CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plannotator-annotate

Open Plannotator's annotation UI for a markdown file, plain-text config file (.yaml, .json, .toml, .ini, .csv, .log, …), HTML file, URL, or folder and then respond to the returned annotations.

69

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary instruction-only skill body: lean, fully executable commands, and an outcome-branched workflow that anticipates dismissed sessions, approved-with-notes approvals, and argument-resolution failures with explicit recovery steps. The structure is appropriately scoped for a simple single-task skill with no external references needed.

DimensionReasoningScore

Conciseness

The body is lean and every sentence carries non-obvious operational detail (gate semantics, dismissed-decision handling, the approved-with-notes nuance, the re-run directive); nothing explains concepts Claude already knows and no padding is present.

5 / 5

Actionability

Provides two copy-paste-ready bash commands ('plannotator annotate <path-or-url>' and the '--gate --json' variant) with clearly delineated trigger conditions, and explicitly branches on concrete output shapes ('"decision": "dismissed"', '"decision": "approved"' with a '"feedback" field, the 'Approved with Notes' message, and unresolvable-arguments errors), covering the common cases.

5 / 5

Workflow Clarity

A clear 6-step sequence with explicit output-inspection checkpoints (steps 3-5 branch on the returned content), an explicit stop condition (step 4), and a feedback loop for error recovery (step 6 re-runs the command with a resolved path/URL); the operation is not destructive or batch, so no validation cap applies.

5 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, has no bundle files and no need for external references; the body is well organized (mode-delineated command blocks, a gate-semantics caveat, a numbered behavior list), which scores 5 under the simple-skill guideline.

5 / 5

Total

20

/

20

Passed

Description

70%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.

A specific, distinctive description that clearly states what the skill does and what it applies to, but it omits any 'Use when...' trigger guidance and misses natural trigger terms like review, feedback, and approve. The unmentioned --gate/approval capability also leaves a gap in what-coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to annotate, review, or give feedback on a document in Plannotator rather than inline in chat' — this would lift completeness from 3 and add natural trigger terms.

Mention the gate/approval capability (e.g. 'run in gate mode when the user asks to review, approve, accept, or gate a generated plan') to close the coverage gap and capture the 'review/approve' trigger vocabulary users actually say.

Consider adding a synonym like 'markup' or 'comment' alongside 'annotation' to broaden natural-term coverage.

DimensionReasoningScore

Specificity

Names two concrete actions ("Open Plannotator's annotation UI", "respond to the returned annotations") with an exhaustive enumeration of target types (".yaml, .json, .toml, .ini, .csv, .log", HTML, URL, folder), which is noticeably more specific than the anchor-3 example; held below 5 because the gate/approval capability is unmentioned, a coverage gap.

4 / 5

Completeness

The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the 'what' is fully concrete rather than vague; not 4 because the 'when' is entirely missing, not merely implicit.

3 / 5

Trigger Term Quality

Includes good natural keywords ("annotation", "markdown file", "config file", "HTML", "URL", "folder") plus concrete file extensions, matching 'good keyword coverage; a few natural terms missing'; not 5 because common synonyms users would say such as 'review', 'feedback', 'approve', or 'comment' are absent.

4 / 5

Distinctiveness Conflict Risk

Names a distinct niche tool with concrete trigger targets (specific file formats, HTML, URLs, folders), giving a clear niche with minimal conflict risk against other skills; no generic language that would overlap with document-review or file-processing skills.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

backnotprop/plannotator

Path

apps/skills/core/plannotator-annotate/SKILL.md

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.