Skip to content

TIKAZI/TIKAZ-AI-Skills / suites/context-economy

context-economy

Flagged

Automatically prepare fidelity-first, bounded context when users paste text, attach files or folders, provide webpages or PDFs for Markdown conversion, continue long conversations, or supply documents containing images and complex tables. Route each input through Text, Hybrid, or Source; reduce exact or formatting-only repetition; protect facts and source anchors; queue only useful visual evidence; preserve uncertain originals; and benchmark efficiency and fidelity separately.

FileKindSize
MANIFEST.inother353 B
README.mdmarkdown17.1 KB
README.zh-CN.mdmarkdown8.6 KB
SKILL.mdskill md5.5 KB
VERSIONother10 B
__init__.pyscript118 B
__main__.pyscript77 B
adapters/defuddle/extract.mjsscript694 B
adapters/defuddle/package-lock.jsonmanifest12.8 KB
adapters/defuddle/package.jsonmanifest172 B
agents/openai.yamlconfig420 B
assets/conversation-state.template.mdmarkdown715 B
assets/workflow.svgother5.7 KB
benchmarks/fixtures/chinese.mdmarkdown168 B
benchmarks/fixtures/code.pyscript127 B
benchmarks/fixtures/conversation.mdmarkdown176 B
benchmarks/fixtures/data.jsonconfig84 B
benchmarks/fixtures/efficiency-long.mdmarkdown3.5 KB
benchmarks/fixtures/english.mdmarkdown167 B
benchmarks/fixtures/long-form.mdmarkdown439 B
benchmarks/fixtures/multimodal-decoration.mdmarkdown150 B
benchmarks/fixtures/multimodal-hybrid.mdmarkdown220 B
benchmarks/fixtures/multimodal-plain-image.mdmarkdown112 B
benchmarks/fixtures/multimodal-simple-table.mdmarkdown75 B
benchmarks/fixtures/multimodal-table.mdmarkdown257 B
benchmarks/fixtures/multimodal-text.mdmarkdown184 B
benchmarks/fixtures/multimodal-two-charts.mdmarkdown101 B
benchmarks/fixtures/prompt-repeat-a.txtmarkdown140 B
benchmarks/fixtures/prompt-repeat-b.txtmarkdown148 B
benchmarks/fixtures/prompt-structural-a.txtmarkdown238 B
benchmarks/fixtures/prompt-structural-b.txtmarkdown220 B
benchmarks/fixtures/service.logother155 B
benchmarks/fixtures/source-scan.pdfbinary193 B
benchmarks/fixtures/web-article-images.htmlother334 B
benchmarks/fixtures/web-article.htmlother389 B
benchmarks/fixtures/web-empty.htmlother135 B
benchmarks/manifest.jsonconfig11.9 KB
benchmarks/pdf/fixtures/illustrated-report.pdfbinary1.9 KB
benchmarks/pdf/fixtures/table-report.pdfbinary1.9 KB
benchmarks/pdf/fixtures/text-report.pdfbinary2.2 KB
benchmarks/pdf/generate_fixtures.pyscript3.1 KB
benchmarks/pdf/ground-truth.jsonconfig1.0 KB
benchmarks/pdf/results/README.mdmarkdown1.4 KB
benchmarks/pdf/results/converted/illustrated-report.mdmarkdown112 B
benchmarks/pdf/results/converted/table-report.mdmarkdown246 B
benchmarks/pdf/results/converted/text-report.mdmarkdown201 B
benchmarks/pdf/results/metrics.jsonconfig1.4 KB
benchmarks/pdf/run_fidelity.pyscript5.5 KB
benchmarks/results/README.mdmarkdown2.2 KB
benchmarks/results/cases.jsonconfig30.2 KB
benchmarks/results/metrics.jsonconfig4.1 KB
benchmarks/results/summary.jsonconfig1.1 KB
benchmarks/retrieval-challenge-v1.jsonconfig9.1 KB
benchmarks/retrieval-manifest.jsonconfig14.5 KB
benchmarks/retrieval-results/challenge-v1/cases.jsonconfig14.1 KB
benchmarks/retrieval-results/challenge-v1/evidence-card.mdmarkdown536 B
benchmarks/retrieval-results/challenge-v1/metrics.jsonconfig494 B
benchmarks/retrieval-results/challenge-v1/summary.jsonconfig1.1 KB
benchmarks/retrieval-results/development-v1/cases.jsonconfig19.6 KB
benchmarks/retrieval-results/development-v1/evidence-card.mdmarkdown603 B
benchmarks/retrieval-results/development-v1/metrics.jsonconfig442 B
benchmarks/retrieval-results/development-v1/summary.jsonconfig1.1 KB
pyproject.tomlmanifest2.1 KB
references/benchmark-method.mdmarkdown2.9 KB
references/context-health.mdmarkdown480 B
references/conversion-adapters.mdmarkdown2.5 KB
references/output-contract.mdmarkdown2.2 KB
references/routing.mdmarkdown1.4 KB
references/threat-model.mdmarkdown5.1 KB
scripts/__init__.pyscript45 B
scripts/tikaz_context.pyscript94.3 KB

