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/development-v1/cases.json

View on GitHub
[
  {
    "id": "release-migration",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.2680412371134021
    },
    "query": "release database migration rollback backup verification",
    "query_variants": [],
    "ranked_ids": [
      "rel-rollback",
      "rel-backup",
      "rel-owner",
      "rel-verify",
      "rel-command",
      "noise-brand",
      "noise-menu",
      "noise-office"
    ],
    "relevant_ids": [
      "rel-backup",
      "rel-command",
      "rel-owner",
      "rel-rollback",
      "rel-verify"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "rel-rollback",
        "rel-backup",
        "rel-owner",
        "rel-verify",
        "rel-command"
      ],
      "selected_tokens_estimated": 71,
      "source_tokens_estimated": 97,
      "status": "matched",
      "token_reduction_estimated": 0.2680412371134021
    }
  },
  {
    "id": "document-fidelity",
    "metrics": {
      "dynamic_facet_coverage": 0.75,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.3125
    },
    "query": "扫描 PDF OCR 表格 图片 来源锚点 高保真转换",
    "query_variants": [],
    "ranked_ids": [
      "doc-anchor",
      "doc-gate",
      "doc-scan",
      "doc-table",
      "doc-image",
      "noise-color",
      "noise-social",
      "noise-logo"
    ],
    "relevant_ids": [
      "doc-anchor",
      "doc-gate",
      "doc-image",
      "doc-scan",
      "doc-table"
    ],
    "selection": {
      "confidence": 0.75,
      "evidence_precision": 1.0,
      "facet_coverage": 0.75,
      "relevant_recall": 1.0,
      "selected_ids": [
        "doc-anchor",
        "doc-gate",
        "doc-scan",
        "doc-table",
        "doc-image"
      ],
      "selected_tokens_estimated": 77,
      "source_tokens_estimated": 112,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.3125
    }
  },
  {
    "id": "code-review",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.25
    },
    "query": "review deployment dependency security error configuration tests",
    "query_variants": [],
    "ranked_ids": [
      "code-test",
      "code-dep",
      "code-error",
      "code-sec",
      "code-entry",
      "noise-css",
      "noise-copy",
      "noise-sales"
    ],
    "relevant_ids": [
      "code-dep",
      "code-entry",
      "code-error",
      "code-sec",
      "code-test"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "code-test",
        "code-dep",
        "code-error",
        "code-sec",
        "code-entry"
      ],
      "selected_tokens_estimated": 72,
      "source_tokens_estimated": 96,
      "status": "matched",
      "token_reduction_estimated": 0.25
    }
  },
  {
    "id": "video-evidence",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.27192982456140347
    },
    "query": "视频 转写 时间戳 关键帧 画面 OCR 语义 证据",
    "query_variants": [],
    "ranked_ids": [
      "vid-anchor",
      "vid-asr",
      "vid-ocr",
      "vid-scene",
      "vid-vlm",
      "noise-music",
      "noise-avatar",
      "noise-footer"
    ],
    "relevant_ids": [
      "vid-anchor",
      "vid-asr",
      "vid-ocr",
      "vid-scene",
      "vid-vlm"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "vid-anchor",
        "vid-asr",
        "vid-ocr",
        "vid-scene",
        "vid-vlm"
      ],
      "selected_tokens_estimated": 83,
      "source_tokens_estimated": 114,
      "status": "matched",
      "token_reduction_estimated": 0.27192982456140347
    }
  },
  {
    "id": "incident-response",
    "metrics": {
      "dynamic_facet_coverage": 0.8888888888888888,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.2808988764044944
    },
    "query": "incident root cause affected systems mitigation validation owner",
    "query_variants": [],
    "ranked_ids": [
      "inc-cause",
      "inc-impact",
      "inc-check",
      "inc-fix",
      "inc-owner",
      "noise-theme",
      "noise-event",
      "noise-print"
    ],
    "relevant_ids": [
      "inc-cause",
      "inc-check",
      "inc-fix",
      "inc-impact",
      "inc-owner"
    ],
    "selection": {
      "confidence": 0.888888888888889,
      "evidence_precision": 1.0,
      "facet_coverage": 0.8888888888888888,
      "relevant_recall": 1.0,
      "selected_ids": [
        "inc-cause",
        "inc-impact",
        "inc-check",
        "inc-fix",
        "inc-owner"
      ],
      "selected_tokens_estimated": 64,
