CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

using-oauth2

Connect to a user-provided OAuth2 app, complete authorization, and use its access token in Code Mode HTTP requests.

Quality

71%

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 ./backend/super-magic/agents/skills/using-oauth2/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 highly actionable — every step ships complete, copy-paste-ready code with a clear tool inventory and explicit rules for token safety and fallbacks. Its weaknesses are systematic duplication of the oauth2_request examples, the absence of any confirmation or validation step before the batch-removal (destructive) operations, and a monolithic single-file structure that inlines reference-grade material.

Suggestions

Add an explicit confirmation checkpoint before oauth2_remove_app and oauth2_remove_api_doc calls (e.g. ask the user to confirm the exact app names / operation_ids first, and verify the removal result), which would lift workflow clarity past the batch-operation cap.

Consolidate the four oauth2_request code examples (minimal GET, full template, form variant, and step 5's GET/POST pair) into the parameter table plus one full template and one variant, cutting roughly a third of the body.

Move the oauth2_request parameter/return tables and the full oauth2_upsert_api_doc OpenAPI schema into a references/ file (e.g. references/api_reference.md) linked from the body, so SKILL.md stays a navigable overview.

DimensionReasoningScore

Conciseness

The oauth2_request usage is demonstrated four separate times (minimal GET, full commented template, form variant, and again in workflow step 5), and the parameter table duplicates the commented template. This is 'mostly efficient but could be tightened' rather than 4's 'minor instances of over-explanation', since the duplication is systematic.

3 / 5

Actionability

Every snippet is complete, executable Python with the exact run_sdk_snippet / tool.call invocation shape, including a parameter table, both json_body and form_body variants, and a working urllib fallback. This matches 'fully executable; copy-paste ready code' covering the common cases.

5 / 5

Workflow Clarity

The six-step standard workflow is well sequenced with authorization status checks and error-recovery rules (OAuth2AuthorizationRequired, refresh failure, pending status). However, the batch/destructive operations oauth2_remove_app and oauth2_remove_api_doc have no validation or user-confirmation checkpoint, which caps workflow clarity at 3 per the judging guidelines.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), so all ~500 lines are inlined in SKILL.md. Sections are well organized with clear headers, but the oauth2_request parameter/return tables and the full oauth2_upsert_api_doc JSON schema are inline content that belongs in a reference file, matching anchor 3's 'content that should be separate is inline'.

3 / 5

Total

14

/

20

Passed

Description

66%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 specific and action-oriented, clearly naming the OAuth2 connect-authorize-call sequence in third person. Its main weakness is the complete absence of a 'Use when...' trigger clause, which both caps completeness and leaves a minor distinctiveness gap against generic HTTP-request skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user provides OAuth2 app credentials or documentation, or asks to call an API that requires OAuth2 authorization.'

Include natural trigger variations users would say, such as 'OAuth', 'sign in with', 'login', or 'authorize', to improve trigger term coverage.

Mention the app-registration and API-doc recording capabilities so the description covers the skill's full scope, not just the token flow.

DimensionReasoningScore

Specificity

Names three concrete actions — 'Connect to a user-provided OAuth2 app, complete authorization, and use its access token in Code Mode HTTP requests' — matching the 'several specific actions' anchor. It falls short of 5 because it omits capabilities the body covers, such as registering apps and recording API documentation.

4 / 5

Completeness

The 'what' is clearly stated (connect, authorize, use token in HTTP requests), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2, because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Includes natural domain terms users would say ('OAuth2', 'access token', 'authorization', 'app') with good coverage. Not 5, because common variations like 'OAuth', 'login', or 'sign in' are missing and 'Code Mode' is product jargon rather than a user-spoken phrase.

4 / 5

Distinctiveness Conflict Risk

The OAuth2 app integration niche is mostly distinct with clear domain-specific triggers, but 'use its access token in Code Mode HTTP requests' leaves minor overlap risk with a generic API-calling skill. Anchor 4 fits better than 5's 'minimal conflict risk'.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (501 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

dtyq/magic

Path

backend/super-magic/agents/skills/using-oauth2/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.