Home / badmuriss / my-llm-kit · skills/ingest/SKILL.md · GitHub

ingest skillA

ingest is agent-read markdown (skill) from badmuriss/my-llm-kit: Extract content from documents when their format or layout prevents reliable direct reading. Verify reading order and tables before analysis..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Ingest

Use direct reading for text, Markdown, CSV that preserves its structure, and
known source-code files. Do not convert or bundle a repository merely to inspect
one file. For editing a document, use its format-specific skill when available.

For PDF or Office extraction, prefer an available local converter such as
`anydoc`. For image or audio input, use a tool with the required OCR or
transcription capability; do not assume every installation has those extras.
Use a layout-aware converter for complex or scanned PDFs when ordinary extraction
scrambles the content. Install extra converters only when the task needs them.

Preserve the original. Write extracted content to a task-local directory and
verify headings, table structure, reading order and footnotes before citing it.
If extraction fails, try a suitable alternative or report which content could
not be read reliably. Never summarize scrambled extraction as established fact.

A conversion batch may be delegated when useful. A returned path or successful
process exit does not replace inspecting the output. Avoid loading an entire
long document when targeted passages are enough.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add badmuriss/my-llm-kit/ingest@git:20260906.3d137c0
Exact content
mdr add badmuriss/my-llm-kit/ingest@sha256:85af33aa453d32ea

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_oeljz3ioxxi52rke.svg)](https://markdownregistry.com/a/art_oeljz3ioxxi52rke)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260906.3d137c0 latest2026-09-06 3d137c0 1,413 BA view · diff
git:20260808.343cbe32026-08-08 343cbe3 3,553 BA view · diff
git:20260807.420ee2d2026-08-07 420ee2d 3,724 BA view · diff
git:20260801.31d2d242026-08-01 31d2d24 2,333 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1413 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

badmuriss/my-llm-kit · 3 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_oeljz3ioxxi52rke
GET https://markdownregistry.com/api/v1/resolve?ref=badmuriss/my-llm-kit/ingest
GET https://markdownregistry.com/api/v1/blob/85af33aa453d32ea4f2c811e39f2ac47a458a7d00ed014aac637625fe702c96d

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from badmuriss/my-llm-kit

AGENTS.md agents
badmuriss/my-llm-kit · AGENTS.md
git:20260906.3d137c0 · audit A · 3 stars
AGENTS.md@instructions agents
badmuriss/my-llm-kit · instructions/AGENTS.md
git:20260923.97e81e6 · audit A · 3 stars
agent-graph skill
badmuriss/my-llm-kit · skills/agent-graph/SKILL.md · Run durable task graphs when independent work needs ownership, integration checks and recovery. Use for graph…
git:20260921.471bbed · audit A · 3 stars
computer-use skill
badmuriss/my-llm-kit · skills/computer-use/SKILL.md · Inspect and operate local browser or desktop interfaces. Prefer Jev Ultrafast for supported browser-only goals when its…
git:20260921.471bbed · audit A · 3 stars
frontend-visual-validation skill
badmuriss/my-llm-kit · skills/frontend-visual-validation/SKILL.md · Verify rendered UI changes with reproducible screenshots and vision review on their supported platforms.
git:20260906.3d137c0 · audit A · 3 stars
grill-me skill
badmuriss/my-llm-kit · skills/grill-me/SKILL.md · Adversarial interview about a plan until you reach shared understanding. use_when: "grill me", stress-test a plan or…
git:20260808.343cbe3 · audit A · 3 stars
grill-with-docs skill
badmuriss/my-llm-kit · skills/grill-with-docs/SKILL.md · Grill a plan against the documented domain model, updating CONTEXT.md and ADRs inline. use_when: stress-test a plan…
git:20260808.343cbe3 · audit A · 3 stars
impl skill
badmuriss/my-llm-kit · skills/impl/SKILL.md · Implement a requested change or approved plan, verify its outcomes, and report concrete blockers. Use graph execution…
git:20260921.471bbed · audit A · 3 stars
readme-pass skill
badmuriss/my-llm-kit · skills/readme-pass/SKILL.md · Make a public repository README easier to understand and use. Apply when README structure or presentation is requested.
git:20260906.3d137c0 · audit A · 3 stars
remove-ai-marks skill
badmuriss/my-llm-kit · skills/remove-ai-marks/SKILL.md · Inspect and remove requested metadata or invisible marks from user-owned files. Use when provenance cleanup is…
git:20260906.3d137c0 · audit B · 3 stars
research skill
badmuriss/my-llm-kit · skills/research/SKILL.md · Research external questions and compare evidence with source attribution. Use for research or fact-checking, not facts…
git:20260923.97e81e6 · audit A · 3 stars
rule-curator skill
badmuriss/my-llm-kit · skills/rule-curator/SKILL.md · Audit an existing corpus of agent instructions for conflicts, duplication and unnecessary process. Use for a…
git:20260906.3d137c0 · audit A · 3 stars

Every file in badmuriss/my-llm-kit

Other files named ingest

ingest skill
garrytan/gbrain · plugin-variants/gbrain-daily/skills/ingest/SKILL.md · Route content to specialized ingestion skills. Detects input type and delegates.
git:20260817.489e277 · audit A · 30,275 stars
ingest skill
garrytan/gbrain · plugin-variants/gbrain-coding/skills/ingest/SKILL.md · Route content to specialized ingestion skills. Detects input type and delegates.
git:20260817.489e277 · audit A · 30,275 stars
ingest skill
suboss87/fdeops · skills/ingest/SKILL.md · Fetch requested source material and prepare sourced engagement updates. Use to catch up from external notes or…
git:20260917.a9ffb90 · audit A · 891 stars
ingest skill
ariaxhan/kernel-claude · skills/ingest/SKILL.md · Entry point for new or resumed work. Researches and scopes new tasks; validates and resumes handoff/checkpoint…
git:20260910.3c9303c · audit A · 13 stars
ingest skill
technicalpickles/pickled-claude-plugins · plugins/second-brain/skills/ingest/SKILL.md · Turn a raw session notes file into an ingested note, ready for the enrich stage. Defaults to keeping it whole; only…
git:20260827.96da65a · audit A · 10 stars

Browse by kind, by grade A, or by owner.