CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lessons

Compare a published piece against the draft it started from and propose new content lessons and allergy-list entries for the author to approve. Use by hand after publishing something that began as a machine draft, or when the author catches an AI-ism or a correction they never want to make again.

Quality

92%

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: terse, concrete, and unambiguous. The approval-gated workflow gives it a real feedback loop, the entry formats are fully specified, and edge cases (duplicates, zero proposals) are addressed in a single pass. Nothing here wastes tokens or leaves the executor guessing.

DimensionReasoningScore

Conciseness

The 53-line body is lean with zero padding: no explanations of concepts Claude already knows, and even the illustrative contrasts ("'This fact was wrong' is a one-off. 'The draft opened on a thesis instead of a moment' is a habit.") earn their tokens by calibrating the skill's core judgment. Every section (Inputs, Procedure, Rules) carries only instruction.

5 / 5

Actionability

For an instruction-only skill the guidance is fully executable: exact destination files (`references/allergy-list.md`, `references/content-lessons.md`), exact entry formats ("next free `A<N>`, short name, one-line definition, and the caught example verbatim"; `L<N>` with category and a `Taught:` line), and a concrete git workflow (branch, one commit per proposal batch, PR). No pseudocode vagueness anywhere.

5 / 5

Workflow Clarity

Seven numbered steps in a clear sequence with explicit validation checkpoints for a batch write operation: read both files first to check duplicates (step 4), show proposals and wait for approve/edit/reject (step 6), and apply only what was approved with rejected proposals changing nothing (step 7). Edge cases are handled ("Zero is a fine answer... Say so and stop").

5 / 5

Progressive Disclosure

A short, simple skill with no bundle files and no need for them; the body is organized into clear Inputs/Procedure/Rules sections, and its only external pointers (the `allergist` and `voice` skills' reference files) are one level deep and clearly signaled with skill name and path.

5 / 5

Total

20

/

20

Passed

Description

83%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 strong description with an explicit what-and-when structure and genuinely natural trigger phrasing. Its only weaknesses are minor: coverage of capabilities stops at the headline actions, and the AI-ism trigger slightly overlaps a sibling skill in the same workflow.

DimensionReasoningScore

Specificity

Names several concrete actions — "Compare a published piece against the draft it started from", "propose new content lessons and allergy-list entries for the author to approve" — which sits above the 1-2-action anchor but below comprehensive, since the diff-by-meaning, duplicate-checking, and PR steps are not hinted at.

4 / 5

Completeness

Explicitly answers both halves: the what ("Compare a published piece against the draft... propose new content lessons and allergy-list entries") and the when ("Use by hand after publishing something that began as a machine draft, or when the author catches an AI-ism or a correction they never want to make again") with concrete trigger phrases, matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Good natural keywords users would actually say: "published", "draft", "machine draft", "AI-ism", "correction they never want to make again". Not anchor-5 comprehensive — common synonyms like "revise", "edit", or "post-publication review" phrasings are missing.

4 / 5

Distinctiveness Conflict Risk

The draft-comparison trigger carves a clear niche, but the second trigger ("when the author catches an AI-ism") overlaps with the closely related `allergist` skill's domain of banning phrases, creating minor conflict risk with a sibling skill rather than the minimal risk of anchor 5.

4 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

shortrib-labs/content-loop

Path

plugins/voice/skills/lessons/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.