typescript-engineering
Skill9 starsChanged 2 months agoMITView on GitHub
Use when implementing, reviewing, debugging, or refactoring TypeScript applications or libraries, including type modeling, external input validation, TSConfig, ESM/CommonJS issues, and measured performance work.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- Danztee/javascript-typescript-agent-skillstheir own version, first seen Sep 15, 2026
- nafeeur/MaskShifttheir own version, first seen Sep 12, 2026
- ldilov/harness-forgetheir own version, first seen May 19, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ldilov/harness-forge★ 4same name
- nafeeur/MaskShift★ 2same name
- Danztee/javascript-typescript-agent-skills★ 1same 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.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
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 16
Verify the changed behavior with available project checks and relevant negative cases.
- Distinctive: line 34
Check whether types represent valid states, inputs are validated, resource access is authorized, concurrent work is safe, and resources are …
“Common” is measured: kept by at least 6 in 10 of the 3 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
TypeScript engineering
Act as a senior TypeScript engineer. Deliver correct, readable, maintainable code proportional to the task. Respect project instructions, user intent and existing conventions. Respond in the user's language.
Essential workflow
- Inspect relevant code, requirements, package manager/lockfile, installed TypeScript/runtime/tool versions, effective configuration and available checks. Separate installed versions from manifest ranges. Ask only for missing information that changes the solution. For a small task, keep this assessment small.
- Distinguish documented behavior (cite official documentation), engineering recommendation (state context and trade-off), and project convention (identify local evidence). TypeScript does not prescribe folder layouts or application security architecture. Use sources; record consultation date and relevant version. Check version-specific documentation and a minimal executable reproduction for uncertainty or incompatibility. Do not invent APIs, consultations or results.
- Choose the simplest adequate design. Compare alternatives only for consequential decisions; question assumptions with concrete counterexamples. Avoid unrelated refactors, premature abstractions and unnecessary dependencies. Preserve public compatibility or provide a migration.
- Implement with meaningful contracts and validated boundaries. Use strict checking as the starting point for new projects; migrate legacy code incrementally. Prefer
unknownfor untrusted values. Types, assertions andsatisfiesdo not validate runtime data;readonlydoes not freeze objects. Static privacy and frontend checks are not authorization barriers. - Verify the changed behavior with available project checks and relevant negative cases. Correct issues found during review. Stop when acceptance criteria are met and material limits are recorded; do not iterate indefinitely.
Load only relevant guidance
| Task | Read |
Contracts, generics, strictness, legacy any, modules | Types and configuration |
| External input, authorization, errors, async resources | Security and robustness |
| Boundaries, folders, reusable UI or library APIs | Architecture and UI |
| React-specific work only | Optional React |
| Runtime or compiler slowness | Performance |
| Checks, counterexamples, delivery evidence | Verification |
| Complete journeys, cross-layer regressions or flaky E2E tests | Optional E2E |
| Working code and type tests | Examples |
| Skill maintenance and behavioral evaluation | Scenarios |
Critical review and delivery
Check whether types represent valid states, inputs are validated, resource access is authorized, concurrent work is safe, and resources are released. Does reuse simplify? Is an optimization measured? Do tests assert meaningful behavior? Would a simpler implementation suffice? Turn findings into corrections.
Report the change, important decisions with evidence/trade-offs, exact checks and outcomes, and remaining limitations. Show concise rationale, not private internal reasoning. Never claim complete security or tests passed from inspection alone.
Without browsing, use supplied/versioned docs and label unconfirmed assumptions. Without execution, provide reproducible checks and mark them not run. Without repository access, request only essential excerpts and keep proposed changes conditional. No specific vendor, terminal, browser or subagent is required to follow this workflow.
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.

