Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ataraxy-labs/sem
Semantic version control CLI. Entity-level diffs for Git (functions, classes, methods instead of lines).
Passed 19 of 19 test cases with the skill, and 4 of 19 without it.
and 13 more in the full report
15 fixed4 passed either way0 still failing0 broke4 errored
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
Using sem MCP tools, which mode parameter in `sem_find` inspects what external entities `calculateTax` invokes?
| Checked | Without skill | With skill |
|---|---|---|
| Sets `mode` parameter to `refs` in `sem_find`. | Missed | Passed |
The instructions your model reads when the skill loads.
sem parses 30+ languages with tree-sitter and answers questions about entities
(functions, classes, methods) and the calls between them. Instead of "lines
43-51 changed" it says "function validateToken in src/auth.ts was
modified, and these 3 callers and 2 tests reach it". It works in any Git repo
with no setup. Answers are deterministic; when a caller set may be incomplete,
sem says so.
| Question | CLI | MCP tool |
|---|---|---|
| Where is it? | sem find NAME, sem grep TEXT | sem_find, sem_grep |
| What does my change touch? | sem impact NAME, sem impact --diff HEAD --tests | sem_impact |
| Is it correct? | sem check | sem_check |
| What should a human review? | sem certify main..HEAD | sem_certify |
Also: sem diff (which entities changed), sem graph (how the code is
connected), sem history (how an entity changed; --blame for a file).
Every verb takes --json.
If the agent has the sem MCP server (tools named mcp__sem__*), call those
instead of running sem in a shell. They return compact results and carry
elapsed_ms. If they are deferred, load them first rather than falling back
to Bash.
| Task | MCP call |
|---|---|
where is X defined | sem_find with query: "X" |
read and understand X | sem_find with query: "X", mode: "context": body plus callers and callees, one call, no file needed |
who calls X | sem_find with mode: "callers" |
what X calls | sem_find with mode: "refs" |
| what is in this file or directory | sem_find with in: "src/auth.ts" |
| find code by intent, name unknown | sem_find with intent: "where retries are scheduled" |
| a string, error message, config key | sem_grep, or sem_find with text (hits named by entity) |
| what breaks / which tests to run | sem_impact (mode: "tests" for tests only) |
| is the change correct | sem_check |
test cases passed, vs 4 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.