Agent skill

Writing Specs

by Netflix-Skunkworks in Netflix-Skunkworks/oci-agent

Invoke this skill when initiating an OCI analysis from a plan or user prompt — i.e.

Apache-2.0Auto-check passedData & Analytics

Install Writing Specs

skills CLI
$ npx skills add Netflix-Skunkworks/oci-agent --skill writing-specs -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Netflix-Skunkworks/oci-agent writing-specs --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Netflix-Skunkworks/oci-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writing-specs .claude/skills/writing-specs && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
writing-specs
GitHub stars
144
Token cost
~364 tokens
SKILL.md length
131 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

Invoke this skill when initiating an OCI analysis from a plan or user prompt — i.e.

  • Tasks that involve Jupyter notebooks
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Writing Specs is an agent skill from Netflix-Skunkworks/oci-agent. Invoke this skill when initiating an OCI analysis from a plan or user prompt — i.e. before any notebook is parameterized or executed. Keywords: - analysis spec, eval spec, spec.yaml - treatment, outcome, covariates, confounders - ATE, ATT, ATO, atothreshold - econml.ipynb, analysisnotebook - ACIC, acictreatment, acicresponse

Its SKILL.md is about 360 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Jupyter notebooks. It works with Jupyter. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Jupyter notebooks

Example prompts

  • “/writing-specs”

What it can do on your machine

Read from SKILL.md and the folder at commit a978030. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Writing Specs loads about 364 tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 131 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~364

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Netflix-Skunkworks/oci-agent at commit a978030, republished under its Apache-2.0 licence (© Netflix-Skunkworks). 131 words, ~364 tokens.

Download SKILL.mdSave it as .claude/skills/writing-specs/SKILL.md (or your agent's skills folder).
name
writing-specs
description
Invoke this skill when initiating an OCI analysis from a plan or user prompt — i.e. before any notebook is parameterized or executed. Keywords: - analysis spec, eval spec, spec.yaml - treatment, outcome, covariates, confounders - ATE, ATT, ATO, ato_threshold - econml.ipynb, analysis_notebook - ACIC, acic_treatment, acic_response

Process

  • Confirm the plan or prompt names a tabular data source (table or CSV) with a treatment column and an outcome column. If either is missing, ask the user before drafting.
  • specs are YAML files. Write them under specs/{plan}/. Create the folder if it does not exist.
  • Point analysis_notebook at an .ipynb file in notebooks/.

Validation (before saving)

  • (skip for ACIC evals) Treatment and outcome columns exist in the data source
  • covariates is non-empty and excludes the treatment and outcome columns.
  • At least one estimand toggle (estimate_ate / estimate_att / estimate_ato) is true.
  • ato_threshold is in (0, 0.5).
  • analysis_notebook exists in notebooks/.

Fields — general analyses

  • data_path, treatment, outcome
  • covariates
  • estimate_ate, estimate_att, estimate_ato
  • ato_threshold
  • seed
  • analysis_notebook

Fields — ACIC evals only

  • acic_treatment, acic_response # replace data_path / treatment / outcome
  • covariates
  • seed
  • estimate_ate, estimate_att, estimate_ato
  • ato_threshold
  • analysis_notebook: econml.ipynb

© Netflix-Skunkworks, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/writing-specs of Netflix-Skunkworks/oci-agent.

Open the folder on GitHubat commit a978030

Compare with similar skills

Writing Specs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Writing Specs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Specs this skillNetflix-Skunkworks/oci-agent144—~364Automated safety check: PassApache-2.0
Jupyter Notebookmicrosoft/ai-agents-for-beginners77k8 repos~1kAutomated safety check: PassApache-2.0
Notebook For ExperimentJetBrains/intellij-community21k—~4.4kAutomated safety check: WarnCustom licence
Jupyter To Marimoericmjl/llamabot1832 repos~475Automated safety check: PassNone
Nbreviewawdeorio/dotfiles102—~2.2kAutomated safety check: PassNone
Save Research Notebooknapjon/krisk117—~702Automated safety check: PassBSD-3-Clause

Similar skills

  • Jupyter Notebook

    microsoft/ai-agents-for-beginners

    Official

    A skill your agent uses when the user asks to create, scaffold, or edit Jupyter notebooks (.ipynb) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script…

    77k GitHub starsUsed in 8 repos~1k tokens
    Data & AnalyticsAuto-check passed
  • Notebook For Experiment

    JetBrains/intellij-community

    Official

    Create reproducible Jupyter notebooks for performance experiments.

