Build a corpus that can see the change, and read what the oracles and sweeps report without over-reading it.

Custom licenceAuto-check passed

Install Sweeps And Oracles

skills CLI
$ npx skills add stylelint-stylistic/stylelint-stylistic --skill sweeps-and-oracles -a claude-code

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

GitHub CLI
$ gh skill install stylelint-stylistic/stylelint-stylistic sweeps-and-oracles --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/stylelint-stylistic/stylelint-stylistic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/sweeps-and-oracles .claude/skills/sweeps-and-oracles && 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
sweeps-and-oracles
GitHub stars
106
Token cost
~4.4k tokens
SKILL.md length
2,971 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
Custom licence

At a glance

Build a corpus that can see the change, and read what the oracles and sweeps report without over-reading it.

  • Writing a sweep
  • SKILL.md covers What the instruments cannot see, A clean run over a shape no…, Every spelling, and cross the… and Reading the output, plus 3 more sections
  • Calls make and git
  • Running make oracles

What it does

Sweeps And Oracles is an agent skill from stylelint-stylistic/stylelint-stylistic. Build a corpus that can see the change, and read what the oracles and sweeps report without over-reading it. Use when writing a sweep, running make oracles or make sweep, quoting a row count in a spec, commit body or PR, or concluding that a branch moved nothing.

Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A collection of stylistic rules for Stylelintin in a form of a plugin.

When your agent uses it

  • Writing a sweep
  • Running make oracles
  • Quoting a row count in a spec
  • Concluding that a branch moved nothing

Example prompts

  • “/sweeps-and-oracles”

What it can do on your machine

Read from SKILL.md and the folder at commit e74a1ee. 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

    Shell commands in SKILL.md call:

    • make
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Sweeps And Oracles loads about 4.4k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 2,971 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~4.4k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,971 words (~4,447 tokens).

“The corpus is the oracle. Everything below is a way a run came back clean over a defect that was standing right there.”

— opening of SKILL.md by stylelint-stylistic, Custom licence
name
sweeps-and-oracles

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/sweeps-and-oracles of stylelint-stylistic/stylelint-stylistic.

Open the folder on GitHubat commit e74a1ee

Compare with similar skills

Sweeps And Oracles 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.

Sweeps And Oracles compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sweeps And Oracles this skillstylelint-stylistic/stylelint-stylistic106—~4.4kAutomated safety check: PassCustom licence
Oracleopenclaw/openclaw392k1 repos~1.2kAutomated safety check: NotesMIT
Corpus Sweepnubjs/nub4.4k—~2.4kAutomated safety check: PassMIT
Tests Query Corpusnetdata/netdata81k—~5.3kAutomated safety check: PassGPL-3.0
What If OracleK-Dense-AI/scientific-agent-skills48k1 repos~2.9kAutomated safety check: PassCC-BY-NC-4.0
Oraclesteipete/agent-scripts7.3k1 repos~2.1kAutomated safety check: NotesMIT

Similar skills

  • Oracle

    openclaw/openclaw

    Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

    392k GitHub starsUsed in 1 repo~1.2k tokens
    DevelopmentAuto-check: notes
  • Corpus Sweep

    nubjs/nub

    Run a large sharded measurement sweep over npm packages (the build-jail catalog probe, or any harness that installs thousands of package-versions and records a verdict per run).

    4.4k GitHub stars~2.4k tokensUpdated yesterday
    SecurityAuto-check passed
  • Tests Query Corpus

    netdata/netdata

    Run, extend or review the Netdata query contract corpus (tests/query-corpus), its fixtures, independent oracles, byte pins and harness.

    81k GitHub stars~5.3k tokensUpdated today
    DevOps & CloudAuto-check passed
  • What If Oracle

    K-Dense-AI/scientific-agent-skills

    Supports structured what-if scenario analysis for research planning, experimental contingencies, and scientific project decisions.

    48k GitHub starsUsed in 1 repo~2.9k tokens
    Research & ScienceAuto-check passed
  • Oracle

    steipete/agent-scripts

    Oracle second-model review: bundle prompts/files, debug, refactor, design.

