{"id":13719,"external_id":"plugin_asdk_app_6aed0f2e57ac8191ae7b49b5df456f04","name":"neosigma","display_name":"NeoSigma","developer":"NeoSigma","category":"Developer Tools","listing_language":"en","listing_language_details":{"method":"cld-0.13.0/listing-v1","reliable":true,"detected_at":"2026-11-17T06:09:24Z","input_sha256":"47a5859d40a34252485e11e2be466ffc3a45933809a0d57691f02d49f374a5de","source_fields":["release.description","release.interface.short_description","release.interface.long_description"]},"version":"1.7.5","skill_count":6,"first_seen_at":"2026-11-17T00:00:34.594Z","last_seen_at":"2026-11-17T18:00:01.806Z","last_changed_at":"2026-11-17T06:14:53.226Z","install_count":null,"search_matches":[],"research_summary":null,"research_reviewed_at":null,"metadata":{"canonical_app_id":"asdk_app_6aed0f2e57ac8191ae7b49b5df456f04","connector_id":"asdk_app_6aed0f2e57ac8191ae7b49b5df456f04","created_at":"2026-11-10T19:19:42.395885Z","discoverability":"LISTED","id":"plugin_asdk_app_6aed0f2e57ac8191ae7b49b5df456f04","is_template":false,"is_template_instance":false,"name":"neosigma","release":{"app_ids":["asdk_app_6aed0f2e57ac8191ae7b49b5df456f04"],"app_manifest":{"apps":{"neosigma":{"id":"asdk_app_6aed0f2e57ac8191ae7b49b5df456f04","required":true}}},"app_templates":[],"description":"NeoSigma skills and MCP tools for coding agents: integrate the NeoSigma SDK (agent tracing and product events), import a codebase's existing checks as verifiers, suggest verifiers that catch missed production failures, convert benchmarks into Harbor tasks, write and verify a workspace's setup script, and read traces, issues, datasets, and evaluation runs through the NeoSigma MCP server.","display_name":"NeoSigma","id":"pluginrel_80bffcfbefe08191a67ff63f458456ca","interface":{"brand_color":"#0090FF","capabilities":["Search production sessions and read agent traces","Read issues and the sessions behind them","Propose evals from failing sessions and save them to datasets","Run experiments and read their results","Set up tracing, verifiers and eval environments"],"category":"Developer Tools","composer_icon_dark_url":null,"composer_icon_url":"https://files.openai.com/content?id=file_00000000d278820daecf6fae690a995e","default_prompt":"Find sessions this week that looked successful but weren't, and explain what went wrong","default_prompts":["Find sessions this week that looked successful but weren't, and explain what went wrong","Turn my agent's recent production failures into evals and save them to a dataset","Compare my last two experiments: which tasks got better and which got worse?"],"developer_name":"NeoSigma","logo_url":"https://files.openai.com/content?id=file_00000000417c820da514f54cf599c62e","logo_url_dark":null,"long_description":"Find out why your AI agent fails in production, and test the fix next to your code.\n\nUse it to:\n- Search production sessions and read traces to find failures, including runs that look successful but are not.\n- Read the issues NeoSigma found and the sessions behind each one.\n- Turn failing sessions into proposed evals, review them, and save them to a dataset.\n- Run experiments on a dataset and compare results across agent versions.\n- Add NeoSigma tracing to your agent, import your existing checks as verifiers, and set up the environment your evals run in.\n\nWho it is for: teams that build and run AI agents and already send traces to NeoSigma, or want to start.\n\nLimits: you need a NeoSigma account, and you sign in on first use. The plugin reads and changes data only in the NeoSigma projects your account can access. It does not change your agent in production. Running an experiment uses your organization's NeoSigma usage.","plugin_category_id":"developer tools","privacy_policy_url":"https://neosigma.ai/privacy","screenshot_urls":[],"short_description":"Find and fix agent failures","terms_of_service_url":"https://neosigma.ai/terms","website_url":"https://neosigma.ai"},"keywords":["neosigma","llm","observability","tracing","product-events","opentelemetry","agents","sdk","verifiers","evals","mcp","harbor"],"onboarding_skill_name":null,"requires_local_executor":false,"skills":[{"description":"Convert a benchmark available in the current workspace into faithful Harbor tasks and publish the validated immutable task set to NeoSigma. Use when asked to prepare, import, or run a benchmark that is not already a NeoSigma dataset; do not use for ordinary trace verifiers.","interface":{"brand_color":null,"default_prompt":null,"display_name":"convert-benchmark-to-harbor","icon_large_url":null,"icon_small_url":null,"iconography":"code","short_description":"Convert a benchmark available in the current workspace into faithful Harbor tasks and publish the validated immutable task set to NeoSigma. Use when asked to prepare, import, or run a benchmark that is not already a NeoSigma dataset; do not use for ordinary trace verifiers."