CtrlK
BlogDocsLog inGet started
Tessl Logo

citations

Canonical rules and HTML/CSS contract for inline `[n]` citation references, end-of-document Citations blocks, and optional per-section citation recaps used across Moody's Agentic Solutions HTML report skills (earnings-brief, peer-analysis, issuer-brief, sector-brief, etc.). Parent skills must read BOTH this `SKILL.md` (rules, numbering, hyperlink behavior, source data shape) AND `assets/template.html` (canonical CSS block + literal HTML markup snippets) before emitting citations. The asset file is the single source of truth for the visual/markup implementation; this `SKILL.md` is the single source of truth for the authoring rules. Triggers when the user asks about citations, sources, references, footnotes, hyperlinking [n] markers, or the Sources/Citations block in any HTML report skill.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A well-structured, highly actionable contract skill that correctly offloads CSS and markup to a real asset file with clear one-level navigation. Minor verbosity and a scattered emit workflow without an error-recovery loop keep it just below the top tier on two dimensions.

Suggestions

Consolidate the repeated "single source of truth" framing and trim the sibling-skill inlining-pattern blockquote to a one-line cross-reference, keeping only what the citations contract needs.

Add one consolidated numbered emit workflow (read both files → emit markup → inline CSS between markers → run checklist) with an explicit validate-and-fix loop, instead of spreading the sequence across sections 1–6.

DimensionReasoningScore

Conciseness

The body is dense and contract-focused with no concept explanations Claude already knows, but the "single source of truth" framing is repeated across the intro, section 5, and the sibling-skill blockquote, and that blockquote's inlining-pattern detail is tangential to the citations contract, so it could be tightened.

2 / 3

Actionability

Guidance is concrete and copy-paste oriented — exact `<template id="…">` ids, a source-data field table, a variant-selection table, literal CSS-comment markers, and an executable `:root` alias snippet with substitution placeholders — fully actionable for an instruction/contract skill.

3 / 3

Workflow Clarity

A verification checklist (section 6) provides explicit validation, but the emit workflow is distributed across sections rather than one consolidated numbered sequence and lacks a validate→fix→retry feedback loop, fitting the "sequence present but checkpoints implicit/scattered" anchor.

2 / 3

Progressive Disclosure

Content is cleanly split — rules in SKILL.md, canonical CSS and markup templates in the verified-real `assets/template.html` — with well-signaled one-level-deep references (each section names the template id it lives in), matching the clear-overview-with-shallow-references anchor.

3 / 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, well-triggered, and complete — it states concrete capabilities, an explicit trigger clause, and a clearly scoped niche in third-person voice. It is among the strongest examples in the rubric's reference set.

DimensionReasoningScore

Specificity

Enumerates multiple concrete capabilities — "inline `[n]` citation references, end-of-document Citations blocks, and optional per-section citation recaps" plus "canonical CSS block + literal HTML markup snippets" — matching the anchor for listing several specific actions rather than vague language.

3 / 3

Completeness

Clearly answers both what ("Canonical rules and HTML/CSS contract for …") and when ("Triggers when the user asks about …"), with the explicit trigger guidance the rubric requires to reach 3.

3 / 3

Trigger Term Quality

The explicit clause "Triggers when the user asks about citations, sources, references, footnotes, hyperlinking [n] markers, or the Sources/Citations block" covers a broad set of natural terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Scoped to "Moody's Agentic Solutions HTML report skills" and a specific citation-rendering contract, giving it a clear niche unlikely to fire for unrelated skills; uses third person throughout so no voice penalty applies.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.