CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

emdash-cli

Use the EmDash CLI to inspect and manage an EmDash instance from the command line, including content, schema, media, taxonomies, menus, search, authentication, seeds, migrations, generated types, and whole-site export and import.

Quality

82%

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

88%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 highly actionable, well-structured CLI reference with exemplary validation and confirmation gating around destructive and bulk operations, and it correctly pushes editing detail out to a reference file. The two real weaknesses are a broken reference — EDITING-FLOW.md is cited but absent from the bundle — and modest redundancy between the Authentication and Drafts/Publishing sections and their inline counterparts.

Suggestions

Ship the missing EDITING-FLOW.md in the skill bundle (or update/remove the link) — the Editing Flow section currently dead-ends for any reader following it.

Move the Cloudflare Access / reverse-proxy auth flows and the long site-import flag prose into a dedicated reference file to keep SKILL.md a lean overview and lift progressive disclosure to anchor 5.

Deduplicate the `--draft`/`--published` guidance: keep it in one place (either the CRUD comments or the Drafts and Publishing section), and fold the conceptual auth ladder into the Quick Reference authentication block.

DimensionReasoningScore

Conciseness

The body is dominated by lean, copy-paste command blocks with terse inline comments, and the prose it does keep is genuinely non-obvious product behavior (auto-publish defaults, `--rev` tokens, scope errors, import exit codes). It misses anchor 5 due to minor duplication — the "Authentication" and "Quick Reference > Authentication" sections overlap, and the "Drafts and Publishing" section restates `--draft`/`--published` semantics already commented inline in the CRUD examples — though these are trimmable rather than padded.

4 / 5

Actionability

Nearly every section is copy-paste-ready: exact `npx emdash ...` commands with realistic values (IDs, `--rev MToyMDI2...`, `--at 2026-03-01T09:00:00Z`), jq pipelines, and the common cases covered per command group. This matches the anchor-5 example of fully executable, specific commands with common-case coverage, and clearly exceeds anchor 4's "minor gaps" level.

5 / 5

Workflow Clarity

Multi-step workflows are explicitly sequenced with strong validation checkpoints: site import runs analyze → review plan/digest → `--plan sha256:<hex> --confirm` → status/resume/receipt with documented exit codes and `receiptDigestValid: true`; content update requires `--rev` from a prior get; destructive ops are gated on a prior read ("Resolve the current target with a read command before a destructive or bulk mutation") and user confirmation of the plan. Feedback loops (resume after interruption, cancel/abandon) are present, satisfying the destructive/batch validation requirement rather than triggering the cap at 3.

5 / 5

Progressive Disclosure

Structure is good: a two-category command overview up front, one section per command group, and detail correctly delegated to a clearly signaled one-level reference ("see [EDITING-FLOW.md](./EDITING-FLOW.md)"). It falls short of anchor 5 because the bundle contains no such file — the sole referenced path does not exist alongside SKILL.md — and the 260-line quick-reference monolith (Cloudflare Access flow, full site-import flag semantics) sits inline where a second reference file would fit; this places it noticeably above anchor 3's "references present but not clearly signaled" but below the clean overview-plus-references ideal.

4 / 5

Total

18

/

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 strong, information-dense description with excellent distinctiveness and broad, specific capability coverage in a single sentence. Its main gap is the complete absence of a "Use when..." trigger clause, which caps completeness and weakens how naturally a user's request would surface this skill.

Suggestions

Append an explicit trigger clause, e.g. ". Use when managing or migrating an EmDash CMS site, or when the user mentions EmDash, site export/import, or running CMS migrations from the command line."

Add user-facing synonyms such as "CMS", "site package/backup", and the `emdash`/`em` command names to improve trigger-term coverage toward anchor 5.

Consider naming one or two concrete actions per area (e.g. "create and publish content", "add collection fields") instead of the generic "inspect and manage" verbs.

DimensionReasoningScore

Specificity

The description names the domain ("EmDash CLI", "EmDash instance", "from the command line") and enumerates twelve concrete capability areas ("content, schema, media, taxonomies, menus, search, authentication, seeds, migrations, generated types, and whole-site export and import"), giving broad coverage. It falls short of anchor 5 because the only verbs are the generic "inspect and manage" — the enumerated items are objects, not distinct concrete actions like "extract text... fill forms, merge documents" — so it sits noticeably above anchor 3 but not fully at the comprehensive-actions anchor.

4 / 5

Completeness

The "what" is clearly answered (inspect and manage an EmDash instance across the listed subsystems), but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3; it does not fall to 2 because the "what" half is concrete and well-scoped.

3 / 5

Trigger Term Quality

Natural trigger words a user would say are present: "command line", "content", "schema", "search", "authentication", "migrations", "export and import", plus the product name "EmDash" itself. It is not anchor 5 because common synonyms and aliases ("CMS", "backup", the `emdash`/`em` command names, or file extensions like `.emdash`) are absent, and no use-when phrasing surfaces the triggers in user voice.

4 / 5

Distinctiveness Conflict Risk

The description is anchored to a specific named product ("EmDash CLI", "EmDash instance") with subsystem-specific terms ("taxonomies", "seeds", "generated types"), giving it a clear niche with minimal overlap risk against generic skills. It matches the anchor-5 pattern of a distinct, well-branded trigger set.

5 / 5

Total

16

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

emdash-cms/emdash

Path

templates/starter/.agents/skills/emdash-cli/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.