CtrlK
BlogDocsLog inGet started
Tessl Logo

netlify-config

Configure Netlify builds and routing via netlify.toml, _redirects, and _headers. Use when setting a build command or publish directory, adding redirects or rewrites or proxies, adding an SPA fallback rewrite, setting custom response headers or basic auth, managing environment variables and secrets, scoping vars per deploy context, marking a var as secret, disabling secret scanning, configuring functions bundling, ignoring builds, or wiring up a monorepo or JavaScript SPA on Netlify.

92

0.98x
Quality

89%

Does it follow best practices?

Impact

97%

0.98x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 very strong single-file reference: extremely dense with executable, platform-specific guidance and honest gotchas, with no filler. Its main weakness is structure: at ~280 lines it keeps everything inline with no references/ offloading, and contains minor duplication and tooling-comment noise.

Suggestions

Split reference-grade catalogs (redirects/rewrite syntax rules, Secrets Controller policies, env-var CLI/API and naming limits) into references/ files (e.g. references/redirects.md, references/secrets.md) and keep SKILL.md as a shorter overview with one-level-deep, clearly signaled links.

Remove the duplicated per-scope precedence explanation (house rule 4 in the merged system section repeats the 'Scopes' paragraph) and strip the ctx-gen/system.md HTML comment noise from the rendered output.

Add a short 'verify your config' step (e.g. run 'netlify build' locally or check the deploy log for redirect/oversize errors) so risky changes get a validation checkpoint before shipping.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — no space is spent explaining what Netlify, TOML, or redirects are; nearly every line is platform-specific knowledge ('307 is unsupported', 'proxy timeout 26 s', 'Paths ... absolute relative to the base directory'). It misses a 5 because of minor trims: house rule 4 duplicates the per-scope precedence rule already stated in the Scopes paragraph, and the HTML comment markers add noise.

4 / 5

Actionability

Virtually every section provides copy-paste-ready executable snippets: TOML blocks for build/contexts, redirects, headers, functions, and dev config; a full '_redirects' syntax block with working example rules; CLI commands ('netlify env:set KEY value --secret'); and a Node ignore script. These cover the common cases directly.

5 / 5

Workflow Clarity

This is a reference-style skill rather than a linear workflow, and each task (add a redirect, set a scoped env var, configure monorepo paths) maps to unambiguous guidance with explicit failure-mode checkpoints ('a /x/ → /x 301! rule loops infinitely', 'oversized serialized output fails the deploy', secret scan 'fails the build on detection'). Not 5: there is no end-to-end validate-after-config sequence or feedback loop for verifying a config before deploy; not 3: checkpoints for the risky operations are explicitly present.

4 / 5

Progressive Disclosure

The body is well-sectioned but is a single ~280-line monolith with no bundle files at all: the full '_redirects' syntax catalog, the Secrets Controller policy details, and the env-var API/name catalog are prime candidates for references/ files. Additionally, the HTML comment 'agent-context/config/system.md — ... merged by ctx-gen' references a file that is not present in the bundle. Anchor 3 ('content that should be separate is inline'), not 4, because essentially no content is offloaded from SKILL.md.

3 / 5

Total

16

/

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.

An excellent description: third-person, dense with concrete actions and natural trigger phrases, and an explicit 'Use when' clause covering the skill's full scope. The only quibble is that it runs long, but every clause is a distinct trigger rather than fluff.

DimensionReasoningScore

Specificity

The description lists many concrete, specific actions — 'setting a build command or publish directory, adding redirects or rewrites or proxies, adding an SPA fallback rewrite, setting custom response headers or basic auth, ... configuring functions bundling, ignoring builds, or wiring up a monorepo' — with comprehensive coverage and no padding. Not 4: there are no meaningful gaps in the action coverage.

5 / 5

Completeness

It explicitly answers both 'what' ('Configure Netlify builds and routing via netlify.toml, _redirects, and _headers') and 'when' with an explicit 'Use when ...' clause enumerating concrete trigger scenarios. Clear anchor-5 match; not 4 because the when-clause is explicit and highly specific.

5 / 5

Trigger Term Quality

It covers natural phrases users would say ('build command', 'publish directory', 'redirects', 'proxies', 'basic auth', 'secrets', 'monorepo', 'SPA') plus the exact config filenames ('netlify.toml', '_redirects', '_headers') as file-level identifiers. Matches the comprehensive-with-synonyms anchor; a 4 would require missing natural terms, which is not the case.

5 / 5

Distinctiveness Conflict Risk

The Netlify-specific triggers ('netlify.toml', '_redirects', '_headers', 'Netlify') carve a clear niche with minimal overlap risk against generic deploy/hosting or CI skills. Not 4: the platform-named triggers make confusion with a closely related skill unlikely.

5 / 5

Total

20

/

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
netlify/context-and-tools
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.