Skip to main content
Run any Skill in Manus
with one click
Traigent
GitHub creator profile

Traigent

Repository-level view of 25 collected skills across 2 GitHub repositories.

skills collected
25
repositories
2
updated
2026-07-08
repository explorer

Repositories and representative skills

traigent-analyze-results
software-developers

Analyze and report Traigent optimization results from the terminal โ€” without opening the portal's tabs. Use when a user asks to analyze a run, 'how did my run do?', 'analyze my latest run in project X', what the winner is, or to read result fields, reports, leaderboards, Pareto trade-offs, correlations, or parameter/example insights. Decision questions route to `traigent-analyze-guidance` for portal-tracked runs and `traigent-analyze-guidance` for offline/local runs. Also covers the local OptimizationResult object: reading results.best_config, comparing trials, checking stop_reason, calling apply_best_config(), accessing total_cost or total_tokens, or understanding why optimization stopped.

2026-07-08
traigent-setup-quickstart
software-developers

Install, set up, and get first value from the Traigent SDK for LLM optimization. The cold-start path: use when the user is new to traigent, wants their first run, has no dataset yet, or wants to install traigent, set up their first optimization, create an evaluation dataset, or get started with @traigent.optimize. Covers pip install, API-key setup, mock mode, a linear first-value walkthrough, and running a first optimization.

2026-07-08
traigent-optimize-run
software-developers

Run Traigent optimization: async/sync execution, algorithm selection, cost limits, stop conditions, and parallel trials. Use when calling func.optimize() or optimize_sync(), choosing algorithms (auto/grid/random today; bayesian/optuna are roadmap, not yet executable), setting max_trials or cost_limit, configuring parallel execution, or handling CostLimitExceeded.

2026-07-08
traigent-optimize-composite-knobs
software-developers

Declare and run Traigent composite knobs: cascades, routers, ensembles, self-consistency, best-of-n, self-refine, self-debug, ReAct tool loops, verification gates, mixture-of-experts, and fallback patterns. Use when choosing a catalog pattern, wiring StageRunner/LoopBodyRunner execution, merging composite telemetry into metrics, or explaining calibration-backed claim scope.

2026-07-08
traigent-setup-integrations
software-developers

Integrate Traigent with LangChain, LiteLLM, DSPy, and other AI frameworks. Use when importing langchain/litellm/dspy alongside traigent, setting up multi-provider model testing, using auto_override_frameworks, or asking about framework-specific adapter patterns.

2026-07-08
traigent-analyze-guidance
software-developers

What should this Traigent optimization run be, and what next? Three modes: (A) pre-run โ€” fetch the service run-plan, present objectives/models/knobs/search/budget/offline options, apply preflight; (B) post-run, portal-tracked โ€” fetch `traigent next-steps RUN_ID --json`, present posture.summary_text plus the single returned command template; (C) offline/local fallback โ€” diagnose flat/noisy/negative local results, which knob mattered, example evidence, form the next iteration hypothesis when offline=True or no service payload. Portal-tracked decisions come from Traigent, never local markdown.

2026-07-08
traigent-boost-agent
software-developers

End-to-end lifecycle playbook โ€” from a single decorated function to a full 12-step codebase onboarding โ€” for adding Traigent to an existing client agent codebase and measurably boosting accuracy, cost, latency, or reliability. Use when asked to add Traigent to this agent, onboard this agent to Traigent end-to-end, run a full agent-build lifecycle, wire an evaluator and optimize, boost accuracy/cost of an existing agent codebase, select TVARs with recommend_configuration_space(), choose composite knobs by agent shape, instrument @traigent.optimize minimally, validate in mock mode, run real optimization with budgets, inspect results, iterate, gate a promoted config, optimize a function with @traigent.optimize, run an optimization, or set up Traigent optimization. ALWAYS start with dry-run (mock mode) to validate the full pipeline, then switch to real execution only when the user explicitly requests it.

2026-07-08
traigent-optimize-config-space
software-developers

Define tuned variables, structural knobs, and configuration spaces for Traigent optimization. Use when setting up parameter search spaces, choosing models/temperatures/prompts, designing task-level text2SQL/RAG/multi-hop knobs, using Range/IntRange/Choices/LogRange types, adding constraints, or using factory presets like Range.temperature().

2026-07-08
Showing top 8 of 18 collected skills in this repository.
traigent-debugging
software-developers

Debug and troubleshoot Traigent optimization issues. Use when encountering CostLimitExceeded, ConfigurationError, OptimizationStateError, ModuleNotFoundError, or when optimization produces unexpected results. Covers mock mode, logging configuration, and common error resolution.

2026-07-04
traigent-decorator-setup
software-developers

Configure the @traigent.optimize() decorator with evaluation, injection, and execution options. Use when setting up eval_dataset, choosing injection_mode, configuring execution_mode, defining objectives, using EvaluationOptions/InjectionOptions/ExecutionOptions, or integrating custom evaluators.

2026-07-02
traigent-run-optimization
software-developers

Run Traigent optimization: async/sync execution, algorithm selection, cost limits, stop conditions, and parallel trials. Use when calling func.optimize() or optimize_sync(), choosing algorithms (grid/random โ€” locally; bayesian/optuna/tpe run in the Traigent cloud), setting max_trials or cost_limit, configuring parallel execution, or handling CostLimitExceeded.

2026-07-02
traigent-quickstart
software-developers

Install and set up the Traigent SDK for LLM optimization. Use when the user wants to install traigent, set up their first optimization, create an eval dataset, or get started with @traigent.optimize. Covers pip install, environment variables, mock mode, and running a first optimization.

2026-06-26
traigent-analyze-results
software-developers

Analyze Traigent optimization results: best config, trial comparison, convergence, cost, and applying results to production. Use when reading results.best_config, comparing trials, checking stop_reason, calling apply_best_config(), accessing total_cost or total_tokens, or understanding why optimization stopped.

2026-06-18
traigent-integrations
software-developers

Integrate Traigent with LangChain, LiteLLM, DSPy, and other AI frameworks. Use when importing langchain/litellm/dspy alongside traigent, setting up multi-provider model testing, using auto_override_frameworks, or asking about framework-specific adapter patterns.

2026-06-18
traigent-configuration-space
software-developers

Define tuned variables and configuration spaces for Traigent optimization. Use when setting up parameter search spaces, choosing models/temperatures/prompts to optimize, using Range/IntRange/Choices/LogRange types, adding constraints between parameters, or using factory presets like Range.temperature().

2026-06-06
Showing 2 of 2 repositories
All repositories loaded