library-author
Skill2 starsChanged 7 days agoMITView on GitHub
Author and review published PHP/Laravel libraries, map testsuites, and plan version-matrix cells. Routes provider/facade design, Testbench setup, Composer contracts, polyfill audits, suite selection, and cell onboarding to separate modes. Not for application code or single-version framework advice. Output follows the selected mode.
In this repository39 other files it gives its agents.
- AGENTS.mdAGENTS.md
- change-verdictSkill
- code-simplifySkill
- code-traceSkill
- create-prSkill
- deploy-listSkill
- doc-maintainSkill
- feature-verifySkill
- flow-driveSkill
- flow-guideSkill
- git-smart-commitSkill
- git-worktreeSkill
- harness-setupSkill
- issue-analyzeSkill
- js-static-checksSkill
- laravelSkill
- legacy-characterization-testsSkill
- merge-prepSkill
- module-designSkill
- nextjsSkill
- openspec-artifact-guardSkill
- opsx-apply-resumeSkill
- phpSkill
- phpunitSkill
- precommitSkill
- project-auditSkill
- project-briefSkill
- proposal-analyzeSkill
- pr-summarySkill
- pythonSkill
- reactSkill
- release-creatorSkill
- repo-intakeSkill
- repo-verifySkill
- swiftSkill
- tdd-workflowSkill
- ui-ux-verifySkill
- vue-2-notesSkill
- yii1Skill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 12
Use a natural-language library task or an explicit mode followed by its inputs.
≈ “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
Library author
Use a natural-language library task or an explicit mode followed by its inputs.
- Select the mode below from the requested deliverable. An explicit mode wins; clarify a genuinely ambiguous deliverable before loading a procedure.
- Identify the consumer package, declared PHP/framework/dependency range, and existing matrix from local metadata. Preserve each procedure's version inference; do not invent pins where consumer evidence is missing.
- Load only the selected mode procedure. Load its named sibling reference only for the relevant branch. Complete its input, authority, and verification gates.
- Return that mode's output with actual check results and remaining gaps. A release plan does not authorize publication, tags, or external changes.
| Mode | Task and input | Procedure | Output |
| author | Provider, facade, publishing or discovery design; supported range | author | Authoring decision or package design with compatibility gates |
| testbench | Multi-major Laravel matrix; package dependency metadata | testbench | Per-cell CI matrix, TestCase, database and discovery evidence |
| composer | Public API, Composer manifest, dependency floor or release contract | composer | Semver verdict, audited manifest or release gate |
| polyfill-audit | File, symbol or all version guards; declared and executed matrices | polyfill-audit | Branch enumeration, matrix gaps and asymmetric-edit report |
| suite-map | Edited paths and actual phpunit.xml suite directories | suite-map | Selected suites, commands and boundary warnings |
| cell-onboard | Proposed pinned runtime/dependency tuple and current workflow | cell-onboard | Composer, workflow, polyfill, Testbench and focused-test cell plan |
Distinct deliverables retain distinct contracts. A task spanning modes may run them in a stated sequence, retaining each mode's evidence and authority.
This relocatable skill is separate from the consumer content module
modules/library-author/. Its mode references are resources, not peer skills.
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.