openspeccer — Claude Code skill: dashboard and setup
openspeccer opens a read-only local dashboard for an OpenSpec repository and reports active changes, artifacts, and tasks. Useful when you need project status.
Apache-2.0 ★ 173 updated 2026-10-24
npx skills add sammcj/agentic-coding --skill openspeccer -a claude-codeWhat openspeccer does
openspeccer serves a read-only web dashboard for repositories that contain an openspec/ directory. It can take a repository path or search upward from the current directory. For a status request, the skill runs serve.py <repo> --summary; for one change, it uses --change <slug>. A full snapshot can be written with --json and read from a file.
The dashboard runs as a background process through serve.py <repo>, and the skill returns its URL. Use --no-open in a headless or remote session, or when another server for the repository is already running. File changes appear on the page without a manual refresh, and active changes from git worktrees are aggregated. It uses Python’s standard library, so no package installation is needed. Without the OpenSpec CLI, the Commands page stays empty; the CLI supplies data for Schemas and Commands.
What it helps with
- open a dashboard for a repository with
openspec/ - see which OpenSpec changes are in flight
- inspect one change with
--change <slug> - review a change’s artifacts and tasks
- export the project snapshot as JSON
Example prompts for the agent
- Open the OpenSpec dashboard for this repository and give me its URL.
- Show which OpenSpec changes are currently in flight using the summary.
- Inspect the artifacts and tasks for the
my-changechange.
How to install openspeccer
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill openspeccer -a claude-code2Manually: put the files in place
~/.claude/skills/openspeccer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/openspeccer/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill openspeccer -a codex2Manually: put the files in place
.agents/skills/openspeccer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill openspeccer -a cursor2Manually: put the files in place
.cursor/skills/openspeccer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sammcj/agentic-coding Skills/openspeccer/SKILL.md2Manually: put the files in place
.github/skills/openspeccer/SKILL.md1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill openspeccer -a gemini-cli2Platform CLI
gemini skills install https://github.com/sammcj/agentic-coding --path Skills/openspeccerManually: put the files in place
.devin/skills/openspeccer/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about openspeccer
How do I install openspeccer in Claude Code?
Run npx skills add sammcj/agentic-coding --skill openspeccer -a claude-code, then check ~/.claude/skills/openspeccer/SKILL.md.
What does openspeccer do?
It serves a local read-only OpenSpec dashboard. The skill reports active changes, artifacts, and tasks, and can return either a summary or a JSON snapshot.
Do I need the OpenSpec CLI?
No. The dashboard can run without it, but the CLI provides data for the Schemas and Commands pages, so Commands is empty without the CLI.
Source text
SKILL.md · Apache-2.0
---
name: openspeccer
description: 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.
metadata:
version: 2026-10-12
---
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.
© sammcj · Apache-2.0 · sammcj/agentic-coding