visualise
Skill34 starsChanged 51 days agoMITView on GitHub
Open the accelerator meta visualiser. Launches the companion-window server in the background and returns a URL. Subcommands stop and status manage the running server.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- sidp-2003/Claude_Skillstheir own version, first seen Oct 13, 2026
- SHYXIN/skillstheir own version, first seen Oct 11, 2026
- limyuquan/plannertheir own version, first seen Oct 9, 2026
- bentossell/visualisetheir own version, first seen Mar 12, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- bentossell/visualise★ 478same name
- SHYXIN/skills★ 6same name
- limyuquan/planner★ 1same name
- sidp-2003/Claude_Skills★ 0same 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 repository38 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- hooks/CLAUDE.mdCLAUDE.md
- tasks/CLAUDE.mdCLAUDE.md
- clean-commentsSkill
- raise-prSkill
- configureSkill
- initSkill
- migrateSkill
- pathsSkill
- create-adrSkill
- extract-adrsSkill
- review-adrSkill
- analyse-design-gapsSkill
- inventory-designSkill
- describe-prSkill
- respond-to-prSkill
- review-prSkill
- create-noteSkill
- create-planSkill
- implement-planSkill
- review-planSkill
- stress-test-planSkill
- validate-planSkill
- conduct-spikeSkill
- research-codebaseSkill
- research-issueSkill
- research-topicSkill
- commitSkill
- create-work-itemSkill
- extract-work-itemsSkill
- list-work-itemsSkill
- refine-work-itemSkill
- rekey-work-itemsSkill
- review-work-itemSkill
- stress-test-work-itemSkill
- sync-work-items-recoverySkill
- sync-work-itemsSkill
- update-work-itemSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
0
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
- Very specific: line 68
Read the hint field and relay the remediation.
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
Visualise Meta Directory
!accelerator config context --skill visualise --fail-safe
Plans directory: !accelerator config path plans --fail-safe
Codebase research directory: !accelerator config path research_codebase --fail-safe
Decisions directory: !accelerator config path decisions --fail-safe
PR descriptions directory: !accelerator config path prs --fail-safe
Validations directory: !accelerator config path validations --fail-safe
Review plans directory: !accelerator config path review_plans --fail-safe
Review PRs directory: !accelerator config path review_prs --fail-safe
Templates directory: !accelerator config path templates --fail-safe
Work directory: !accelerator config path work --fail-safe
Work reviews directory: !accelerator config path review_work --fail-safe
Notes directory: !accelerator config path notes --fail-safe
Design gaps directory: !accelerator config path research_design_gaps --fail-safe
Design inventories directory: !accelerator config path research_design_inventories --fail-safe
Tmp directory: !accelerator config path tmp --fail-safe
Visualiser: !accelerator visualiser --owner-pid $PPID ${ARGUMENTS:-start}
Server lifecycle
<!--
Context for Claude only — do not relay to the user verbatim:
The visualiser server is a locally-backgrounded Rust process. It
binds a random high port on 127.0.0.1 and exits automatically when
idle for 8 hours, when the process that launched the server
exits, or when `/accelerator:visualise stop` is invoked. Re-running
`/accelerator:visualise` while the server is up reuses the
existing instance. Note: "the process that launched the server"
means different things by invocation mode — for the slash command
it's the Claude Code harness; for the CLI wrapper it's the
terminal shell. Don't assume Claude Code specifically.
`accelerator visualiser` routes a single argument: empty/`start`
launches the server, `stop` terminates it, `status` probes its
lifecycle files. Output shape varies by subcommand — read it
carefully before relaying to the user.
-->The user's argument selects the action. Interpret the
**Visualiser**: line above according to which subcommand was
invoked:
No argument (start) — the line is either:
**Visualiser URL**: <url>— server is running, relay the URL to the user. Tell them:- Open the URL in a browser to use the visualiser UI.
