wellspring
Skill2 starsChanged 31 days agoApache-2.0View on GitHub
Generate alternatives for frontend state and interaction models using ownership, time, and representation shifts. Use when the model is awkward, not for a mandatory state audit.
In this repository37 other files it gives its agents.
- canonSkill
- colorSkill
- formSkill
- graphicsSkill
- layoutSkill
- motionSkill
- pilotSkill
- systemsSkill
- typeSkill
- holdfastSkill
- aegisSkill
- assaySkill
- flightlineSkill
- gaugeSkill
- groundworkSkill
- gungnirSkill
- husbandrySkill
- load-bearingSkill
- pilotSkill
- plumbSkill
- stationkeepingSkill
- crucibleSkill
- envoySkill
- forgeSkill
- ledgerSkill
- prospectSkill
- reckoningSkill
- forageSkill
- touchstoneSkill
- bearingsSkill
- bulwarkSkill
- keelSkill
- liverySkill
- lookoutSkill
- pilotSkill
- seaworthySkill
- trialsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Follow a value from creation to display, revision, disagreement, and disappearance.
- Distinctive: line 46
When a model is selected, keel implements the path and trials protects its visible behaviour.
- Distinctive: line 50
Read selectively when a thread needs another perspective or a concrete technique.
≈ “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
<!--
Copyright 2026 IamK77 — Licensed under the Apache License, Version 2.0.
See ./LICENSE and ./NOTICE · https://www.apache.org/licenses/LICENSE-2.0
-->wellspring
Generate alternatives for frontend state and interaction models using ownership, time, and representation shifts. Use when the model is awkward, not for a mandatory state audit.
Starting point
State is a claim about what should remain true between moments. Many troublesome variables are clues that the interaction could be imagined differently.
Bring a question, fragment, reference, or tension. Follow whichever association becomes useful; these invitations are not a sequence to complete. Speculation should remain distinguishable from an observed fact.
Thought experiments
Tell a value’s biography
Follow a value from creation to display, revision, disagreement, and disappearance. Try changing its author or its lifespan. What copy becomes unnecessary, or suddenly meaningful?
Replace flags with a story
Narrate a difficult interaction as a small play: scenes, events, interruptions, returns. Sketch a state machine only if that story clarifies the experience.
Make a fork intentional
Imagine edits as a draft, a branch, a transaction, or a live shared surface. These metaphors imply different save, undo, and conflict behaviours; explore the differences.
A possible turn
A form keeps mirroring a server record and loses edits during refresh. Calling it a draft instead of a mirror suggests an explicit base revision and a commit. Calling it a live document suggests collaboration and reconciliation. Both are coherent, but serve different experiences.
Leave the space open
Offer a few genuinely different possibilities, a sketch, an analogy, or a sharper question when useful. Do not turn every prompt into a scored diagnostic, a completion gate, or a demand for an action plan. The human may choose a direction, combine them, or leave the question open.
When a model is selected, keel implements the path and trials protects its visible behaviour.
Optional references
Read selectively when a thread needs another perspective or a concrete technique. The notes supply possibilities, examples, and limits; none is a prerequisite or a requirement to close the exploration.
- Several homes for a value
- Channels, composition, and component relationships
- Observation, freshness, and a local proposal
- Copies with different meanings
- Interactions as stories with explicit transitions
- State as ownership and memory
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.