benchmarks/retrieval-results/challenge-v1/cases.json

View on GitHub
[
  {
    "id": "zh-certificate-outage",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 3.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.44318181818181823
    },
    "query": "证书失效导致加密流量中断后,如何恢复并防止复发?",
    "query_variants": [],
    "ranked_ids": [
      "prevent",
      "cause",
      "recover",
      "traffic",
      "identity",
      "machine"
    ],
    "relevant_ids": [
      "cause",
      "prevent",
      "recover"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "prevent",
        "cause",
        "recover"
      ],
      "selected_tokens_estimated": 49,
      "source_tokens_estimated": 88,
      "status": "matched",
      "token_reduction_estimated": 0.44318181818181823
    }
  },
  {
    "id": "zh-accessibility",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 3.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.38636363636363635
    },
    "query": "不用鼠标也能操作,并且在手机窄屏上保持可读",
    "query_variants": [],
    "ranked_ids": [
      "labels",
      "mobile",
      "keyboard",
      "mouse",
      "phone",
      "audio"
    ],
    "relevant_ids": [
      "keyboard",
      "labels",
      "mobile"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "labels",
        "mobile",
        "keyboard"
      ],
      "selected_tokens_estimated": 54,
      "source_tokens_estimated": 88,
      "status": "matched",
      "token_reduction_estimated": 0.38636363636363635
    }
  },
  {
    "id": "zh-context-proof",
    "metrics": {
      "dynamic_facet_coverage": 0.8,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 3.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.367816091954023
    },
    "query": "生成最小有用的上下文,同时保留证据和可追溯性",
    "query_variants": [],
    "ranked_ids": [
      "facts",
      "budget",
      "anchors",
      "small",
      "proof",
      "material"
    ],
    "relevant_ids": [
      "anchors",
      "budget",
      "facts"
    ],
    "selection": {
      "confidence": 0.8000000000000002,
      "evidence_precision": 1.0,
      "facet_coverage": 0.8,
      "relevant_recall": 1.0,
      "selected_ids": [
        "facts",
        "budget",
        "anchors"
      ],
      "selected_tokens_estimated": 55,
      "source_tokens_estimated": 87,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.367816091954023
    }
  },
  {
    "id": "en-scanned-document",
    "metrics": {
      "dynamic_facet_coverage": 0.2727272727272727,
      "dynamic_precision": 0.6,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 0.6666666666666666,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 0.7039180890341348,
      "precision_at_1": 1.0,
      "precision_at_3": 0.6666666666666666,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 0.6666666666666666,
      "selected_token_reduction_estimated": 0.13432835820895528
    },
    "query": "A report without a text layer must retain tables, illustrations, and page evidence",
    "query_variants": [],
    "ranked_ids": [
      "table",
      "print",
      "detect",
      "cover",
      "visual",
      "chart"
    ],
    "relevant_ids": [
      "detect",
      "table",
      "visual"
    ],
    "selection": {
      "confidence": 0.2727272727272727,
      "evidence_precision": 0.6,
      "facet_coverage": 0.2727272727272727,
      "relevant_recall": 1.0,
      "selected_ids": [
        "table",
        "print",
        "detect",
        "cover",
        "visual"
      ],
      "selected_tokens_estimated": 58,
      "source_tokens_estimated": 67,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.13432835820895528
    }
  },
  {
    "id": "release-rollback",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 0.75,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 4.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.23880597014925375
    },
    "query": "release database rollback backup verification owner",
    "query_variants": [],
    "ranked_ids": [
      "backup",
      "verify",
      "rollback",
      "brand",
      "office",
      "menu"
    ],
    "relevant_ids": [
      "backup",
      "rollback",
      "verify"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 0.75,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "backup",
        "verify",
        "rollback",
        "brand"
      ],
      "selected_tokens_estimated": 51,
      "source_tokens_estimated": 67,
      "status": "matched",
      "token_reduction_estimated": 0.23880597014925375
    }
  },
  {
    "id": "incident-response",
    "metrics": {
      "dynamic_facet_coverage": 0.75,
      "dynamic_precision": 1.0,
      "dynamic_recall": 0.6666666666666666,
      "dynamic_selected_count": 2.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.5483870967741935
    },
    "query": "incident impact root cause mitigation validation accountable owner",
    "query_variants": [],
    "ranked_ids": [
      "cause",
      "action",
      "impact",
      "event",
      "paper",
      "theme"
    ],
    "relevant_ids": [
      "action",
      "cause",
      "impact"
    ],
    "selection": {
      "confidence": 0.75,
      "evidence_precision": 1.0,
      "facet_coverage": 0.75,
      "relevant_recall": 0.6666666666666666,
      "selected_ids": [
        "cause",
        "action"
      ],
      "selected_tokens_estimated": 28,
      "source_tokens_estimated": 62,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.5483870967741935
    }
  },
  {