      "source_tokens_estimated": 89,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.2808988764044944
    }
  },
  {
    "id": "frontend-quality",
    "metrics": {
      "dynamic_facet_coverage": 0.875,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.2872340425531915
    },
    "query": "frontend accessibility responsive contrast typography interaction states",
    "query_variants": [],
    "ranked_ids": [
      "ui-state",
      "ui-a11y",
      "ui-responsive",
      "ui-type",
      "ui-contrast",
      "noise-db",
      "noise-audio",
      "noise-legal"
    ],
    "relevant_ids": [
      "ui-a11y",
      "ui-contrast",
      "ui-responsive",
      "ui-state",
      "ui-type"
    ],
    "selection": {
      "confidence": 0.875,
      "evidence_precision": 1.0,
      "facet_coverage": 0.875,
      "relevant_recall": 1.0,
      "selected_ids": [
        "ui-state",
        "ui-a11y",
        "ui-responsive",
        "ui-type",
        "ui-contrast"
      ],
      "selected_tokens_estimated": 67,
      "source_tokens_estimated": 94,
      "status": "partial-evidence",
      "token_reduction_estimated": 0.2872340425531915
    }
  },
  {
    "id": "financial-reconciliation",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.3176470588235294
    },
    "query": "invoice reconciliation approved pending total anomaly audit",
    "query_variants": [],
    "ranked_ids": [
      "fin-approved",
      "fin-pending",
      "fin-audit",
      "fin-anomaly",
      "fin-total",
      "noise-video",
      "noise-font",
      "noise-cache"
    ],
    "relevant_ids": [
      "fin-anomaly",
      "fin-approved",
      "fin-audit",
      "fin-pending",
      "fin-total"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "fin-approved",
        "fin-pending",
        "fin-audit",
        "fin-anomaly",
        "fin-total"
      ],
      "selected_tokens_estimated": 58,
      "source_tokens_estimated": 85,
      "status": "matched",
      "token_reduction_estimated": 0.3176470588235294
    }
  },
  {
    "id": "contract-obligations",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.2558139534883721
    },
    "query": "contract effective date termination amount approval audit obligation",
    "query_variants": [],
    "ranked_ids": [
      "law-date",
      "law-audit",
      "law-amount",
      "law-term",
      "law-approval",
      "noise-chart",
      "noise-search",
      "noise-photo"
    ],
    "relevant_ids": [
      "law-amount",
      "law-approval",
      "law-audit",
      "law-date",
      "law-term"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "law-date",
        "law-audit",
        "law-amount",
        "law-term",
        "law-approval"
      ],
      "selected_tokens_estimated": 64,
      "source_tokens_estimated": 86,
      "status": "matched",
      "token_reduction_estimated": 0.2558139534883721
    }
  },
  {
    "id": "dynamic-web",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.2727272727272727
    },
    "query": "dynamic webpage rendered main content citation screenshot source anchor",
    "query_variants": [],
    "ranked_ids": [
      "web-anchor",
      "web-render",
      "web-main",
      "web-cite",
      "web-shot",
      "noise-team",
      "noise-color",
      "noise-price"
    ],
    "relevant_ids": [
      "web-anchor",
      "web-cite",
      "web-main",
      "web-render",
      "web-shot"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "web-anchor",
        "web-render",
        "web-main",
        "web-cite",
        "web-shot"
      ],
      "selected_tokens_estimated": 56,
      "source_tokens_estimated": 77,
      "status": "matched",
      "token_reduction_estimated": 0.2727272727272727
    }
  },
  {
    "id": "research-synthesis",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.2696629213483146
    },
    "query": "research method sample result limitation citation evidence",
    "query_variants": [],
    "ranked_ids": [
      "res-cite",
      "res-limit",
      "res-method",
      "res-sample",
      "res-result",
      "noise-logo",
      "noise-build",
      "noise-social"
    ],
    "relevant_ids": [
      "res-cite",
      "res-limit",
      "res-method",
      "res-result",
      "res-sample"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "res-cite",
        "res-limit",
        "res-method",
        "res-sample",
        "res-result"
      ],
      "selected_tokens_estimated": 65,
      "source_tokens_estimated": 89,
      "status": "matched",
