agentleFS
LightconeResearchLightconeResearch/agent-skills/skills/astra/SKILL.md

astra

Skill2 starsChanged 18 days agoBSD-3-ClauseView on GitHub

ASTRA (astra.yaml) support: what the format is, and how to drive the `astra` CLI. Invoke whenever reading, writing, validating, or restructuring an astra.yaml spec, working with universes or evidence, or when the user asks about ASTRA.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. orlando-vazquez-career/astra-protocol★ 2same name
    2. Lesani/skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Always invoke the astra CLI through uv's pinned runner, exactly as written everywhere in this document:

    line 24
  2. Very specific:

    Never run a bare astra found on PATH — its version is unknown and may not match what this skill assumes.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ASTRA

What ASTRA is

An ASTRA analysis (astra.yaml) is an intermediate layer of abstraction between code and paper: a machine-readable record of the inputs, outputs, and every consequential methodological decision — with its reasoning — at the level needed to make the scientific claims verifiable and reproducible. The goal is to make the full decision space explicit, so that alternative defensible choices can be systematically explored (as universes) rather than silently baked in. The structure is self-similar: a top-level analysis and a nested sub-analysis have exactly the same shape.

Running astra

Always invoke the astra CLI through uv's pinned runner, exactly as written everywhere in this document:

uvx astra-tools@0.2.18 <command>

Never run a bare astra found on PATH — its version is unknown and may not match what this skill assumes. (uvx caches the environment, so repeated calls are fast. If uvx is missing, ask the user to install uv: https://docs.astral.sh/uv/getting-started/installation/ — never install it yourself.)

Orient before authoring

The CLI serves everything this skill deliberately does not repeat:

  • uvx astra-tools@0.2.18 guide — the complete agent briefing on the format: core concepts, worked examples, the authoring workflow and judgment (what deserves to be a decision, when to split a sub-analysis, universes, evidence), and the format rules. Read it before any substantial authoring or restructuring work.
  • uvx astra-tools@0.2.18 spec — the field-level ground truth, served in sync with the schema the validator enforces: no argument prints the concept map; uvx astra-tools@0.2.18 spec <term> prints one concept in full (the mode to reach for while editing); uvx astra-tools@0.2.18 spec --full prints the entire reference (long).

Re-validate after every change: uvx astra-tools@0.2.18 validate with no argument checks every spec and universe file under the current directory.

Citations, quotes, and supporting evidence

Claims in ASTRA are backed by verifiable evidence: prior_insights (imported claims that motivate decisions) and findings (claims the analysis produces) both carry evidence entries — a doi with a verbatim quote for literature, or an artifact naming an output. The paper utilities manage the literature side end to end:

  1. Cache the source at authoring time — run uvx astra-tools@0.2.18 paper add <doi> the moment you cite a paper (pass --version N to pin an arXiv revision). The PDF lands in the project's paper cache, so the citation stays checkable without asking the reader to fetch anything.
  2. Pull exact quotes from the cached PDF — uvx astra-tools@0.2.18 paper path <doi> prints the cached file's path so you can open it and copy the supporting text verbatim into quote.exact; add prefix/suffix (~20–100 chars on either side) when the exact string occurs more than once. Write every quote as if a machine will look for it — one will.
  3. Verify before you're done — uvx astra-tools@0.2.18 paper verify-quotes <doi> checks one paper's quotes; uvx astra-tools@0.2.18 validate astra.yaml --verify-evidence checks every quote in the spec. A quote that doesn't match the PDF fails validation.

uvx astra-tools@0.2.18 paper list shows the cache; uvx astra-tools@0.2.18 paper show <doi> prints a cached paper's metadata. Artifact-backed evidence (typical for findings whose outputs aren't materialized yet) is reported as SKIPPED, not failed.

CLI reference

The astra CLI validates and inspects; it never executes recipes. The separation is deliberate — the spec stays stable while agents and execution layers evolve, and the choice of runner stays yours — so don't encode runner-specific behavior into the spec.

uvx astra-tools@0.2.18 init [DIRECTORY]                          # Scaffold an empty analysis
uvx astra-tools@0.2.18 validate [FILE]                           # Validate the whole project, or one file (run after every change)
uvx astra-tools@0.2.18 validate astra.yaml --verify-evidence     # + verify insight quotes against PDFs
uvx astra-tools@0.2.18 guide                                     # Full agent briefing on the format (read before authoring)
uvx astra-tools@0.2.18 spec [TERM|--full]                        # Schema reference (see above)
uvx astra-tools@0.2.18 info [--decisions|--inputs|--outputs]     # Analysis summary / element details
uvx astra-tools@0.2.18 universe generate -n NAME [-d "desc"]     # Generate universe from defaults
uvx astra-tools@0.2.18 universe check universes/x.yaml           # Check universe constraints
uvx astra-tools@0.2.18 paper add DOI [--version N]               # Cache a paper (resolved from its DOI)
uvx astra-tools@0.2.18 paper list                                # List cached papers
uvx astra-tools@0.2.18 paper show DOI                            # Show metadata for a cached paper
uvx astra-tools@0.2.18 paper path DOI [--version N]              # Print the cached PDF's path
uvx astra-tools@0.2.18 paper verify-quotes DOI                   # Batch-verify quotes; reads {"quotes":[...]} JSON from stdin

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.