    7.3k GitHub starsUsed in 1 repo~2.1k tokens
    DevOps & CloudAuto-check: notes
  • Brooks Sweep

    sickn33/agentic-awesome-skills

    Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase.

    47k GitHub starsUsed in 1 repo~668 tokens
    DevelopmentAuto-check passed

More from stylelint-stylistic/stylelint-stylistic

  • Base Comparison

    stylelint-stylistic/stylelint-stylistic

    Measure a branch against the commit it stands on — extract the base instead of flipping the working tree, pick the base by hash, and prove a new test case red on it.

    106 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Engine Probes

    stylelint-stylistic/stylelint-stylistic

    Ask a real engine what a stylesheet means instead of reasoning about tokens — the Less compiler, lightningcss, dart-sass, and a custom syntax's own parser.

    106 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • History Rewriting

    stylelint-stylistic/stylelint-stylistic

    Fold fixups into a branch without losing a message, a marker or somebody else's branch — the amend!

    106 GitHub stars~826 tokensUpdated today
    Auto-check passed
  • Outward Prose

    stylelint-stylistic/stylelint-stylistic

    Write a commit body, a changelog entry, a PR body, an issue comment or a code comment so that no sentence in it is a claim nobody ran.

    106 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Stacks And Issues

    stylelint-stylistic/stylelint-stylistic

    The GitHub mechanics of this repository — building and re-rooting a gh stack, why CI runs on the bottom PR alone, which hash is stable after a merge, and how an umbrella issue closes.

    106 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Questions about Sweeps And Oracles

What does Sweeps And Oracles do?

Build a corpus that can see the change, and read what the oracles and sweeps report without over-reading it. Sweeps And Oracles is an agent skill from stylelint-stylistic/stylelint-stylistic. Build a corpus that can see the change, and read what the oracles and sweeps report without over-reading it.

When should I use Sweeps And Oracles?

Sweeps And Oracles fits situations like: writing a sweep; running make oracles; quoting a row count in a spec; concluding that a branch moved nothing.

How do I install Sweeps And Oracles in Claude Code?

Run `npx skills add stylelint-stylistic/stylelint-stylistic --skill sweeps-and-oracles -a claude-code`. Or copy the skill folder (.agents/skills/sweeps-and-oracles in stylelint-stylistic/stylelint-stylistic) into .claude/skills/sweeps-and-oracles in your project. Claude Code loads it when a task matches its description.

How do I install Sweeps And Oracles in Codex?

Run `npx skills add stylelint-stylistic/stylelint-stylistic --skill sweeps-and-oracles -a codex`. Or copy the skill folder (.agents/skills/sweeps-and-oracles in stylelint-stylistic/stylelint-stylistic) into .agents/skills/sweeps-and-oracles in your project. Codex loads it when a task matches its description.

Can I use Sweeps And Oracles 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 stylelint-stylistic/stylelint-stylistic --skill sweeps-and-oracles -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sweeps-and-oracles, .gemini/skills/sweeps-and-oracles, .github/skills/sweeps-and-oracles and .opencode/skills/sweeps-and-oracles in your project.

What does Sweeps And Oracles need to run?

Going by SKILL.md and its folder, Sweeps And Oracles needs the command-line tools its instructions call (make and git).

Does Sweeps And Oracles access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Sweeps And Oracles 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 Sweeps And Oracles use?

Sweeps And Oracles has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Sweeps And Oracles use?

About 4.4k tokens (SKILL.md is roughly 18k 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 Sweeps And Oracles?

Skills that share tags, products or a category with Sweeps And Oracles: Oracle (openclaw/openclaw, 392k stars), Corpus Sweep (nubjs/nub, 4.4k stars), Tests Query Corpus (netdata/netdata, 81k stars) and What If Oracle (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sweeps And Oracles?

stylelint-stylistic (a GitHub organization) maintains it in stylelint-stylistic/stylelint-stylistic, which has 106 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 5, 2026.

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