    21k GitHub stars~4.4k tokensUpdated today
    Data & AnalyticsAuto-check: warnings
  • Jupyter To Marimo

    ericmjl/llamabot

    Convert a Jupyter notebook (.ipynb) to a marimo notebook (.py).

    183 GitHub starsUsed in 2 repos~475 tokens
    Data & AnalyticsAuto-check passed
  • Nbreview

    awdeorio/dotfiles

    This skill should be used when the user asks to "review this notebook", "nbreview", "check my notebook", or otherwise requests a Jupyter notebook review.

    102 GitHub stars~2.2k tokensUpdated 4 days ago
    Data & AnalyticsAuto-check passed
  • Convert a completed data-analysis conversation into evidence-backed, reproducible living research through the Krisk MCP server.

    117 GitHub stars~702 tokensUpdated 9 days ago
    Data & AnalyticsAuto-check passed
  • Jupyter Notebook

    microsoft/ai-agents-for-beginners

    Official

    Kasuta, kui kasutaja palub luua, üles ehitada või redigeerida Jupyteri märkmikke (.ipynb) katsetuste, uurimiste või juhendite jaoks; eelista kaasasolevaid malle ja käivita abiskript newnotebook.py…

    77k GitHub stars~1.2k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

More from Netflix-Skunkworks/oci-agent

  • Changing Notebooks

    Netflix-Skunkworks/oci-agent

    Invoke this skill when making any modification to a notebook (.ipynb) in the OCI agent.

    144 GitHub stars~484 tokensUpdated 1 mo ago
    Auto-check passed
  • Suggesting Remedies

    Netflix-Skunkworks/oci-agent

    Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed.

    144 GitHub stars~916 tokensUpdated 1 mo ago
    Auto-check passed
  • Writing Reports

    Netflix-Skunkworks/oci-agent

    Invoke this skill when writing oci-report.md from an executed OCI analysis.

    144 GitHub stars~832 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Writing Specs

What does Writing Specs do?

Invoke this skill when initiating an OCI analysis from a plan or user prompt — i.e. Writing Specs is an agent skill from Netflix-Skunkworks/oci-agent.e.

When should I use Writing Specs?

Writing Specs fits situations like: tasks that involve Jupyter notebooks.

How do I install Writing Specs in Claude Code?

Run `npx skills add Netflix-Skunkworks/oci-agent --skill writing-specs -a claude-code`. Or copy the skill folder (skills/writing-specs in Netflix-Skunkworks/oci-agent) into .claude/skills/writing-specs in your project. Claude Code loads it when a task matches its description.

How do I install Writing Specs in Codex?

Run `npx skills add Netflix-Skunkworks/oci-agent --skill writing-specs -a codex`. Or copy the skill folder (skills/writing-specs in Netflix-Skunkworks/oci-agent) into .agents/skills/writing-specs in your project. Codex loads it when a task matches its description.

Can I use Writing Specs in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Netflix-Skunkworks/oci-agent --skill writing-specs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-specs, .gemini/skills/writing-specs, .github/skills/writing-specs and .opencode/skills/writing-specs in your project.

What does Writing Specs need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Specs is instructions for the agent only.

Does Writing Specs access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Writing Specs safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Writing Specs use?

Writing Specs is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Writing Specs use?

About 364 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Writing Specs?

Skills that share tags, products or a category with Writing Specs: Jupyter Notebook (microsoft/ai-agents-for-beginners, 77k stars), Notebook For Experiment (JetBrains/intellij-community, 21k stars), Jupyter To Marimo (ericmjl/llamabot, 183 stars) and Nbreview (awdeorio/dotfiles, 102 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Specs?

Netflix-Skunkworks (a GitHub organization) maintains it in Netflix-Skunkworks/oci-agent, which has 144 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on August 15, 2026.

Source: Netflix-Skunkworks/oci-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.