},"name":"convert-benchmark-to-harbor","plugin_release_skill_id":"pluginrsk_6afbae96a3cc81918fec4abe186ffa3d"},{"description":"Imports a codebase's existing quality checks into NeoSigma as engine-backed verifier YAML. Activates on requests like \"import our verifiers into NeoSigma\", \"set up verifiers from my codebase\", \"add our evals to NeoSigma\", \"onboard our quality checks to NeoSigma\", or \"turn our eval suite into NeoSigma verifiers\". Requires the NeoSigma MCP to be connected. Do NOT use for analyzing traces already in NeoSigma or for integrating the tracing SDK (use integrate-sdk).","interface":{"brand_color":null,"default_prompt":null,"display_name":"import-verifiers","icon_large_url":null,"icon_small_url":null,"iconography":"code","short_description":"Imports a codebase's existing quality checks into NeoSigma as engine-backed verifier YAML. Activates on requests like \"import our verifiers into NeoSigma\", \"set up verifiers from my codebase\", \"add our evals to NeoSigma\", \"onboard our quality checks to NeoSigma\", or \"turn our eval suite into NeoSigma verifiers\". Requires the NeoSigma MCP to be connected. Do NOT use for analyzing traces already in NeoSigma or for integrating the tracing SDK (use integrate-sdk)."},"name":"import-verifiers","plugin_release_skill_id":"pluginrsk_6afbae95c3288191bdbd360b988bd716"},{"description":"Integrates the NeoSigma SDKs into a codebase so traces and product events flow into NeoSigma. Activates on requests like \"integrate NeoSigma\", \"add NeoSigma tracing to this app\", \"migrate us off the old neosigma-sdk package\", \"get our traces into NeoSigma\", \"onboard this codebase to NeoSigma\", \"set up the NeoSigma SDK\", \"send product events to NeoSigma\", \"wire NeoSigma into our existing OpenTelemetry setup\", or \"dual export to NeoSigma and another backend\". Do NOT use for analyzing traces already in NeoSigma, building evals, or developing the NeoSigma platform itself.","interface":{"brand_color":null,"default_prompt":null,"display_name":"integrate-sdk","icon_large_url":null,"icon_small_url":null,"iconography":"code","short_description":"Integrates the NeoSigma SDKs into a codebase so traces and product events flow into NeoSigma. Activates on requests like \"integrate NeoSigma\", \"add NeoSigma tracing to this app\", \"migrate us off the old neosigma-sdk package\", \"get our traces into NeoSigma\", \"onboard this codebase to NeoSigma\", \"set up the NeoSigma SDK\", \"send product events to NeoSigma\", \"wire NeoSigma into our existing OpenTelemetry setup\", or \"dual export to NeoSigma and another backend\". Do NOT use for analyzing traces already in NeoSigma, building evals, or developing the NeoSigma platform itself."},"name":"integrate-sdk","plugin_release_skill_id":"pluginrsk_6afbae95eaf88191bac7a21586a49530"},{"description":"Writes the setup script that boots a NeoSigma project's repositories in a NeoSigma sandbox into the repository at .neosigma/workspaces/<workspace_id>/projects/<project_id>/setup.sh, verifies it on a branch, repairs it from the verification diagnostics until it passes, and opens a pull request. Activates on requests like \"set up my NeoSigma project\", \"set up my NeoSigma workspace\", \"write the NeoSigma setup script\", \"create the NeoSigma setup script for this repo\", \"get this project running in the NeoSigma sandbox\", \"fix my project setup script\", \"why does my NeoSigma setup verification fail\", or \"make this repo eval-ready in NeoSigma\". Requires the NeoSigma MCP to be connected. Do NOT use for adding tracing to an application (use integrate-sdk), for importing verifiers (use import-verifiers), for converting benchmarks (use convert-benchmark-to-harbor), or for running evals.","interface":{"brand_color":null,"default_prompt":null,"display_name":"setup-environment","icon_large_url":null,"icon_small_url":null,"iconography":"bolt","short_description":"Writes the setup script that boots a NeoSigma project's repositories in a NeoSigma sandbox into the repository at .neosigma/workspaces/<workspace_id>/projects/<project_id>/setup.sh, verifies it on a branch, repairs it from the verification diagnostics until it passes, and opens a pull request. Activates on requests like \"set up my NeoSigma project\", \"set up my NeoSigma workspace\", \"write the NeoSigma setup script\", \"create the NeoSigma setup script for this repo\", \"get this project running in the NeoSigma sandbox\", \"fix my project setup script\", \"why does my NeoSigma setup verification fail\", or \"make this repo eval-ready in NeoSigma\". Requires the NeoSigma MCP to be connected. Do NOT use for adding tracing to an application (use integrate-sdk), for importing verifiers (use import-verifiers), for converting benchmarks (use convert-benchmark-to-harbor), or for running evals."