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

references/conversion-adapters.md

View on GitHub
# Conversion adapters

The standard-library core directly reads Markdown, text, JSON/JSONL, CSV/TSV, YAML, HTML, common code, configuration, and log files. It does not silently OCR or parse proprietary binary formats.

For PDF or Office input, use an available external converter such as a local document-to-Markdown workflow, inspect representative pages or sections for fidelity, and pass the resulting Markdown to `tikaz-context pack`. Keep the original file unchanged and report losses. Run `doctor` to inspect availability; it never installs software.

Executable discovery is only a probe, not a capability guarantee. A converter can exist while its PDF/OCR extras are missing. Run a known fixture before declaring a format supported, record the adapter used, and retain conversion failures as evidence. The public generated-PDF benchmark supports explicit `markitdown` and `pdfplumber` adapters without bundling either one.

## Webpage adapter

The optional `adapters/defuddle` bridge pins Defuddle `0.19.2` and linkedom `0.18.13`. Install it explicitly with `npm ci` inside that adapter directory; the Python core and `doctor` never run package installation. The bridge parses supplied HTML without executing page scripts, uses `separateMarkdown: true`, retains images, and disables Defuddle's third-party async fallback with `useAsync: false`.

```powershell
python .\scripts\tikaz_context.py web `
  --url 'https://example.com/article' `
  --task 'extract release evidence' `
  --output .\.context-economy-web
```

Only public HTTP(S) targets are accepted. Local, private, reserved, and link-local addresses are rejected; redirects are revalidated; fetches have explicit size and timeout bounds. Dynamic client-rendered shells, extraction failures, and missing dependencies return `source` instead of pretending Markdown is complete.

Use the profiler before conversion decisions:

- pure text and structurally safe tables -> `text`;
- text plus informative figures or complex tables -> `hybrid`;
- scans, design/layout-heavy assets, low-confidence extraction, or missing page references -> `source`.

In `hybrid`, Markdown is the primary text asset. Put only task-relevant figures or source visuals into `visual-evidence.json`, deduplicate repeated targets, cap `--visual-budget`, and let an image-capable host resolve queued items. Keep descriptions, detected values, uncertainty, and the original page/image anchor together. If no vision capability is available, keep `pending-vision` and recommend the relevant source page rather than silently flattening it.
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