CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

authentication

How auth works in agent-native apps. Use when wiring login/signup, configuring auth modes, setting up organizations, protecting routes, or debugging session issues.

Quality

72%

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 ./.agents/skills/authentication/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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, framework-specific reference with excellent concrete code, env vars, and validation gates, and no filler. Its main costs are token efficiency — dense multi-clause prose walls in the MCP OAuth and Desktop SSO sections — and a monolithic single-file structure that inlines runbook-level detail a reference file should carry.

Suggestions

Move the 'Remote MCP OAuth' and 'Packaged Desktop workspace sign-in' sections' runbook-level detail into reference files (e.g. references/mcp-oauth.md, references/desktop-sso.md), keeping only the rules and entry points inline so SKILL.md stays an overview.

Tighten the long run-on paragraphs in 'Remote MCP OAuth' and 'Cross-App SSO' into short bullet lists of invariants; several pack 5+ rules per sentence, which is the main conciseness cost.

Add code or command examples for the SSO/MCP configuration sections (e.g. the env var sets for federation secrets, the authorize-URL construction) so those sections are as executable as the org-roles and route-protection ones.

DimensionReasoningScore

Conciseness

The body is dense with framework-specific facts and explains nothing Claude already knows, but sections like 'Remote MCP OAuth' and 'Packaged Desktop workspace sign-in' are long run-on prose paragraphs packing many invariants per sentence, which could be meaningfully tightened into lists or shorter statements. It is not score 2 because there is no generic filler or padding, and not 4 because the tightening needed goes beyond minor instances.

3 / 5

Actionability

Concrete, executable guidance dominates: copy-paste snippets for defineAppRoles, the getSession(event) route guard, the /sign-in?return= redirect, and AppProviders wiring, plus exact env vars, file paths, and function names. It falls short of 5 because several major sections (Remote MCP OAuth, Cross-App SSO, Desktop sign-in) are declarative policy with no code or commands for the common cases they describe.

4 / 5

Workflow Clarity

Where workflows exist they are well sequenced with explicit verification gates — the canary rollout checklist ('verify (logout → silent SSO → same pre-existing account, same canonical org ID, ... data intact)'), same-origin validation of the return path, and named enforcement guards (guard:ssr-cache-shell, guard-no-localhost-fallback.mjs). It is not 5 because most of the document is reference policy rather than sequenced procedures with checkpoints.

4 / 5

Progressive Disclosure

Section headers are clear and external pointers are well signaled ('/docs/cross-app-sso', the 'security' and 'actions' skills), but the bundle has no reference files at all while ~430 lines of specialized detail — the Desktop SSO runbook, MCP OAuth token semantics, and the app-roles API — are inlined in SKILL.md where a one-level-deep reference structure belongs. Not 4 because the split is more than a minor organization gap; not 2 because structure is good and links are explicit.

3 / 5

Total

14

/

20

Passed

Description

75%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 well-formed description with an explicit and well-triggered 'Use when' clause listing five concrete tasks. Its main weaknesses are a generic 'what' statement and missing common trigger synonyms (sign-in, OAuth, SSO) for parts of the skill the description never names.

DimensionReasoningScore

Specificity

Lists five concrete actions — 'wiring login/signup, configuring auth modes, setting up organizations, protecting routes, or debugging session issues' — but large parts of the skill's coverage (MCP OAuth, cross-app SSO, service principals, app roles) go unmentioned, so coverage has minor gaps rather than being comprehensive.

4 / 5

Completeness

The 'when' is explicit and specific ('Use when wiring login/signup, ... or debugging session issues'), but the 'what' ('How auth works in agent-native apps') is a topic statement rather than a list of concrete capabilities, so the what-side is present yet not explicit enough for a 5.

4 / 5

Trigger Term Quality

Natural phrases users would say are present ('login/signup', 'setting up organizations', 'debugging session issues'), but common synonyms such as 'sign-in', 'log in', 'OAuth', 'SSO', or 'permissions' are missing, keeping it short of comprehensive keyword coverage.

4 / 5

Distinctiveness Conflict Risk

Scoping to 'agent-native apps' carves out a clear niche with distinct triggers, though the auth domain overlaps somewhat with the sibling 'security' and 'actions' skills referenced in the body.

4 / 5

Total

16

/

20

Passed

Validation

68%

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

Validation — 11 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

11

/

16

Passed

Repository

BuilderIO/agent-native

Path

.agents/skills/authentication/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.