},"name":"setup-environment","plugin_release_skill_id":"pluginrsk_6afbae970e888191bb44c770ed0a3438"},{"description":"Sets up `neosigma setup-eval` in a repository, so its own CI runs a NeoSigma dataset against the customer's agent and gets scores. Writes the ACP adapter, the `.neosigma/setup-eval.yaml` manifest, and the CI step. Activates on requests like \"set up NeoSigma evals in CI\", \"run NeoSigma evals on our PRs\", \"score this branch with NeoSigma\", \"add neosigma setup-eval to this repo\", \"write the setup-eval manifest\", \"compare a PR against main with NeoSigma evals\", or \"run NeoSigma evals on our own infrastructure\". Do NOT use to run evals in a NeoSigma sandbox (use setup-environment), to add tracing (use integrate-sdk), to write verifiers (use import-verifiers), or to create evals.","interface":{"brand_color":null,"default_prompt":null,"display_name":"setup-eval","icon_large_url":null,"icon_small_url":null,"iconography":"code","short_description":"Sets up `neosigma setup-eval` in a repository, so its own CI runs a NeoSigma dataset against the customer's agent and gets scores. Writes the ACP adapter, the `.neosigma/setup-eval.yaml` manifest, and the CI step. Activates on requests like \"set up NeoSigma evals in CI\", \"run NeoSigma evals on our PRs\", \"score this branch with NeoSigma\", \"add neosigma setup-eval to this repo\", \"write the setup-eval manifest\", \"compare a PR against main with NeoSigma evals\", or \"run NeoSigma evals on our own infrastructure\". Do NOT use to run evals in a NeoSigma sandbox (use setup-environment), to add tracing (use integrate-sdk), to write verifiers (use import-verifiers), or to create evals."},"name":"setup-eval","plugin_release_skill_id":"pluginrsk_6afbae96a158819196c53ee493058c32"},{"description":"Finds failures in a project's recent sessions that no verifier caught, and suggests a change to an existing verifier or a new verifier that would catch them, for a person to review on the Verifiers page. Activates on requests like \"which failures did our verifiers miss yesterday\", \"suggest verifiers from the last day of failures\", \"what verifiers should we add\", or \"improve our verifiers from production failures\". Requires the NeoSigma MCP to be connected. Do NOT use for creating evals from failures (use create-evals-from-failures), importing a codebase's checks as verifiers (use import-verifiers), or changing a verifier directly.","interface":{"brand_color":null,"default_prompt":null,"display_name":"suggest-verifiers-from-failures","icon_large_url":null,"icon_small_url":null,"iconography":"radar","short_description":"Finds failures in a project's recent sessions that no verifier caught, and suggests a change to an existing verifier or a new verifier that would catch them, for a person to review on the Verifiers page. Activates on requests like \"which failures did our verifiers miss yesterday\", \"suggest verifiers from the last day of failures\", \"what verifiers should we add\", or \"improve our verifiers from production failures\". Requires the NeoSigma MCP to be connected. Do NOT use for creating evals from failures (use create-evals-from-failures), importing a codebase's checks as verifiers (use import-verifiers), or changing a verifier directly."},"name":"suggest-verifiers-from-failures","plugin_release_skill_id":"pluginrsk_6afbae95c7d08191aca4654c2e5cef7c"}],"version":"1.7.5"},"scope":"GLOBAL","status":"ENABLED"},"research":null,"package_metadata":{"name":"neosigma","author":{"url":"https://neosigma.ai","name":"NeoSigma"},"license":"MIT","sources":[{"path":".codex-plugin/plugin.json","sha256":"736366538eaf959bac0aa3bd4ec91e481b4bd6588ab4504489efdb74a88fa15b"}],"version":"1.7.5","homepage":"https://neosigma.ai","keywords":["neosigma","llm","observability","tracing","product-events","opentelemetry","agents","sdk","verifiers","evals","mcp","harbor"],"repository":"https://github.com/neosigmaai/skills","artifact_id":269376,"observed_at":"2026-11-17T06:14:52Z","support_url":"https://docs.neosigma.ai","capabilities":["Search production sessions and read agent traces","Read issues and the sessions behind them","Propose evals from failing sessions and save them to datasets","Run experiments and read their results","Set up tracing, verifiers and eval environments"],"field_sources":{"name":0,"author":0,"license":0,"version":0,"homepage":0,"keywords":0,"repository":0,"support_url":0,"capabilities":0,"release_notes":0,"review_case_counts":0},"release_notes":"A shorter first line for the directory description. No change to skills or tools.","extraction_version":1,"review_case_counts":{"negative":3,"positive":5},"conflicts_or_errors":[]}}