The library

ent-design-partners · Structuring early B2B customer relationships that are committed, paid, and co-creative—avoiding big-logo traps and tire-kickers.

standup · Convening multiple worktrees/PRs as agents in a shared markdown chat to reconcile overlapping work without committing changes prematurely.

ent-idea-coach · Distinguishing wishes from ideas from insights—harvesting structural blindspots that incumbents can't pursue, not just consensus trends.

timeline-report · Analyzing a project's entire development history from persistent memory—tracing architectural evolution, breakthroughs, and work patterns across the full timeline.

ent-intake · Cold-start placement of a founder on the 00→07 journey—replacing blank forms with conversational state capture and automatic file writes.

claude-code-plugin-release · Provide expert guidance at a specific stage.

ent-interview-debrief · Provide expert guidance at a specific stage.

weekly-digests · Provide expert guidance at a specific stage.

ent-interview-prep · Provide expert guidance at a specific stage.

wowerpoint · Provide expert guidance at a specific stage.

ent-mvp-review · Provide expert guidance at a specific stage.

get-unpublished-changes · Provide expert guidance at a specific stage.

ent-mvp-scoper · Provide expert guidance at a specific stage.

github-triage · Provide expert guidance at a specific stage.

ent-office-hours · Provide expert guidance at a specific stage.

hyperplan · Provide expert guidance at a specific stage.

ent-pivot-coach · When a founder faces a critical go/no-go decision after PMF stall and needs data-driven clarity, not narrative hope.

ent-pmf-evaluator · When a team asks 'do we have PMF?' and you need to give an honest, rubric-backed answer that stands up to VC scrutiny.

opencode-qa · When you need to prove a specific hook fired or a CLI command works without manual testing overhead.

ent-pmf-memo · When you need a single shareable document that honestly answers 'where are you on PMF?' for investors or early hires.

pre-publish-review · When you're about to publish an npm package and need multi-agent coverage to catch edge cases across core, opencode, and codex layers.

ent-problem-statement · When a founder has finished a discovery batch and needs to crystallize one sharp problem before designing a solution.

publish · When you need end-to-end release orchestration across npm, GitHub, lazycodex, and Discord in a single coordinated workflow.

ent-prompt-troubleshoot · When AI output is disappointing and the fix is in the prompt, not the model — saves time vs trying new models.

remove-deadcode · When you need to clean dead code at scale without manually hunting — LSP verification prevents false positives.

ent-rdi-coach · When a team is at 2–3/6 PMF and needs a framework to prioritize what retention/desperation lever to pull next.

security-research · When you need multi-agent security review that catches adversarial thinking across code, infra, and supply chain.

ent-red-team · When you're about to commit to a high-stakes decision and need multi-agent critique to surface blind spots before shipping.

work-with-pr · When you need structured PR review that checks correctness, tests, and merge conflicts before the merge button.

ent-stage-router · When a founder asks 'what do I do next?' and you need to route them to the right playbook without skipping prerequisites.

ent-synthesis-coach · When a venture journey ends and you need to extract the timeless patterns that inform the next venture.

ent-thesis · When a founder is building their repeatable founder operating system — learning what works, what doesn't, and why.

ent-unit-econ-check · When a founder uses a unit econ model to make go/no-go decisions and you need to stress-test the assumptions.

ent-value-hypothesis-builder · When you have a validated problem and need to diverge on solution direction before concept-testing.

session-search · When you need to quickly find a past session by partial memory (a phrase, a date range, a person name).

lsp · When you need precise symbol tracking (dead code, refactor impact, dependency discovery) without regex fragility.

task-profile · Understanding your own Claude usage patterns when you want atomic skill recommendations tailored to repeated friction.

rules · Automating per-project instruction injection without rewriting CLAUDE.md for every session.

token-doctor · Identifying spend concentrations and antipatterns when your Claude bill is unexpectedly high.

ulw-plan · Large or ambiguous work when you need one decision-complete plan rather than back-and-forth negotiation.

ai-firstify · Systematically aligning existing projects to AI-first principles when piecemeal refactoring has plateaued.

ulw-loop · Long-running durable work with checkpoints when context resets and manual QA are acceptable overhead.

analyze-performance · Optimizing content strategy when you have a portfolio of published posts with known performance.

brainstorm-linkedin · Converting research, articles, or external ideas into personal LinkedIn angles without starting from scratch.

debugging · Production bugs and flaky tests when you need runtime truth instead of plausible code stories.

brainstorm-opinion · Cross-pollinating LinkedIn content into opinion pieces when you want deeper societal reach.

content-studio · Entry point when user has content requests but you need to confirm tool readiness.

git-master · Atomic commits and complex history investigations when you need evidence-led git operations.

setup-content-studio · Bootstrapping thought leadership content systems when you have an author and examples but no infrastructure.

init-deep · Rapidly documenting complex codebases when you need a living CLAUDE.md that grows with the project.