deductive-runner SKILL.md skillA

deductive-runner from lulufoo/lulu-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lulufoo/lulu-workflow/deductive-runner@git:20261004.fc49baf

Pins git:20261004.fc49baf in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lulufoo/lulu-workflow
Path
compose/deductive-runner/SKILL.md
Versions recorded
5
Latest version
git:20261004.fc49baf, committed Oct 4, 2026
First version recorded
Sep 26, 2026
Size
5,194 bytes
Repository stars
3
License
MIT

Compose deductive fact-production orchestrator.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# deductive-runner

Orchestrate deductive fact production from already-intaken facts. Done
when facts validate and the parent can enter Writing.

## Responsibility

| Area | Boundary |
|------|----------|
| Invocation | Run only from compose L-execution on the deductive path. |
| Owns | pending-init → Derive → Pending Confirm → Complete. `$FAST_COMPLETE` true skips Derive and Confirm. |
| Delegates | `derive-runner` owns Floor / Ceiling / Cascade. |
| Downstream | Writing, delivery Eval, and FreeEdit remain with the parent. |

## Cognition

Facts and their fields carry the meanings defined in these units.

| Term | Unit |
|---|---|
| deduction, projection, hole, leftover | `../references/cognition/producer/deduce.md` |
| fact, `lens`, `anchors` | `../references/cognition/fact.md` |
| lens, `section-registry` edges | `../references/cognition/lens.md` |
| `origin` (`derived`), `derivation.disposition` | `../references/cognition/producer/provenance.md` |
| role `consume_policy` | `../references/cognition/profile/role.md` |

Derive material is the carried intake facts plus facts already derived;
quarantined and not_needed facts are provenance records, not material.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add lulufoo/lulu-workflow/deductive-runner@sha256:7ff106d63b59c634

The line at the top of this page pins the label git:20261004.fc49baf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_e6p6jta55un4iwg4.svg)](https://markdownregistry.com/a/art_e6p6jta55un4iwg4)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 26, 2026 and Oct 4, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261004.fc49baf latest2026-10-04 fc49baf 5,194 BA view · diff
git:20261003.1620ace2026-10-03 1620ace 5,300 BA view · diff
git:20260930.1f976aa2026-09-30 1f976aa 5,174 BA view · diff
git:20260926.d35166c2026-09-26 d35166c 5,182 BA view · diff
git:20260926.09b7c012026-09-26 09b7c01 5,176 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (5194 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

lulufoo/lulu-workflow · 3 stars · license MIT · pushed 2026-10-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_e6p6jta55un4iwg4
GET https://markdownregistry.com/api/v1/resolve?ref=lulufoo/lulu-workflow/deductive-runner
GET https://markdownregistry.com/api/v1/blob/7ff106d63b59c6348846115b252b3dafc621958932787764f8b998b08ac93e7e

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from lulufoo/lulu-workflow

lulu-workflow SKILL.md skill
lulufoo/lulu-workflow · SKILL.md · Top-level development workflow framework. Use when mentioning lulu-workflow, 开发工作流, dev workflow, product doc workflow…
git:20261002.b8bad36 · audit A · 3 stars
compose SKILL.md skill
lulufoo/lulu-workflow · compose/SKILL.md · Internal compose engine; load only via stage holder HARD-GATE — do not invoke directly.
git:20261004.fc49baf · audit A · 3 stars
chapter-write-runner SKILL.md skill
lulufoo/lulu-workflow · compose/chapter-write-runner/SKILL.md · Compose chapter-write and assemble runner for narrative-arc write units.
git:20261004.fc49baf · audit A · 3 stars
derive-runner SKILL.md skill
lulufoo/lulu-workflow · compose/deductive-runner/derive-runner/SKILL.md · Compose deductive L1: Derive Floor + Ceiling (KW ruler) after fact-intake.
git:20261004.fc49baf · audit A · 3 stars
fact-intake-runner SKILL.md skill
lulufoo/lulu-workflow · compose/fact-intake-runner/SKILL.md · Compose fact-intake orchestrator: intake document to classified focus-slice facts.
git:20261004.fc49baf · audit A · 3 stars
fact-cut-runner SKILL.md skill
lulufoo/lulu-workflow · compose/fact-intake-runner/fact-cut-runner/SKILL.md · Compose fact-intake L1: whole-doc cut and disposition classify.
git:20261004.4ffd0ff · audit A · 3 stars
fact-store-runner SKILL.md skill
lulufoo/lulu-workflow · compose/fact-store-runner/SKILL.md · Compose fact store: permit-gated write of the slice fact set.
git:20261004.4ffd0ff · audit A · 3 stars
inductive-runner SKILL.md skill
lulufoo/lulu-workflow · compose/inductive-runner/SKILL.md · Coordinates pre-writing induction across topic convergence and open-point resolution.
git:20261004.4ffd0ff · audit A · 3 stars
open-point-detect-runner SKILL.md skill
lulufoo/lulu-workflow · compose/inductive-runner/open-point-detect-runner/SKILL.md · Performs full-lens, read-only detection of unresolved questions for the current slice.
git:20261004.fc49baf · audit A · 3 stars
open-point-process-runner SKILL.md skill
lulufoo/lulu-workflow · compose/inductive-runner/open-point-process-runner/SKILL.md · Validates and analyzes one registered Open group (one lens) against current evidence.
git:20261003.33872cc · audit A · 3 stars
narrative-arc-runner SKILL.md skill
lulufoo/lulu-workflow · compose/narrative-arc-runner/SKILL.md · Compose semantic narrative-arc builder for write-ready document spines.
git:20261004.4ffd0ff · audit A · 3 stars
writing-runner SKILL.md skill
lulufoo/lulu-workflow · compose/writing-runner/SKILL.md · Compose Writing orchestrator.
git:20261004.4ffd0ff · audit A · 3 stars

Every file in lulufoo/lulu-workflow

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