CtrlK
BlogDocsLog inGet started
Tessl Logo

markdown-html-orchestrator

Use when a user wants to convert any markdown file in their Claude project into a single-file, lightly-interactive HTML — long-form documents (specs, plans, RFCs, reports, explainers), code reviews with diffs and severity-tagged annotations, or slide decks. Triggers on "convert this markdown to HTML", "make this an HTML file", "turn this into an interactive document", "render this report as HTML", "PR writeup as HTML", "slides from this markdown". Forks context to route to one of three converter sub-skills (md-document, md-review, md-slides) based on a deterministic doctype classifier, after the user has run the design-system onboarding once. Refuses if input is under 100 lines (per Shihipar — markdown still wins below the threshold) or design-system isn't onboarded. Distinct from Anthropic's official Playground plugin (which is interactive prompt-tuning controls with sliders/knobs/prompt-copy-back) and from marketing/landing/ (which is a landing-page generator).

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/markdown-html-orchestrator/SKILL.md

The canonical home for this skill is markdown-html-orchestrator in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

56%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.

A well-structured, actionable orchestrator body with a clear gated workflow and concrete scripts, but it is noticeably verbose for an overview skill and inlines routing detail that belongs in bundle files which are absent.

Suggestions

Trim the forcing-question library and merge its essentials into the routing/workflow sections to reduce token overhead for an orchestrator that mainly delegates to sub-skills.

Move the signal table and detailed classifier routing heuristics into a references/ file, keeping SKILL.md as a lean overview that points to it.

Add an explicit verify-output step (e.g., confirming the single-file HTML was written and is non-empty) at the end of the Step 5 handoff to complete the workflow feedback loop.

DimensionReasoningScore

Conciseness

Noticeably verbose for an orchestrator overview: the forcing-question library (lines 89-104), full signal table, and extensive 'Distinct from'/'Anti-patterns' sections restate routing logic and disambiguation the body already covers, padding the token budget beyond what Claude needs.

2 / 5

Actionability

Provides concrete executable pipelines — the classifier/route_explainer pipe (lines 48-52), onboard.py, output_path_resolver.py with flag examples — with only minor gaps (the renderer handoff is named but its invocation command is not shown).

4 / 5

Workflow Clarity

Clear five-step sequence with named scripts at each stage and explicit pre-flight refusal gates that act as validation checkpoints; the destructive-overwrite concern is handled via collision-suffix logic, though the final render step lacks a verify-output checkpoint.

4 / 5

Progressive Disclosure

Sections are well-labeled and cross-references to sibling sub-skills are one-level-deep, but the References block points at external repos/URLs rather than local bundle files, and no references/ scripts/ assets/ bundles exist to absorb the inlined routing detail, so structure is only partially externalized.

3 / 5

Total

13

/

20

Passed

Description

100%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 high-quality, specific description with explicit 'Use when' triggers, concrete artifact types, and clear distinction from adjacent tools. It fully answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and artifact types — 'convert any markdown file ... into a single-file, lightly-interactive HTML', with enumerated input classes (long-form documents, code reviews with diffs and severity-tagged annotations, slide decks) and explicit fork/route behavior.

5 / 5

Completeness

Opens with an explicit 'Use when a user wants to...' clause answering both what (markdown→HTML conversion across three doctypes) and when (the listed trigger phrases), plus refusal conditions and routing behavior.

5 / 5

Trigger Term Quality

Provides comprehensive natural trigger phrases users would actually say — 'convert this markdown to HTML', 'make this an HTML file', 'turn this into an interactive document', 'render this report as HTML', 'PR writeup as HTML', 'slides from this markdown'.

5 / 5

Distinctiveness Conflict Risk

States a clear niche (markdown→single-file HTML conversion) and explicitly distinguishes it from Anthropic's Playground plugin and marketing/landing/, minimizing conflict risk.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-skills
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.