Registry skillby graphif
type-check
graphif/type-check
运行 TypeScript 类型检查
What it changes
Passed 17 of 20 test cases with the skill, and 5 of 20 without it.
Without skill23%
With skill86%
Checks it passed that the model alone missed
- The output specifies `type-check` as the script name.
- The output specifies the full package filter `@graphif/project-graph`.
- The output specifies the command `pnpm --filter @graphif/project-graph type-check`.
14 fixed5 passed either way3 still failing0 broke
- Pass-rate lift
- +64 pp
- Tokens
- -72%
- Agent turns
- 0%
- Response time
- -69%
Model gemini-3.6-flashMeasured 8/10/2026v119 of 22 cases passed with skill · 20 comparable
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptProvide the exact pnpm filter command needed to typecheck @graphif/project-graph.
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| The output specifies the command `pnpm --filter @graphif/project-graph type-check`. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md7 linessingle file
type-check
运行以下命令来执行 TypeScript 类型检查：
pnpm --filter @graphif/project-graph type-check
Track record
Benchmark
17 / 20
test cases passed, vs 5 / 20 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedImported 8/3/2026Version v1