agentleFS
sammcjsammcj/agentic-coding/Skills/openspeccer/SKILL.md

openspeccer

Skill167 starsChanged 10 days agoApache-2.0View on GitHub

Use when the user wants to open or browse an OpenSpec project's dashboard, or asks which OpenSpec changes are in flight or how far along one is. Do NOT use for creating, editing, verifying or archiving changes; use the OpenSpec workflow skills for those.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Distinctive:

    Create a task per step below, each with its completion criterion, then work through them.

    line 12
  2. Very specific:

    If the user wants the dashboard, start serve.py <repo> as a background process.

    line 15
  3. Very specific:

    Always give the user the URL.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

openspeccer is a read-only local web dashboard for any repository holding an openspec/ directory. It is stdlib Python and needs no install. Run <this-skill-dir>/scripts/serve.py --help for every option.

Workflow

  1. Create a task per step below, each with its completion criterion, then work through them.
  2. Find the repo: pass the user's repo path, or omit it and the script searches upward from the current directory for openspec/.
  3. For a status question ("what's in flight?"), run serve.py <repo> --summary and answer from its output. For one change's artifacts and tasks, use --change <slug>. --json prints the whole snapshot; send it to a file and read only what you need. Done once you have answered, with no server started.
  4. If the user wants the dashboard, start serve.py <repo> as a background process. Done when a line containing serving <name> at <url> appears, or the process exits; on exit, report its stderr to the user.
  5. Always give the user the URL. Pass --no-open in headless or remote sessions, and when re-running against a server that is already up.
  6. To stop it, end the background process you started, using the PID or task handle you captured at launch.

Gotchas

  • Re-running for the same repo reuses the running server and prints already serving, so step 4 is safe to repeat.
  • A server you did not start (no handle from this session) belongs to the user. Leave it running.
  • The OpenSpec CLI is optional and only feeds the Schemas and Commands pages. Without it, only project schemas show and Commands is empty. For a CLI outside PATH, set OPENSPECCER_OPENSPEC_BIN.
  • Active changes from every git worktree are aggregated by default.
  • The page updates as files change, so there is nothing to refresh after editing artifacts.

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.