CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flutter-authentication

Implement, repair, or review Flutter user authentication and session lifecycle, including OAuth or OIDC redirects, PKCE, token refresh, logout, account switching, passkeys, and device re-authentication. Use when sign-in identity or session behavior is the task; route broad threat audits to flutter-security and request transport to flutter-networking.

Quality

91%

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

The canonical home for this skill is thiennc-tesoglobal/flutter-skills

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

Excellent token efficiency and progressive disclosure: a lean overview body that conditionally routes to three real, well-scoped reference files, with a strong verification checklist. The minor gaps are in actionability (policy-level guidance without concrete package/API examples) and workflow clarity (implicit rather than explicit step sequencing, no failure-recovery loop).

Suggestions

Add one or two concrete Dart/package-level anchors (e.g., a named plugin or code snippet for PKCE verifier generation or token refresh coordination) to lift actionability from policy-level to fully executable guidance.

Make the Preflight → implement → verify sequence explicit (e.g., numbered steps or an ordered 'Workflow' heading) and add a short directive for what to do when a verification scenario fails, closing the feedback loop.

Consider mentioning 'login'/'log in' as a trigger synonym in the description to broaden natural keyword coverage.

DimensionReasoningScore

Conciseness

The ~35-line body is lean with zero padding: it never explains what Flutter, OAuth, or PKCE are, and every line is directive ("Read `pubspec.yaml`...", "Never trust a redirect merely because its scheme matches"). This matches the 'every token earns its place' anchor; the level below would require some trimming, and none is evident.

5 / 5

Actionability

For an instruction-only skill the guidance is largely concrete: preflight names exact artifacts to read, the flow section prescribes "authorization-code flow with PKCE and an external user-agent" and "correlate the response using state and, for OIDC, nonce", and verification enumerates a specific scenario matrix. It falls short of the top anchor because guidance stays at the policy level — no specific commands, APIs, or plugin/package examples to make it fully copy-paste executable.

4 / 5

Workflow Clarity

A clear implicit sequence (Preflight → conditional references → boundary routing → Verification) with strong explicit checkpoints — the verification section is a detailed checklist ("State which provider, client type, platform, account state, redirect, storage, and backend checks were actually observed"). It is not a 5 because steps are section-implied rather than explicitly sequenced and there is no feedback loop for what to do when a verification scenario fails.

4 / 5

Progressive Disclosure

The body is a concise overview and all three bundle files in references/ are real, one level deep (no nested links), each surfaced under 'Load references conditionally' with a clear description of exactly when to read it — matching the well-signaled one-level-deep anchor; the level below would require buried or unclearly signaled references.

5 / 5

Total

18

/

20

Passed

Description

92%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 description: it names the domain, enumerates concrete capabilities comprehensively, gives an explicit 'Use when' trigger, and actively disambiguates against neighboring skills. The only minor gap is a missing common synonym ('login') in the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("Implement, repair, or review") and comprehensively enumerates capabilities: "OAuth or OIDC redirects, PKCE, token refresh, logout, account switching, passkeys, and device re-authentication" — full coverage of the domain rather than 1-2 actions, matching the comprehensive anchor rather than the 'several actions with minor gaps' anchor below it.

5 / 5

Completeness

Explicitly answers both: what ("Implement, repair, or review Flutter user authentication and session lifecycle...") and when ("Use when sign-in identity or session behavior is the task"), plus routing guidance for adjacent skills — matching the anchor requiring both what and when with concrete trigger phrasing, not the level below where 'when' is only adequately explicit.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "sign-in", "token refresh", "logout", "account switching", "passkeys", "session", "OAuth". A few common variations are missing (e.g., "login"/"log in" as a synonym for sign-in), so it sits just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche (identity and session behavior) with explicit disambiguation — "route broad threat audits to flutter-security and request transport to flutter-networking" — minimizing conflict risk with the most likely overlapping siblings, which fits the minimal-conflict anchor rather than the 'minor overlap risk' anchor.

5 / 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

thienqo/flutter-skills

Path

skills/flutter-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.