CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

here-now

here.now lets agents publish websites and files to live URLs in seconds. Publish HTML, documents, images, PDFs, videos, and static files to live URLs at {slug}.here.now or custom domains. Use when asked to "publish this", "host this", "deploy this", "share this on the web", "make a website", "put this online", "create a webpage", "generate a URL", "build a chatbot", "password protect this site", "make this site private", or "share this site with only certain people". here.now also includes workspaces — shared team accounts where Sites belong to the team and serve at {label}.{workspace}.here.now — use when asked to "publish this to our team workspace", "share this with my team", or "put this in our company workspace". Agents can also buy a domain for a Site through here.now (no markup, DNS and SSL automatic) — use when asked to "buy a domain", "get me a .com for this", or "register a domain".

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The body is a dense, highly actionable operations manual: every workflow ships with exact commands, real endpoints, error-recovery paths, and explicit user-communication rules. Its main weakness is sheer length — long prose sections (stale-base protection, folders, vanity URLs) inflate the always-loaded SKILL.md instead of living in one-level-deep references like the external docs it already points to.

Suggestions

Trim the 'Stale-base protection' paragraph to the conflict rule and the two recovery options, moving the drift-detection endpoint walkthrough into a reference doc or the existing https://here.now/docs anchor.

Compress the 'Current docs' topic list (~15 bullets) to the handful that change most often, since the docs page itself enumerates all endpoints.

Move the folders section's raw-API details (endpoint-by-endpoint listing, limits like '50 folders per account, names up to 60 characters') to a bundled reference file or the referenced docs page, keeping only the --folder usage and the 'never invent folders' rule inline.

DimensionReasoningScore

Conciseness

The body is ~320 lines and, while nearly all of it is non-obvious product detail (no padding with concepts Claude already knows), sections like the stale-base protection paragraph ('The live Site may have changed since your local files were published — the owner can edit it...') and the folders/vanity-URL/client-attribution details run long and could be tightened or split out. It fits 'mostly efficient but includes some unnecessary explanation or could be tightened' (level 3) rather than level 4's 'minor instances', because the length itself is a recurring cost across several sections.

3 / 5

Actionability

Guidance is fully executable throughout: copy-paste commands ('./scripts/publish.sh {file-or-dir}', 'curl -sS https://here.now/api/auth/agent/request-code -H "content-type: application/json" -d '{"email": "user@example.com"}'), the complete three-step raw API flow ('POST /api/v1/publish with a files array... PUT each file's bytes... POST the returned finalizeUrl'), a concrete state-file JSON example, and a full flags table. This matches the level-5 anchor 'copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with validation checkpoints and feedback loops: the publish flow ('A site is not live until finalize succeeds', finalize reports missing files), the five-step API-key acquisition, and explicit conflict recovery ('if the live Site moved past it, the update is rejected with code: "version_conflict"... offer to (a) read the live files... or (b) re-run with --overwrite'), plus the explicit-yes checkpoint before irreversible domain purchases. This matches the level-5 anchor ('explicit validation steps; feedback loops for error recovery') rather than level 4's 'minor validation gaps'.

5 / 5

Progressive Disclosure

The bundle is SKILL.md plus two verified scripts (./scripts/publish.sh, ./scripts/drive.sh), and the body keeps bulk detail in clearly signaled, one-level-deep external references ('→ **https://here.now/docs**', 'machine-readable schemas: https://here.now/openapi.json') with anchored sections. However, sizable inline content such as the versioning/stale-base prose and folder-management details is kept in SKILL.md rather than split into reference files, fitting 'good structure; most content is appropriately placed; minor organization gaps' (level 4) rather than level 5's fully split overview.

4 / 5

Total

17

/

20

Passed

Description

96%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.

The description is a strong example: it states concrete capabilities in third person, gives an explicit and richly populated 'Use when asked to...' trigger list for every feature area (publishing, privacy, workspaces, domain buying), and stays free of vague filler. The only reservation is that a few generic web triggers ('deploy this', 'make a website') could collide with other hosting/deployment skills.

DimensionReasoningScore

Specificity

Multiple concrete actions are enumerated: 'Publish HTML, documents, images, PDFs, videos, and static files to live URLs at {slug}.here.now or custom domains', plus workspaces ('shared team accounts where Sites belong to the team and serve at {label}.{workspace}.here.now') and domain purchase ('buy a domain... no markup, DNS and SSL automatic'). Coverage spans the product's whole capability surface, matching the level-5 anchor 'multiple specific concrete actions; comprehensive coverage'; it is well above level 4 (which allows minor gaps) and level 3 (only 1-2 actions).

5 / 5

Completeness

The 'what' is explicit ('lets agents publish websites and files to live URLs in seconds... at {slug}.here.now or custom domains') and the 'when' is explicit with three distinct 'Use when asked to...' trigger lists covering publishing, privacy, workspaces, and domain buying. This clearly matches the level-5 anchor ('clearly and explicitly answers both what AND when with concrete trigger phrases'); the level-4 anchor requires a 'when' that could be more explicit, which does not apply here.

5 / 5

Trigger Term Quality

Trigger coverage is comprehensive and natural: 'publish this', 'host this', 'deploy this', 'share this on the web', 'make a website', 'put this online', 'create a webpage', 'generate a URL', 'build a chatbot', 'password protect this site', 'make this site private', plus workspace phrases ('publish this to our team workspace') and domain phrases ('get me a .com for this', 'register a domain'). These are exactly the phrasings a user would naturally say, with synonyms and variations covered, matching the level-5 anchor; nothing significant is missing to drop it to level 4.

5 / 5

Distinctiveness Conflict Risk

The niche (instant live-URL publishing under the here.now domain, with chatbot hosting, claim links, and domain purchase) is well differentiated by branded details like '{slug}.here.now' and 'buy a domain'. However, broadly shared triggers such as 'deploy this', 'make a website', and 'put this online' have minor overlap risk with general web-development or deployment skills, so it fits 'mostly distinct; minor overlap risk with closely related skills' (level 4) better than level 5's 'minimal conflict risk'.

4 / 5

Total

19

/

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

heredotnow/skill

Path

skills/here-now/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.