hunch
claudeA grab bag of hunches — experimental skills and plugin features tried here before they earn a place in hope or sound. Everything graduates or dies.
6 skills
Thinking discipline for AI work. Clarify intent, shape approach, consult experts, guard unsupervised work, hand work back so you own it.
Plugin hope from marketplace moo.md in saadshahd/moo.md. Commands read from the repo's manifest — today.
anchorRewrite a rule so anyone applies it the same way. Use when a stated rule or claim takes the reader's judgment to apply.
clarifyTurn words with two readings into one confirmed ask. Use when the user's words admit two readings that would build different things.
composePlan the skills an ask needs, invoke each as its condition arrives. Use when the ask has multiple aspects that different skills carry, or the user named multiple skills.
consultBring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict.
deepenHold an ask to the bar a top professional in its field would set — a deeper ask, never a bigger one. Use when an ask is clear but nothing yet names the sources, methods, target, or outside check the work will meet.
draftBuild the thing the user can't specify, choices surfaced. Use when the user needs something to react to before they can choose.
elicitDraw out what the user holds but can't say. Use when the user knows something they cannot yet express.
explainShow one settled thing so the user holds it. Use when the user does not hold something already settled.
freezeFreeze outside-the-repo state into one snapshot. Use when the work depends on the current state of a service, database, queue, third party, or live logs.
intentTurn a rough ask into a clear work order. Use when the ask is rough, unspoken, or double-readable — before planning or building.
interrogateMake the user defend a proposal they committed to. Use when a proposal is committed but its decisions are undefended.
inversionFind the route to guaranteed failure, negate it. Use when a goal keeps not being reached head-on.
judgeOne committed verdict on something that exists, cited. Use when something exists and a claim about it needs a verdict.
provocationExtract movement from a statement known to be false. Use when nobody can see past an obvious answer.
reduceRe-derive something written into the shortest version that still covers everything. Use when something already written should get shorter and nothing it covers can be lost.
reframeRestate a problem off the framing it arrived in. Use when a framing came by default, not by choice — every option inside it loses, or an ask names a step or an artifact and leaves the outcome it serves unnamed.
routerSpawn agents and verify their output — route work, never do it. Use when the work splits into pieces agents can carry and the session should route and check, not execute.
shapeDecide the technical path once the ask is clear. Use when the WHAT is confirmed but more than one way to build it remains — architecture, technology, design.
shiftRestate the problem in a distant domain's terms. Use when a problem circles inside its own vocabulary.
targetDefine how unsupervised work is judged before it runs. Use when work will run without a human watching, optimizing toward something.
widenAssemble cases from context, induce the widest sound rule. Use when a real case shows a class no rule yet decides, or a rule decides only the cases it came from.
/hope:fullRun the full hope pipeline — intent, shape, target, freeze as needed — then execute
A grab bag of hunches — experimental skills and plugin features tried here before they earn a place in hope or sound. Everything graduates or dies.
6 skills
Comprehension at the human's pace. Grasp a change, drive a behavior, land one thing in an audience — until you can say how it works with the agent out of the room. A reply's Mermaid diagrams draw as pictures, and the pictures Claude touches open in place.
4 skills
Code taste as installable rules. Probe a repo's stack, select only the rules its code shows a surface for (evidence-cited per rule), confirm, and scaffold a browsable .claude/sound/ rule map (surfaced by the sound:prime skill). Installed rules are user-owned; re-runs reconcile.
3 skills
Work items become Claude Code agent runs, on your Mac or in CI. The repo's own checks decide what they can, a path's risk level decides who reviews, and only what nothing settles becomes a question to you.
1 skill
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Legacy core-only installation. For the release-managed bundle of every skill, install hyperframes@hyperframes and then uninstall core-skills@hyperframes.
22 skills
Core Ruflo MCP tools, commands, and Claude Code orchestration patterns
5 skills · 2 commands · 4 agents · 1 MCP server · hooks
Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.
1 skill
Action-first, ADHD-friendly output shaping for Claude Code.
1 skill · hooks
Install the "Essentials" workflow plugin from Agentic Awesome Skills.
5 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.