Tessl • The management layer for AI agent skills

SkillPublic

is-agentic

Score how ready a website, domain, or public MCP endpoint is for AI agents using Is Agentic, and read or act on the resulting report. Use when asked to check a site's agent readiness, get its Is Agentic score, fetch a scored report as JSON, or fix the issues that lower a site's score.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

96%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 excellent, token-efficient, fully actionable skill body with a validated improve-workflow and concrete error handling. Its only structural shortfall is that the report schema and gotchas are inlined in a slightly-over-threshold body rather than split into a one-level reference.

Suggestions

Move the "Read a report" field-by-field PublicScanReport schema into a references/report-schema.md file and keep a 3-4 line summary inline, bringing the body under 50 lines and earning the simple-skill progressive-disclosure exemption.

Optionally relocate the caching/rate-limit details in "Gotchas" to a references/gotchas.md, keeping only the scanned_at staleness check inline since it guards the improve workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a one-sentence intro, executable commands, and dense gotchas (cache TTL, 404-vs-scan behavior, exact-target semantics, rate limit, Accept: text/markdown) with no padding or explanation of concepts Claude already knows. Every line earns its place.	5 / 5
Actionability	Fully executable throughout: `npx is-agentic <domain> --json`, the exact API endpoint `GET https://is-agentic.com/api/v1/report?url=...`, named MCP tools, concrete field-by-field report decoding, and per-error-code actions (e.g., "honor `Retry-After` before retrying"). Copy-paste ready and covers the common cases.	5 / 5
Workflow Clarity	The "Improve a site's score" section gives a clear 4-step sequence with an explicit prioritization rule (essential failures → essential partials → recommended) and a validation checkpoint (re-score and "compare `scanned_at`" to avoid reading a stale snapshot), while the Errors section supplies feedback loops for recovery. Not a destructive/batch operation, so no cap applies.	5 / 5
Progressive Disclosure	Well-organized with clear sections, no buried references (the bundle is a single self-contained SKILL.md with no reference files), and nothing misplaced. However, the ~57-line body slightly exceeds the rubric's under-50-line simple-skill threshold, and the full report-field schema and gotchas are inlined where a one-level-deep reference file could carry them — a minor organization gap between anchors 4 and 5.	4 / 5
	Total	19 / 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.

The description is exemplary: concrete third-person actions, an explicit "Use when" trigger clause with natural phrasing, and a distinct named-tool niche. It directly matches the rubric's good-overall examples in structure and quality.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Score how ready a website, domain, or public MCP endpoint is", "read or act on the resulting report", "fetch a scored report as JSON", "fix the issues that lower a site's score" — with comprehensive coverage of the tool's capabilities and named target types.	5 / 5
Completeness	Explicitly answers both: what it does ("Score how ready a website... and read or act on the resulting report") and when to use it via a literal "Use when asked to..." clause with concrete trigger phrases — matching the anchor-5 example pattern exactly.	5 / 5
Trigger Term Quality	Covers the natural phrases a user would say — "check a site's agent readiness", "get its Is Agentic score", "fetch a scored report as JSON", "fix the issues" — plus synonyms across "website", "domain", "MCP endpoint", and "AI agents". No common variation is missing.	5 / 5
Distinctiveness Conflict Risk	A clear niche — agent-readiness auditing via the distinctly named "Is Agentic" tool — with triggers (agent readiness, Is Agentic score) that no other skill would claim; minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: vercel/vercel-plugin
Path: skills/is-agentic/SKILL.md
Revision: 3c88cfc

Reviewed: 19 days ago

Discovery Implementation Validation

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.

is-agentic

Table of Contents

Is this your skill?