project-task
Skill566 starsChanged 13 days agoApache-2.0View on GitHub
Complete Vernet feature work, bug fixes, release tasks, workflow issues, and repo-wide implementation work by using the project’s instructions, memory, and the most relevant specialized skill.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- android-fastlane-releaseSkill
- close-chatSkill
- firebase-hosting-configSkill
- flutter-feature-iterationSkill
- flutter-test-repairSkill
- github-actions-repository-workflowsSkill
- github-issue-creatorSkill
- github-issue-implementationSkill
- github-project-managerSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 7 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use this when a request is broad or cross-cutting and needs the repo’s guidance, memory, and the most relevant specialized skill to …
- Very specific: line 13
Read the repository guidance first: .github/copilot-instructions.md, AGENTS.md, and ARCHITECTURE.md before making a structural or …
- Distinctive: line 14
Check relevant memory before deciding the approach:
- Very specific: line 15
read /memories/ for user or repo constraints, testing patterns, and past fixes
- Very specific: line 16
use /memories/session/ for multi-step task tracking
- Distinctive: line 28
Keep changes narrow and in the correct layer:
- Very specific: line 36
prefer flutter test path/to/test.dart for targeted checks
- Very specific: line 37
run flutter analyze after coherent Dart changes
- Distinctive: line 43
Treat the app as a Flutter network-diagnostics project with a layered architecture.
- Distinctive: line 44
When a task touches project memory or historical debugging patterns, incorporate the relevant stored guidance as part of the working plan.
- Distinctive: line 45
Do not claim a check passed without fresh output.
- Distinctive: line 46
If local verification is blocked by environment limits, report the exact blocker and what remains unverified.
≈ “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
Project Task
Use this when a request is broad or cross-cutting and needs the repo’s guidance, memory, and the most relevant specialized skill to complete the work without guessing.
Procedure
- Read the repository guidance first:
.github/copilot-instructions.md,AGENTS.md, andARCHITECTURE.mdbefore making a structural or architectural change. - Check relevant memory before deciding the approach:
- read
/memories/for user or repo constraints, testing patterns, and past fixes - use
/memories/session/for multi-step task tracking - preserve prior notes about failing-test workflow and verification standards
- read
- Identify the task type and choose the closest specialized skill:
graphifyfor architecture, file relationships, request routing, or “where is this implemented?” questionsgithub-issue-implementationfor issue-driven fixes or requested behavior changesflutter-feature-iterationfor UI, screens, and feature behavior changesflutter-test-repairfor failing unit, widget, or integration testsgithub-actions-repository-workflowsfor CI workflow or repo automation failuresandroid-fastlane-releasefor Android release or beta delivery workfirebase-hosting-configfor Firebase or web deployment config problemsclose-chatwhen asked to close or wrap up a chat, record durable context, or prepare a handoff
- State one falsifiable cause or expected-behavior hypothesis, then pick the smallest validation that could disprove it. Start from the concrete problem, not a broad refactor.
- Keep changes narrow and in the correct layer:
- UI in
lib/pages/orlib/widgets/ - networking in
lib/services/ - data in
lib/models/ - utilities in
lib/utils/ - feature state in the local or existing project pattern
- UI in
- Preserve user work and unrelated dirty files. Never discard or overwrite changes without explicit reason.
- Validate with the smallest relevant command and rerun after the first meaningful edit:
- prefer
flutter test path/to/test.dartfor targeted checks - run
flutter analyzeafter coherent Dart changes - for CI or platform work, use the corresponding repository command rather than a broad suite
- prefer
- Report the outcome with a short summary of the task, root cause or behavior implemented, files changed, validation commands and results, and any remaining limitations.
Vernet-specific expectations
- Treat the app as a Flutter network-diagnostics project with a layered architecture; do not mix UI and service logic.
- When a task touches project memory or historical debugging patterns, incorporate the relevant stored guidance as part of the working plan.
- Do not claim a check passed without fresh output.
- If local verification is blocked by environment limits, report the exact blocker and what remains unverified.
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.

