CtrlK
BlogDocsLog inGet started
Tessl Logo

replay-qa-api

Use when calling Replay QA's REST API directly from Codex. Covers bearer-token setup, Replay recording prerequisites, project creation from Replay recordings or target URLs, polling, bug retrieval, journeys, test runs, explorations, and fix workflow discipline.

75

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered API skill: fully executable examples, a validated multi-step fix workflow, and clean sectioned organization with no concept filler. The only minor redundancy is the API Reference table restating endpoints already shown as curl, but it serves as a useful quick-reference rather than padding.

DimensionReasoningScore

Conciseness

The body is lean and instruction-only: executable curl blocks, short field lists, and a quick-reference table with no padding explaining what a REST API or Replay is, so every section earns its place rather than the mostly-efficient-but-tightenable score 2.

3 / 3

Actionability

Every endpoint ships a complete, copy-paste-ready curl example with headers and JSON bodies (e.g. the project-creation POST), plus concrete field constraints like 'agent_count must be between 1 and 10', matching the fully-executable anchor.

3 / 3

Workflow Clarity

The Fix Workflow Discipline section is a numbered 7-step sequence with explicit checkpoints ('Wait for each selected project to finish analysis', 'Do not infer a root cause ... while Replay QA analysis is still pending') and a re-run feedback loop, satisfying the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the skill is self-contained and organized into clearly headed one-level sections (Authentication, Base URL, Poll, Fetch Bugs, etc.), which scores 3 for a no-external-reference skill per the simple-skills scoring note.

3 / 3

Total

12

/

12

Passed

Description

85%Weight 40%Scale 1-3

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, specific description with an explicit Use-when trigger and a clear niche. Its only weakness is trigger-term naturalness: the phrasing is somewhat technical and offers limited variation of the terms a user would actually say.

Suggestions

Soften the trigger to natural phrasing a user would say, e.g. 'Use when the user wants Replay QA to analyze a failing test or explore an app for bugs', to broaden natural keyword coverage.

Add common user-facing variants of the trigger term (e.g. 'Replay QA analysis', 'Replay bug reports') alongside the REST-API phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'bearer-token setup, Replay recording prerequisites, project creation from Replay recordings or target URLs, polling, bug retrieval, journeys, test runs, explorations, and fix workflow discipline', matching the multiple-specific-actions anchor rather than the partial coverage of score 2.

3 / 3

Completeness

It explicitly answers both what (the enumerated capabilities) and when ('Use when calling Replay QA's REST API directly from Codex'), satisfying the explicit-trigger anchor; score 2 is ruled out because the when-clause is present and explicit.

3 / 3

Trigger Term Quality

The trigger names the relevant product term ('Replay QA') but the phrasing ('calling Replay QA's REST API directly from Codex') is technical and offers few natural user-facing variations, so it lands at 'some relevant keywords but missing common variations' rather than the broad coverage of score 3.

2 / 3

Distinctiveness Conflict Risk

'Replay QA's REST API' is a clear, narrow niche with a distinct trigger unlikely to fire for unrelated skills, matching the clear-niche anchor instead of the overlap-prone score 2.

3 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.