      "token_reduction_estimated": 0.2696629213483146
    }
  },
  {
    "id": "semantic-certificate-recovery",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.31999999999999995
    },
    "query": "What should operators do when encrypted traffic stops because machine identity is no longer valid?",
    "query_variants": [],
    "ranked_ids": [
      "sem-cert-check",
      "sem-cert-restart",
      "sem-cert-alert",
      "sem-cert-cause",
      "sem-cert-rotate",
      "sem-noise-machine",
      "sem-noise-traffic",
      "sem-noise-identity"
    ],
    "relevant_ids": [
      "sem-cert-alert",
      "sem-cert-cause",
      "sem-cert-check",
      "sem-cert-restart",
      "sem-cert-rotate"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "sem-cert-check",
        "sem-cert-restart",
        "sem-cert-alert",
        "sem-cert-cause",
        "sem-cert-rotate"
      ],
      "selected_tokens_estimated": 68,
      "source_tokens_estimated": 100,
      "status": "matched",
      "token_reduction_estimated": 0.31999999999999995
    }
  },
  {
    "id": "semantic-scanned-report",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.29268292682926833
    },
    "query": "没有可复制文字的报告怎样保住表格和插图信息",
    "query_variants": [],
    "ranked_ids": [
      "sem-scan-table",
      "sem-scan-detect",
      "sem-scan-fallback",
      "sem-scan-image",
      "sem-scan-anchor",
      "sem-noise-copy",
      "sem-noise-print",
      "sem-noise-chart"
    ],
    "relevant_ids": [
      "sem-scan-anchor",
      "sem-scan-detect",
      "sem-scan-fallback",
      "sem-scan-image",
      "sem-scan-table"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "sem-scan-table",
        "sem-scan-detect",
        "sem-scan-fallback",
        "sem-scan-image",
        "sem-scan-anchor"
      ],
      "selected_tokens_estimated": 87,
      "source_tokens_estimated": 123,
      "status": "matched",
      "token_reduction_estimated": 0.29268292682926833
    }
  },
  {
    "id": "semantic-context-proof",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.2808988764044944
    },
    "query": "prepare the smallest useful material while keeping proof",
    "query_variants": [],
    "ranked_ids": [
      "sem-context-fact",
      "sem-context-task",
      "sem-context-omit",
      "sem-context-budget",
      "sem-context-anchor",
      "sem-noise-material",
      "sem-noise-proof",
      "sem-noise-small"
    ],
    "relevant_ids": [
      "sem-context-anchor",
      "sem-context-budget",
      "sem-context-fact",
      "sem-context-omit",
      "sem-context-task"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "sem-context-fact",
        "sem-context-task",
        "sem-context-omit",
        "sem-context-budget",
        "sem-context-anchor"
      ],
      "selected_tokens_estimated": 64,
      "source_tokens_estimated": 89,
      "status": "matched",
      "token_reduction_estimated": 0.2808988764044944
    }
  },
  {
    "id": "semantic-accessibility",
    "metrics": {
      "dynamic_facet_coverage": 1.0,
      "dynamic_precision": 1.0,
      "dynamic_recall": 1.0,
      "dynamic_selected_count": 5.0,
      "evidence_precision": 1.0,
      "mrr": 1.0,
      "ndcg_at_1": 1.0,
      "ndcg_at_3": 1.0,
      "ndcg_at_5": 1.0,
      "precision_at_1": 1.0,
      "precision_at_3": 1.0,
      "precision_at_5": 1.0,
      "recall_at_1": 0.2,
      "recall_at_3": 0.6,
      "recall_at_5": 1.0,
      "selected_token_reduction_estimated": 0.30927835051546393
    },
    "query": "make the interface usable without a mouse and readable on a phone",
    "query_variants": [],
    "ranked_ids": [
      "sem-ui-label",
      "sem-ui-type",
      "sem-ui-mobile",
      "sem-ui-focus",
      "sem-ui-keyboard",
      "sem-noise-interface",
      "sem-noise-mouse",
      "sem-noise-phone"
    ],
    "relevant_ids": [
      "sem-ui-focus",
      "sem-ui-keyboard",
      "sem-ui-label",
      "sem-ui-mobile",
      "sem-ui-type"
    ],
    "selection": {
      "confidence": 1.0,
      "evidence_precision": 1.0,
      "facet_coverage": 1.0,
      "relevant_recall": 1.0,
      "selected_ids": [
        "sem-ui-label",
        "sem-ui-type",
        "sem-ui-mobile",
        "sem-ui-focus",
        "sem-ui-keyboard"
      ],
      "selected_tokens_estimated": 67,
      "source_tokens_estimated": 97,
      "status": "matched",
      "token_reduction_estimated": 0.30927835051546393
    }
  }
]
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