composer-update
Skill10 starsChanged 3 months agoMITView on GitHub
Use when analyze composer update results, detect conflicts, and
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Use output from composer update if available
- Distinctive: line 39
If none: state "No conflicts detected"
- Very specific: line 68
Use the template defined in templates/update-report.md.
- Distinctive: line 75
Prefer local sources over remote
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Composer Update
Purpose
Analyze dependency updates after composer update, detect conflicts, and summarize relevant changes.
Constraints
- Apply @rules/php/core-standards.mdc
- Apply @rules/php/dependency-selection.mdc — this skill primarily bumps existing packages (rule out of scope per its Scope section), but a bump frequently uncovers an upstream that has been archived or marked abandoned. When that happens, re-run the Activity gate + Compatibility gate against the suggested replacement (or against a fresh search if no replacement is documented) before recommending the migration. Never silently keep an archived / abandoned package in the lockfile just because the bump compiles.
- Output Markdown only
Execution
1. Update Context
- Use output from
composer updateif available - Otherwise compare current
composer.lockwith the previous version
2. Detect Updated Packages
- List all added or changed packages
- Include version changes:
old → new
3. Conflict Detection
- Identify dependency conflicts from:
- composer output
- version constraint mismatches (
composer.jsonvscomposer.lock)
- Summarize conflicts clearly (package → reason)
- If none: state "No conflicts detected"
4. Changelog Extraction
For each updated package:
- Prefer:
vendor/<package>/CHANGELOG*
- Fallback:
- repository releases (GitHub/GitLab)
- package homepage
- Extract:
- breaking changes
- new features
- important fixes
- If unavailable:
- state "No changelog found"
5. Suggested Follow-up
- Recommend relevant checks:
- run tests
composer validatecomposer audit
Output Format
Use the template defined in templates/update-report.md.
Principles
- Focus on impactful changes, not noise
- Highlight breaking changes first
- Prefer local sources over remote
- Be concise and actionable
- Highlight security-related changes when present
In this repository62 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyze-problemSkill
- api-reviewSkill
- article-writingSkill
- assignment-compliance-checkSkill
- automation-audit-opsSkill
- autonomous-loopsSkill
- benchmark-optimization-loopSkill
- benchmarkSkill
- blueprintSkill
- class-refactoringSkill
- cleanup-local-branchesSkill
- codebase-simplification-auditSkill
- code-review-bugsnagSkill
- code-review-githubSkill
- code-review-jiraSkill
- code-reviewSkill
- create-issues-from-textSkill
- create-issueSkill
- create-missing-tests-in-prSkill
- create-testSkill
- design-systemSkill
- docker-patternsSkill
- e2e-testingSkill
- frontend-a11ySkill
- frontend-design-directionSkill
- frontend-patternsSkill
- frontend-slidesSkill
- git-workflowSkill
- laravel-authorization-reviewSkill
- laravel-securitySkill
- laravel-telescopeSkill
- latency-critical-systemsSkill
- merge-github-prSkill
- mysql-patternsSkill
- mysql-problem-solverSkill
- penetration-testerSkill
- postgres-patternsSkill
- prepare-issue-contextSkill
- process-code-reviewSkill
- product-capabilitySkill
- production-auditSkill
- pr-staged-merge-planSkill
- pr-summarySkill
- record-project-memorySkill
- redis-patternsSkill
- refactor-entry-point-to-actionSkill
- refresh-claude-mdSkill
- resolve-issueSkill
- rewrite-tests-pestSkill
- security-bounty-hunterSkill
- security-reviewSkill
- security-threat-analysisSkill
- seoSkill
- skill-creatorSkill
- slack-messagingSkill
- smartest-project-additionSkill
- test-driven-developmentSkill
- tester-cookbookSkill
- test-like-humanSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

