agent-usage-optimizer-provider-capability-reference

Sub-skill of agent-usage-optimizer: Provider Capability Reference.

5 stars

Best use case

agent-usage-optimizer-provider-capability-reference is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Sub-skill of agent-usage-optimizer: Provider Capability Reference.

Teams using agent-usage-optimizer-provider-capability-reference should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/provider-capability-reference/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/_archive/ai/agent-usage-optimizer/provider-capability-reference/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/provider-capability-reference/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How agent-usage-optimizer-provider-capability-reference Compares

Feature / Agentagent-usage-optimizer-provider-capability-referenceStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Sub-skill of agent-usage-optimizer: Provider Capability Reference.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Provider Capability Reference

## Provider Capability Reference


| Provider       | Strengths                                          | Avoid When                          |
|----------------|----------------------------------------------------|-------------------------------------|
| Codex Opus    | Architecture, deep reasoning, compound tasks       | Quota < 20%; simple tasks           |
| Codex Sonnet  | Standard code, reviews, balanced quality/speed     | Quota < 20% and Route C needed      |
| Codex Haiku   | Bulk data, summarisation, cost-effective volume    | Architecture or security decisions  |
| Codex          | Focused code gen, unit tests, debugging functions  | Long-context docs; planning work    |
| Gemini         | Long-context analysis, large files, cross-repo     | Fine-grained code edits             |

Related Skills

provider-session-ecosystem-audit-and-exporters

5
from vamseeachanta/workspace-hub

Build and maintain cross-provider session-log audits for Codex, Codex, Hermes, and Gemini, including exporter design, normalization, and behavioral verification.

provider-audit-bootstrap-and-path-classification

5
from vamseeachanta/workspace-hub

Fix provider-session ecosystem audit failures caused by source-checkout imports and over-aggressive symbolic-path classification.

provider-review-prompt-path-guard

5
from vamseeachanta/workspace-hub

Prevent adversarial review dispatch failures caused by sandbox/tmp path mismatches and provider CLI working-directory drift when launching Codex or Gemini with prompt files.

multi-provider-adversarial-review

5
from vamseeachanta/workspace-hub

Dispatch parallel adversarial reviews to Codex and Gemini CLIs for plans or code artifacts. Use when the AI Review Routing Policy requires two- or three-provider review — architecture-heavy, security-affecting, cross-module, or high-stakes changes.

aqwa-reference

5
from vamseeachanta/workspace-hub

AQWA solver stages (RESTART), OPTIONS keywords, FIDP/FISK external damping/stiffness cards, backend bugs, and MCP tool integration patterns.

docs-stale-reference-guardrails

5
from vamseeachanta/workspace-hub

Prevent deleted workflow/path references from creeping back into live docs by combining strict scans, legacy allowlists, and shared regex helpers.

provider-session-learning-transfer

5
from vamseeachanta/workspace-hub

Refresh provider session audit, identify post-audit/unassessed sessions, extract actionable learnings, and transfer them into repo notes and GitHub issues before a follow-up implementation session.

provider-session-ecosystem-audit

5
from vamseeachanta/workspace-hub

Audit Codex/Codex/Hermes/Gemini session logs, normalize provider-specific quirks, and wire recurring exports/reporting for ongoing ecosystem health checks.

seo-optimizer

5
from vamseeachanta/workspace-hub

SEO optimization toolkit with scoring, keyword research, and technical SEO auditing. Use for improving search rankings, content optimization, and technical SEO fixes. Based on alirezarezvani/Codex-skills.

provider-utilization-scorecard

5
from vamseeachanta/workspace-hub

Refresh provider quota snapshots and generate a weekly Codex/Codex/Gemini utilization scorecard grounded in quota data when available and session-activity fallback when not.

provider-session-quota-operations

5
from vamseeachanta/workspace-hub

Class-level provider/session operations for Codex, Codex, Gemini, Hermes, quotas, audit exporters, readiness dispatch, and utilization scorecards.

usage-optimization

5
from vamseeachanta/workspace-hub

Optimize AI usage efficiency through script-first patterns, batch operations, and input preparation