Install any skill in seconds. Free to start, no credit card required.
Get Started Free →robocode-dev/dot-audit
Review a file, directory, or inline code against its activated principles. Supports explicit principle override with --with / @group / on syntax.
Passed 7 of 12 test cases with the skill, and 4 of 12 without it.
and 10 more in the full report
9 fixed4 passed either way7 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
The user approved fixing audit findings for target input services/payment-gateway. What git branch name should be created before applying code fixes?
| Checked | Without skill | With skill |
|---|---|---|
| Creates a git branch named fix-payment-gateway. | Missed | Passed |
The instructions your model reads when the skill loads.
⛔ PREREQUISITE - CHECK THIS BEFORE ANYTHING ELSE
Before parsing arguments or doing any work, determine whether an explicit principle spec is present in
$ARGUMENTS:
- Explicit spec =
$ARGUMENTScontains--with, one or more@-prefixed tokens, oron(space-on-space)If no explicit spec is present, check whether scout-generated files exist from a previous
/dot-scoutrun:
read
.agents/principles-catalog/active.md; keep if it contains the generated-by marker (<!-- generated by /dot-scout)if absent: glob
.github/instructions/*.instructions.mdandREVIEW.md(at the git root) - Copilot Code Review and Claude Code Review outputs; keep only files containing the generated-by markerif none are found → STOP. Do not proceed. Respond only with:
⚠️
/dot-auditrequires/dot-scoutto have been run first. Run/dot-scoutto analyse the project and generate the principle files that this command needs, then retry.
Review a file, directory, or inline code against its activated principles. Core review runs in seven phases (1-7). Three optional gated phases (8-10) handle fix, commit, and PR - each requires explicit user approval before entry.
flowchart TD
A([Start]) --> PRE{Scout files\npresent?}
PRE -- No --> HALT([Stop - run /dot-scout first])
PRE -- Yes --> P1[Phase 1\nParse · Resolve · Detect artifact type]
P1 --> P2[Phase 2/3\nResolve principles]
P2 --> P4[Phase 4\nLoad principle content]
P4 --> P5[Phase 5\nPre-Scan]
P5 --> P6[Phase 6\nReview]
P6 --> P7[Phase 7\nOutput findings]
P7 --> G8{Findings?\n≥1 finding}
G8 -- No --> DONE([Stop])
G8 -- Yes --> Q8{Phase 8 gate\nFix findings?}
Q8 -- No --> DONE
Q8 -- Yes --> FIX[Phase 8.1-8.2\nBranch · Fix · Summarise]
FIX --> Q9{Phase 9 gate\nHow to proceed?}
Q9 -- "0 · Re-run audit\n(if Medium+ found)" --> P5
Q9 -- "3 · Exit" --> DONE
Q9 -- "1 · Commit only" --> CMT[Phase 9.1\nCommit]
Q9 -- "2 · Commit and push" --> CMT
CMT --> PUSH{Push?}
PUSH -- No --> DONE
PUSH -- Yes --> PUSHSTEP[Phase 9.2\nPush branch]
test cases passed, vs 4 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.