agentleFS
open-science-pillarsopen-science-pillars/core/skills/start/SKILL.md

start

Skill0 starsChanged 53 days agoApache-2.0View on GitHub

Session orientation: list installed science plugins, connector status, local config, available workflow skills, one suggested next step.

130 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-audio and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    Also in 13 projects that use this

  • CoralGameSkill

    team-audio

    Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.

    Also in 13 projects that use this

  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 11 projects that use this

  • +5 more from CoralGame
  • +3 more from lilangMax

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 117 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Local config summary: If a project local config exists (for example ocean-science.local.md), summarize the filled blocks (data paths, …

    line 38
  2. Distinctive:

    Read-only: start never loads data, writes files, or asks questions.

    line 56
  3. Distinctive:

    Never invent status: check what is actually loaded and configured.

    line 57
  4. Distinctive:

    Never list knowledge skills in the menu of things to invoke.

    line 65
  5. Distinctive:

    Never suggest more than one next step.

    line 66
  6. Distinctive:

    Never trigger a download, a file write, or a connector call that costs more than a status check.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 117 edited versions of this file we could read. “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

start

Orient the scientist in one screen: what is installed, what is connected, what is configured, and what to do next. Works identically invoked by slash command or by asking conversationally ("what science tools do I have here?").

Behavior

Produce exactly one screen with these five parts, in order:

  1. Installed OSP plugins and their knowledge. Which Open Science Pillars plugins are present (core; ocean-science and other domain plugins; the provider bundle plugin they depend on, such as nasa-daac-knowledge), with one clause each on what they cover, read from the installer's record (claude plugin list --json where a shell exists; see consult-knowledge for how bundle roots are found from it). One line per plugin: version, the date it was installed or last updated, and its knowledge in numbers: concepts by status (stable, draft, deprecated) and how many stable concepts are past their stale_after date today, counted from the concept frontmatter under each bundle root. A plugin whose record carries errors is reported as disabled with the error's own words. All of this is read from disk; nothing is fetched, and no comparison with the catalog is made. The part closes with one line: installs stay at the release they were installed from, and claude plugin update <name>@open-science-pillars moves one.
  2. Connector status. Whether the Earthdata MCP connector is configured and reachable this session; when it is not, say so plainly and note that discovery falls back to knowledge-based search (discover-data names the fallback when it fires). On surfaces with per-session connectors, "not configured this session" is a normal state, not an error.
  3. Local config summary. If a project local config exists (for example ocean-science.local.md), summarize the filled blocks (data paths, compute, region defaults) in a line or two; if none exists, say none is configured and which template creates one.
  4. Available workflow skills, grouped by plugin. Core's workflows (discover-data, report), then each installed domain plugin's workflows. Knowledge skills are not listed; they load themselves as background expertise.
  5. One suggested next step. Exactly one, chosen from the state above: a plugin disabled by a dependency error suggests the install command the error names; no data touched yet suggests discover-data; an analysis in progress suggests finishing it and running report; a domain plugin installed but unconfigured suggests filling its local config.

Rules

  • One screen. No scrolling walls, no exhaustive option lists.
  • Read-only: start never loads data, writes files, or asks questions.
  • Never invent status: check what is actually loaded and configured; when something cannot be checked from this surface (the installer's record on a surface without a shell), say so rather than guessing.
  • Knowledge counts come from the files under the bundle roots, never from an index line or a remembered figure.

Must NOT

  • Never list knowledge skills in the menu of things to invoke.
  • Never suggest more than one next step.
  • Never trigger a download, a file write, or a connector call that costs more than a status check.

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.