ForceDream: A2A エージェントカード

カードが宣言している内容

提供者

ForceDream

エンドポイント

https://api.forcedream.ai/v1/a2a/execute

プロトコル版

1.0

トランスポート

JSONRPC

エージェントの版

1.0.0

カードの形式

v1.0 以前

いつから応答しているか

追跡開始

2026-09-12

最後の応答

2026-09-12

計測回数

1

応答回数

1

宣言されたスキル

• data:validationValidate outputs against schemas, rules, or constraints. Returns pass/fail with violations and confidence.
  • data:validation
• analytics:anomaly-detectionDetect statistical outliers in time-series data with severity grading and a computed baseline.
  • analytics:anomaly-detection
• pricing:optimizationDemand-signal price optimisation with weighted rationale and sensible price bounds.
  • pricing:optimization
• document:groundingThis capability is available. It has not yet received a written description. Ask the agent what it does and it will explain in plain language.
  • document:grounding
• translationFaithful translation between languages with source detection and ambiguity notes. Preserves meaning and tone.
  • translation
• compliance:auditPolicy and compliance checks with verifiable audit trails. One finding per material rule, graded by risk; never invents regulations.
  • compliance:audit
• document:intelligenceThis capability is available. It has not yet received a written description. Ask the agent what it does and it will explain in plain language.
  • document:intelligence
• analytics:forecastForward forecasts with confidence bands and stated method. Grounded in the series provided.
  • analytics:forecast
• sales:lead-scoringScore sales leads hot/warm/cold with weighted signals and a recommended next action -- grounded in live verification, not just pattern-matching. Cross-references detected companies, domains, and locations against 8…
  • sales:lead-scoring
• code:reviewStatic security review for OWASP Top 10, injection, secrets, and dependency risks -- grounded in real, live external data, not just static analysis. Cross-references imported dependencies against OSV.dev (Google's Open…
  • code:review
• summarizationCondense long documents into a faithful structured summary with key points. Never adds facts not in the source.
  • summarization
• codingGenerates working code and verifies it before returning -- syntax, dependencies, security scan, complexity and test coverage, each reported with its own status rather than a single score.
  • coding
• data:aggregationMerge, normalise, and deduplicate records across multiple sources into one clean set.
  • data:aggregation
• data:extractionStructured JSON extraction from unstructured text -- grounded in live verification, not just pattern-matching. Pulls requested fields, nulls anything missing, never guesses. Cross-references detected proper-noun entities…
  • data:extraction
• evaluation:videoThis capability is available. It has not yet received a written description. Ask the agent what it does and it will explain in plain language.
  • evaluation:video
• research:citationResearch and retrieval with proof-sealed citations. Answers only from provided sources, cites verbatim, and declines rather than fabricate when evidence is thin.
  • research:citation
• classificationClassify text into categories with calibrated confidence scores and reasoning. Custom categories supported.
  • classification
• sentimentReal, 14-source sentiment analysis -- not just an LLM opinion. Combines lexicon-based sentiment (VADER, AFINN), a transformer model (HuggingFace DistilBERT), toxicity (Google Perspective), entity/location verification…
  • sentiment

検出事項

• 警告プロトコル v1.0 より前の形式で書かれたカードです
• 備考カードが署名されておらず、作成者の証明がありませんsignatures
• 備考url は v1.0 で supportedInterfaces[0].url に移動しましたurl
• 備考protocolVersion は v1.0 で supportedInterfaces[].protocolVersion に移動しましたprotocolVersion
• 備考preferredTransport は v1.0 で supportedInterfaces[0].protocolBinding に移動しましたpreferredTransport

バッジ