the troubleshooting sections into a single TROUBLESHOOTING.md reference file

Remove redundant explanations like 'Checks CLI and git repo state' when the script name (check-status.sh) already conveys this

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but overly verbose for its purpose. Many sections could be condensed (e.g., the Obsidian integration section is ~100 lines when 30 would suffice). Some explanations like 'What it does' bullets repeat information obvious from the commands.	2 / 3
Actionability	Excellent actionability with copy-paste ready bash commands, complete script paths, and specific CLI invocations. Every pattern includes executable examples with clear flags and options.	3 / 3
Workflow Clarity	Clear multi-step workflows with explicit sequencing (numbered steps in Recommended Workflow section). Includes validation via check-status.sh script and clear checkpoints like 'Restart Claude Code after running this'.	3 / 3
Progressive Disclosure	Good use of tables and sections for organization, but the document is monolithic at ~400 lines. The Obsidian Integration section and troubleshooting could be split into separate reference files. References section exists but inline content is excessive.	2 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (577 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: supercent-io/skills-template
Commit: c033769

Reviewed: 15 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.