common-tasks
Skill1 starsChanged 3 months agoMITView on GitHub
Use as the entry point when the request is a generic "how do I add X?" or "generate a prompt for Y", or when no other skill obviously matches. Routes to the right specialized skill.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- idavidov13/agentic-playwrighttheir own version, first seen Nov 8, 2026
- trezor/trezor-suitetheir own version, first seen Oct 8, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- trezor/trezor-suite★ 1.1ksame name
- idavidov13/agentic-playwright★ 294same 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 repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- ai-native-workflowSkill
- api-testingSkill
- bootstrapSkill
- configSkill
- data-strategySkill
- debuggingSkill
- enumsSkill
- fixturesSkill
- page-objectsSkill
- salesforce-authSkill
- salesforce-dataSkill
- salesforce-locatorsSkill
- salesforce-metadata-contractSkill
- salesforce-personasSkill
- salesforceSkill
- salesforce-waitsSkill
- security-testingSkill
- selectorsSkill
- test-standardsSkill
- type-safetySkill
- wait-strategySkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
When the ask is generic, classify it and hand off to the specialized skill that owns the deep rules.
- Very specific: line 28
If asked to produce a reusable prompt for a teammate/Copilot, write it to point at the relevant SKILL.md and the Constitution (CLAUDE.md …
- Distinctive: line 34
Ask one clarifying question.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Common Tasks (router)
When the ask is generic, classify it and hand off to the specialized skill that owns the deep rules.
| The user wants… | Hand off to | First move |
| Configure a fresh clone | bootstrap | check PROJECT.md exists |
| A page object / new screen | page-objects | ls pages/, then explore |
| A functional UI test | test-standards | split into behaviors |
| An e2e journey | test-standards | map the journey in playwright-cli |
| API tests for an endpoint | api-testing | Phase-1 tool gate, then OpenAPI |
| Security / fuzzing tests | security-testing | enumerate input fields |
| A locator chosen/fixed | selectors | explore the live element |
| A flake fixed | wait-strategy → debugging | classify the wait |
A Zod schema / kill an any | type-safety | source the contract |
| A factory / invalid data | data-strategy | classify the value kind |
| A fixture wired | fixtures | page-object vs helper |
| An endpoint/route/message added | enums | verify live, then add |
| An env var / URL / secret | config | env vs enums |
Generate-a-prompt requests
If asked to produce a reusable prompt for a teammate/Copilot, write it to point at the relevant SKILL.md and the Constitution (CLAUDE.md §1), include the explore-first rule and the confidence gate, and list the hard stops that apply to that task.
If nothing matches
Ask one clarifying question. Don't guess a skill — wrong routing wastes a whole cycle.
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.