    "id": "contract-audit",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 3.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.4482758620689655
    },
    "query": "contract effective date payment termination approval audit",
    "query_variants": [],
    "ranked_ids": [
      "date",
      "payment",
      "audit",
      "photo",
      "search",
      "chart"
    ],
    "relevant_ids": [
      "audit",
      "date",
      "payment"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "date",
        "payment",
        "audit"
      ],
      "selected_tokens_estimated": 32,
      "source_tokens_estimated": 58,
      "status": "matched",
      "token_reduction_estimated": 0.4482758620689655
    }
  },
  {
    "id": "finance-reconciliation",
    "metrics": {
      "dynamic_facet_coverage": 0.75,
      "dynamic_precision": 0.75,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 4.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.30000000000000004
    },
    "query": "reconcile invoices approved pending anomaly total audit",
    "query_variants": [],
    "ranked_ids": [
      "status",
      "anomaly",
      "total",
      "font",
      "video",
      "cache"
    ],
    "relevant_ids": [
      "anomaly",
      "status",
      "total"
    ],
    "selection": {
      "confidence": 0.75,
      "evidence_precision": 0.75,
      "facet_coverage": 0.75,
      "relevant_recall": 1.0,
      "selected_ids": [
        "status",
        "anomaly",
        "total",
        "font"
      ],
      "selected_tokens_estimated": 42,
      "source_tokens_estimated": 60,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.30000000000000004
    }
  },
  {
    "id": "research-synthesis",
    "metrics": {
      "dynamic_facet_coverage": 0.8181818181818182,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 3.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.4032258064516129
    },
    "query": "research methods samples results limitations citations",
    "query_variants": [],
    "ranked_ids": [
      "limit",
      "method",
      "result",
      "logo",
      "build",
      "social"
    ],
    "relevant_ids": [
      "limit",
      "method",
      "result"
    ],
    "selection": {
      "confidence": 0.8181818181818182,
      "evidence_precision": 1.0,
      "facet_coverage": 0.8181818181818182,
      "relevant_recall": 1.0,
      "selected_ids": [
        "limit",
        "method",
        "result"
      ],
      "selected_tokens_estimated": 37,
      "source_tokens_estimated": 62,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.4032258064516129
    }
  },
  {
    "id": "video-evidence",
    "metrics": {
      "dynamic_facet_coverage": 0.3958333333333333,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 3.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.3780487804878049
    },
    "query": "视频转写时间戳关键帧画面语义来源证据",
    "query_variants": [],
    "ranked_ids": [
      "meaning",
      "asr",
      "frames",
      "music",
      "avatar",
      "footer"
    ],
    "relevant_ids": [
      "asr",
      "frames",
      "meaning"
    ],
    "selection": {
      "confidence": 0.3958333333333333,
      "evidence_precision": 1.0,
      "facet_coverage": 0.3958333333333333,
      "relevant_recall": 1.0,
      "selected_ids": [
        "meaning",
        "asr",
        "frames"
      ],
      "selected_tokens_estimated": 51,
      "source_tokens_estimated": 82,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.3780487804878049
    }
  },
  {
    "id": "dynamic-web",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 3.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 1.0,
      "selected_token_reduction_estimated": 0.3709677419354839
    },
    "query": "render dynamic webpage main content screenshot citation source anchor",
    "query_variants": [],
    "ranked_ids": [
      "render",
      "shot",
      "cite",
      "team",
      "price",
      "color"
    ],
    "relevant_ids": [
      "cite",
      "render",
      "shot"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "render",
        "shot",
        "cite"
      ],
      "selected_tokens_estimated": 39,
      "source_tokens_estimated": 62,
      "status": "matched",
      "token_reduction_estimated": 0.3709677419354839
    }
  },
  {
    "id": "negative-evidence",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 0.6666666666666666,
      "dynamic_selected_count": 2.0,
      "evidence_precision": 0.6666666666666666,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 0.7653606369886218,
      "precision_at_1": 1.0,
      "precision_at_3": 0.6666666666666666,
      "recall_at_1": 0.3333333333333333,
      "recall_at_3": 0.6666666666666666,
      "selected_token_reduction_estimated": 0.6376811594202898
    },
    "query": "database rollback verification evidence",
    "query_variants": [],
    "ranked_ids": [
      "rollback",
      "record",
      "none-a",
      "none-b",
      "none-c",
      "backup"
    ],
    "relevant_ids": [
      "backup",
      "record",
      "rollback"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 0.6666666666666666,
      "selected_ids": [
        "rollback",
        "record"
      ],
      "selected_tokens_estimated": 25,
      "source_tokens_estimated": 69,
      "status": "matched",
      "token_reduction_estimated": 0.6376811594202898
    }
  }
]
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 196kUpdated Claude CodeCodexVerifiedInstall