ac-ideate
Skill1 starsChanged 50 days agoMITView on GitHub
Run Auto-Claude AI-powered ideation for any project directory. Generates low-hanging fruit, high-value features, and UI/UX ideas using the Auto-Claude backend. Use when brainstorming new specs, features, or architectural directions for a project.
In this repository113 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ac-listSkill
- ac-roadmapSkill
- 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
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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:
≈ “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-ideate — Auto-Claude Ideation Runner
Runs the Auto-Claude ideation pipeline against a project directory and writes
spec ideas to <project>/.auto-claude/ideation/.
Binary location
/Applications/Auto-Claude.app/Contents/Resources/backend/runners/ideation_runner.pyAlways set PYTHONPATH to the backend root:
PYTHONPATH=/Applications/Auto-Claude.app/Contents/Resources/backendBasic usage
# Ideate on current directory
PYTHONPATH=/Applications/Auto-Claude.app/Contents/Resources/backend \
python3 /Applications/Auto-Claude.app/Contents/Resources/backend/runners/ideation_runner.py \
--project /path/to/project
# With options
PYTHONPATH=/Applications/Auto-Claude.app/Contents/Resources/backend \
python3 /Applications/Auto-Claude.app/Contents/Resources/backend/runners/ideation_runner.py \
--project /path/to/project \
--types low_hanging_fruit,high_value_features \
--thinking-level high \
--max-ideas 8 \
--refreshAll flags
| Flag | Default | Description |
--project PATH | cwd | Project directory to analyze |
--output PATH | <project>/.auto-claude/ideation | Where to write results |
--types LIST | all | Comma-separated: code_improvements, ui_ux_improvements, documentation_gaps, security_hardening, performance_optimizations, code_quality |
--thinking-level | medium | low / medium / high |
--max-ideas N | 5 | Max ideas per type |
--model | sonnet | haiku, sonnet, opus, or full model ID |
--refresh | false | Force regenerate even if results exist |
--append | false | Add to existing session instead of replacing |
--no-roadmap | false | Skip roadmap context |
--no-kanban | false | Skip kanban context |
--fast-mode | false | Faster Opus 4.6 output |
Open a Zellij tab for ideation
# New tab — runs ideation then drops to shell
zellij --session $ZELLIJ_SESSION_NAME action new-tab --name "ideation" \
-- sh -c 'cd /path/to/project && \
PYTHONPATH=/Applications/Auto-Claude.app/Contents/Resources/backend \
python3 /Applications/Auto-Claude.app/Contents/Resources/backend/runners/ideation_runner.py \
--project . --thinking-level high --max-ideas 8 --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.
Typical workflow
- New project — run with
--types low_hanging_fruit,high_value_features --refresh - Read results —
ls <project>/.auto-claude/ideation/ - Promote to specs — copy ideas into
.auto-claude/specs/<NNN>-<slug>/spec.md - Dispatch —
./dispatch.nu run --wave N --yesor via Auto-Claude UI
Projects
| Project | Path |
| dub (EFI bootloader) | $HOME/efi |
| bop (jobcard system) | $HOME/bop |
| zam (unikernel VM reader) | $HOME/zam |
Notes
- Ideation reads
PLAN.md, existing specs, andCLAUDE.mdfor context automatically. --refreshis safe to run repeatedly — it overwrites the previous session.- Does not require an API key — uses Auto-Claude's OAuth session (Claude Code subscription).
- Inside an agent session,
CLAUDECODEenv var is already set; no need to unset it for this runner.
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.