ac-roadmap
Skill1 starsChanged 49 days agoMITView on GitHub
Run Auto-Claude AI-powered roadmap generation for any project directory. Analyzes project structure, target audience, and existing specs to produce a strategic feature roadmap. Use when planning milestones, phases, or strategic direction for a project.
In this repository113 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ac-ideateSkill
- ac-listSkill
- agentbridge-mcpSkill
- almanacSkill
- almquist-shellSkill
- ansible-fleetSkill
- apfsSkill
- apple-siliconSkill
- arena-actorsSkill
- asustor-nasSkill
- a-teamSkill
- atem-miniSkill
- at-tuiSkill
- autoresearchSkill
- babysitSkill
- bonzibuddySkill
- bop-brainstormSkill
- bop-catalogSkill
- bop-onSkill
- bop-teamSkill
- bop-workflowSkill
- bsd-portabilitySkill
- code-refactoringSkill
- codex-personasSkill
- context-graphSkill
- councilSkill
- datadog-backupSkill
- dd-tagsSkill
- delegateSkill
- deming-pdsaSkill
- deterministic-replaySkill
- dispatch-nuSkill
- durable-commitSkill
- elixir-gastown-opsSkill
- ergo-ircSkill
- esp32-tang-bridgeSkill
- fleet-evalSkill
- fleet-ircSkill
- freebsd-build-vmSkill
- freebsd-piSkill
- freebsdSkill
- ganttSkill
- gastown-opsSkill
- gastown-slingSkill
- gh-authSkill
- gitea-releaseSkill
- gitea-runnerSkill
- henshuSkill
- irclaw-cluster-opsSkill
- irclaw-research-teamSkill
- irc-taskSkill
- jail-factorySkill
- jjSkill
- jobcard-systemSkill
- kubernetesSkill
- leptosSkill
- loreSkill
- lower-bound-reviewSkill
- macvlan-netSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 17
Always set PYTHONPATH to the backend root:
- Distinctive: line 66
Run in this order — each step feeds context into the next:
- Distinctive: line 95
Run roadmap before ideation so ideation can incorporate strategic milestones as context.
≈ “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.
Files
ac-roadmap — Auto-Claude Roadmap Runner
Runs the Auto-Claude roadmap pipeline against a project directory and writes
results to <project>/.auto-claude/roadmap/.
Binary location
/Applications/Auto-Claude.app/Contents/Resources/backend/runners/roadmap_runner.pyAlways set PYTHONPATH to the backend root:
PYTHONPATH=/Applications/Auto-Claude.app/Contents/Resources/backendBasic usage
# Generate roadmap for current directory
PYTHONPATH=/Applications/Auto-Claude.app/Contents/Resources/backend \
python3 /Applications/Auto-Claude.app/Contents/Resources/backend/runners/roadmap_runner.py \
--project /path/to/project
# With competitor analysis and high thinking
PYTHONPATH=/Applications/Auto-Claude.app/Contents/Resources/backend \
python3 /Applications/Auto-Claude.app/Contents/Resources/backend/runners/roadmap_runner.py \
--project /path/to/project \
--thinking-level high \
--competitor-analysis \
--refreshAll flags
| Flag | Default | Description |
--project PATH | cwd | Project directory to analyze |
--output PATH | <project>/.auto-claude/roadmap | Where to write results |
--model | sonnet | haiku, sonnet, opus, or full model ID |
--thinking-level | medium | low / medium / high |
--refresh | false | Force regenerate even if roadmap exists |
--competitor-analysis | false | Enable competitor analysis phase |
--refresh-competitor-analysis | false | Force refresh competitor analysis (requires --competitor-analysis) |
Open a Zellij tab for roadmap generation
zellij --session $ZELLIJ_SESSION_NAME action new-tab --name "roadmap" \
-- sh -c 'cd /path/to/project && \
PYTHONPATH=/Applications/Auto-Claude.app/Contents/Resources/backend \
python3 /Applications/Auto-Claude.app/Contents/Resources/backend/runners/roadmap_runner.py \
--project . --thinking-level high --refresh; exec $SHELL'$ZELLIJ_SESSION_NAME is set automatically inside any Zellij session. If running outside, replace with the session name from zellij list-sessions.
Recommended sequence for a new project
Run in this order — each step feeds context into the next:
# 1. Roadmap first (strategic framing)
ac-roadmap --project . --thinking-level high --refresh
# 2. Ideation second (reads roadmap context automatically)
ac-ideate --project . --thinking-level high --refresh
# 3. Promote ideas to specs
# cp .auto-claude/ideation/<idea>.md .auto-claude/specs/<NNN>-<slug>/spec.md
# 4. Dispatch specs
# ./dispatch.nu run --wave N --yesProjects
| Project | Path |
| dub (EFI bootloader) | $HOME/efi |
| bop (jobcard system) | $HOME/bop |
| zam (unikernel VM reader) | $HOME/zam |
Notes
- Reads
PLAN.md,CLAUDE.md, and existing specs for context automatically. --competitor-analysisdoes a web search phase — useful for positioning but slower.- Does not require an API key — uses Auto-Claude's OAuth session (Claude Code subscription).
- Run roadmap before ideation so ideation can incorporate strategic milestones as context.
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.