A Deliverable Is Not an Instruction

by tangxiangru

A Deliverable Is Not an Instruction is an AI Engineering skill for Claude Code, published by tangxiangru in AutoR.

804 stars25 forkson tangxiangru/AutoRAdded 2026/08/22Repository updated 2026/08/22

View source on GitHub Download repo ZIP

agentaiai-scientistauto-researchclaudeclaude-codecliharnessllmopenaipaperscience

Install in seconds

Install A Deliverable Is Not an Instruction

Copy A Deliverable Is Not an Instruction into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/tangxiangru/AutoR/tree/main/src/skills/a-deliverable-is-not-an-instruction ~/.claude/skills/a-deliverable-is-not-an-instruction

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/tangxiangru/AutoR.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: src/skills/a-deliverable-is-not-an-instruction/SKILL.md in tangxiangru/AutoR
Installs to: ~/.claude/skills/a-deliverable-is-not-an-instruction
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What A Deliverable Is Not an Instruction does

A Deliverable Is Not an Instruction helps separate research deliverables from harness instructions when building a study plan and checking coverage. Use it to keep `report_plan.json` focused on findings and to mark genuinely unreachable items honestly.

A Deliverable Is Not an Instruction is cataloged under AI Engineering on DirSkills. A Deliverable Is Not an Instruction comes from a repository tagged agent, ai, ai-scientist, auto-research and claude.

Documentation

README

Excerpt

The sheet you were handed is two documents. Only one of them is the task.

A task statement that arrives through a harness is rarely only the task. Around the research question sits a second document: how to operate, where to write files, what not to do, what counts as finished. Both are addressed to you, both are written in the imperative, and one of them is not a deliverable.

Enumerate the wrong one and the study is planned against phantoms.

The failure this prevents

Measured on a forty-task benchmark arm: the deliverable list drawn off the whole instruction sheet held 337 requirements; the research questions alone held 142. Fifty-eight per cent of what every run was planning against was the harness talking about itself, and the same five phantoms appeared in all forty runs:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about A Deliverable Is Not an Instruction

What else does tangxiangru publish alongside A Deliverable Is Not an Instruction?
A Deliverable Is Not an Instruction is one of 25 skills that DirSkills catalogs from tangxiangru/AutoR, the repository it ships in. Its siblings there include A Value You Did Not Measure Still Has A Source, Answer The Why, Not Only The What and Assume This Stage Is The Last One You Get. Each one is a separate skill with its own page in this directory, installs the same way A Deliverable Is Not an Instruction does, and is maintained by tangxiangru in that same repository. The rest of the collection is listed on the tangxiangru/AutoR page.
How does A Deliverable Is Not an Instruction compare to other AI Engineering skills?
A Deliverable Is Not an Instruction ranks #1588 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of A Deliverable Is Not an Instruction against them. Open each page to compare what they document and how they install.