keel
Skill2 starsChanged 31 days agoApache-2.0View on GitHub
Build a walking skeleton for one selected frontend journey across real integration seams. Use to establish an end-to-end path, not for ordinary CSS questions or speculative architecture.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- matrixfede/keeltheir own version, first seen Nov 1, 2026
- APareek89/ai-buildcrafttheir own version, first seen Nov 1, 2026
- Chaierss/keeltheir own version, first seen Nov 1, 2026
- xiaol/Keeltheir own version, first seen Oct 20, 2026
- kisrafistya/keeltheir own version, first seen Oct 15, 2026
- joseconti/keel-skilltheir own version, first seen Oct 7, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- lencx/skills★ 196same name
- joseconti/keel-skill★ 14same name
- broomva/skills★ 4same name
- Chaierss/keel★ 1same name
- matrixfede/keel★ 1same name
- APareek89/ai-buildcraft★ 0same name
- kisrafistya/keel★ 0same name
- xiaol/Keel★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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
- liverySkill
- lookoutSkill
- pilotSkill
- seaworthySkill
- trialsSkill
- wellspringSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 41
When this stage is fulfilled: checklist advance seams --run "$RUN".
- Distinctive: line 58
Run the path from documented setup and exercise a failure case.
- Distinctive: line 71
Do not turn a skeleton into the whole product.
- Very specific: line 73
If an input or permission is missing, name the blocker and leave the relevant item pending.
- Very specific: line 79
After all required work and stage closures is recorded, use checklist done --run "$RUN".
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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
-->keel
Build a walking skeleton for one selected frontend journey across real integration seams. Use to establish an end-to-end path, not for ordinary CSS questions or speculative architecture.
Inputs
Chosen journey and acceptance example; target project; API/data contract; environment and deployment constraints.
Run record
Use checklist 0.5 or newer for this SOP. Reading or reloading the skill must not reset work. For a new task, run checklist init "${CLAUDE_SKILL_DIR}" --new --path "/absolute/project"; retain its returned ID as RUN. For existing work, use checklist resume "$RUN", then checklist show --run "$RUN". Outside Claude, replace the skill-directory variable with this directory’s actual path.
Commands below record work after it is done. Replace evidence placeholders with concise artifact locations and observations. Manual confirmations are not independent proof; a sensor pass covers only the command and inputs it observed. verify does not close a stage; advance checks that its required readings are fulfilled. Use report --run "$RUN" for the retained history.
Procedure
seams
Map the selected journey from user action through UI, service, persistence, and return path. Name uncertain integration seams and choose the smallest slice that exercises them.
Record these artifacts after doing the work:
- One concrete user journey and its acceptance outcome are agreed.
checklist check seams journey --run "$RUN" --evidence "<artifact and observation>" - Integration seams and contract assumptions are explicit.
checklist check seams seams --run "$RUN" --evidence "<artifact and observation>"
When this stage is fulfilled: checklist advance seams --run "$RUN".
slice
Implement the thin path using real contracts. If a service is unavailable, use a clearly labelled contract-faithful substitute and retain the unresolved integration task.
Record these artifacts after doing the work:
- The thin user-visible path runs through the intended seams.
checklist check slice path --run "$RUN" --evidence "<artifact and observation>" - Contracts are checked and substitutions or unresolved seams are named.
checklist check slice contract --run "$RUN" --evidence "<artifact and observation>"
When this stage is fulfilled: checklist advance slice --run "$RUN".
handoff
Run the path from documented setup and exercise a failure case. Leave enough setup and observation guidance that another contributor can reproduce the result.
Record these artifacts after doing the work:
- The selected journey can be run from documented setup.
checklist check handoff reproduce --run "$RUN" --evidence "<artifact and observation>" - Failure behaviour and remaining integration gaps are recorded.
checklist check handoff limits --run "$RUN" --evidence "<artifact and observation>"
When this stage is fulfilled: checklist advance handoff --run "$RUN".
Branches
Do not turn a skeleton into the whole product. Routine layout or styling fixes should be handled directly. Bearings is optional exploration when the journey itself is unsettled.
If an input or permission is missing, name the blocker and leave the relevant item pending. A changed requirement may need a new run; an accepted checklist edit uses resume "$RUN" --refresh and requires fresh readings. To abandon work, use checklist reset --run "$RUN" --reason "<reason>"; history is retained.
Completion
A reproducible thin vertical slice and a seam-risk record. Seaworthy and trials can extend robustness and regression coverage.
After all required work and stage closures is recorded, use checklist done --run "$RUN". This archives the result without deleting its history; it does not authorise any external action.
Reference shelf
Open the technique relevant to the current step. These notes provide concrete methods and examples, not additional phases; this entrypoint defines the run's completion conditions.
- Keep the client/server seam inspectable
- Implement the chosen spatial relationship
- Trace one thin journey across its seams
- Accept the thin slice at its stated boundary
- A thin slice through real integration seams
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.