- Re-running
/accelerator:visualisereturns the same URL while the server is alive. - The server auto-exits after the idle window (8 hours by
default, configurable via
visualiser.idle_timeout/ACCELERATOR_VISUALISER_IDLE_TIMEOUT, and disable-able withnever/0), or when the process that launched it exits. To stop it explicitly, run/accelerator:visualise stop.
- A JSON
{"error":...}object — the server isn't running. Read thehintfield and relay the remediation.
stop — the line is a JSON object describing the result:
{"status":"stopped"}(optionally"forced":true) — the server has been terminated.{"status":"not_running"}— there was no server to stop.{"status":"refused",...}or{"status":"failed",...}— relay the reason/error to the user.
status — the line is a JSON object:
{"status":"running","url":...,"pid":...} when the server is up, or
{"status":"stopped"} when it is not (never started, cleanly stopped,
crashed, or leftover state from a recycled PID). Relay the status (and
URL/PID when present) to the user.
{"error":"unknown subcommand",...} — the user passed an
unrecognised argument. Tell them the valid subcommands are
stop and status (no argument starts the server).
Overrides
By default the plugin downloads a verified per-arch binary from GitHub Releases on first use. Two overrides exist for dev, air-gapped, or pinned-binary workflows:
- Environment variable (one-shot, shell-scoped):
ACCELERATOR_VISUALISER_BIN=<path>. Bypasses SHA-256 verification; use for local dev builds. Config key (persistent, per-project):
--- visualiser: binary: <absolute or project-relative path> ---in
.accelerator/config.md(team-committed) or.accelerator/config.local.md(personal, gitignored). Relative paths resolve against the project root.The team-committed form is trusted on par with the rest of the repo — anyone approving a PR that changes it should treat the value as code, not data.
The release-binary mirror URL can be overridden via
ACCELERATOR_VISUALISER_RELEASES_URL=<base-url> (air-gapped
or proxy-hosted mirrors).
The idle auto-shutdown window is configurable via the
visualiser.idle_timeout config key (a humantime duration like
"8h", "30m", "1h30m"; never/0 disables it), with the
ACCELERATOR_VISUALISER_IDLE_TIMEOUT environment variable as a
one-shot, shell-scoped override (precedence:
env > visualiser.idle_timeout > 8h default).
The detail-page Open in editor action is configured via the
visualiser.editor config key (with ACCELERATOR_VISUALISER_EDITOR
as a one-shot env override; precedence env > config). When unset the
button renders disabled. The value is either a preset key or a
custom URL template:
- VS Code family preset keys —
vscode,vscode-insiders,vscodium,cursor,windsurf— each opening{scheme}://file{abs}(a single slash before the absolute path). - JetBrains preset keys —
idea,web-storm,pycharm,php-storm,goland,rubymine,clion,rd,rustrover— each openingjetbrains://{tag}/navigate/reference?project={project}&path={rel}. The{project}name comes fromvisualiser.editor_project(env overrideACCELERATOR_VISUALISER_EDITOR_PROJECT); when unset it defaults to the project directory's basename. Ignored by non-JetBrains presets. - Custom template — for editors without a preset (e.g. Zed, Sublime),
set
visualiser.editorto a URL template. It must contain at least one{abs}(percent-encoded absolute path) or{rel}(percent-encoded project-relative path) placeholder — a value that cannot reference the file is treated as unresolvable and the button renders disabled. Example:zed://file{abs}. As a safety guard a resolved link whose scheme isjavascript,data,vbscript,blob, orfileis rejected (disabled); any other editor scheme is allowed.
---
visualiser:
editor: cursor
# editor: web-storm
# editor_project: myrepo # JetBrains project name override
# editor: "zed://file{abs}" # custom-template escape hatch
---To run the visualiser from a terminal, link the accelerator CLI onto your
$PATH and invoke accelerator visualiser [stop | status]. The link is a
two-hop chain so it survives plugin upgrades — see Terminal
Invocation
for the setup steps.
!accelerator config instructions visualise --fail-safe
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
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.

