Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Decide · superset-sh | DecimalAI

code reviewby superset-sh

Decide

superset-sh/decide

Source superset-sh/superset ↗License NOASSERTION

Walk the user through design or implementation decisions one at a time, or review completed code one change at a time.

SkillScore68Maintained

Automatic

QA & Test Engineering pack

Last verified 8/13/2026

What it changes

Passed 12 of 18 test cases with the skill, and 7 of 18 without it.

Without skill41%

With skill68%

Checks it passed that the model alone missed

The response informs the user that they can correct the assumption.
The response offers to switch to decision mode for that design fork.
The response offers to convert the audit into an implementation plan.

and 7 more in the full report

7 fixed8 passed either way6 still failing1 broke

Pass-rate lift: +27 pp
Tokens: -16%
Agent turns: 0%
Response time: -49%

Model gemini-3.6-flashMeasured 8/13/2026v115 of 22 cases passed with skill · 18 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/superset-sh-decide/SKILL.md https://app.decimal.ai/s/superset-sh-decide/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add superset-sh-decide, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/superset-sh-decide/ and pins it in .decimal/skills.lock

decimalai skills add superset-sh-decide

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/superset-sh-decide/SKILL.md https://app.decimal.ai/s/superset-sh-decide/SKILL.md

Raw file: /s/superset-sh-decide/SKILL.md ↗ · machine-readable summary at /s/superset-sh-decide.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

We are reviewing a complex 500-line change to the consensus module in raft.ts. What extra verdict option should be offered beyond approving or pushing back?

What was checked, without and with the skill
Checked	Without skill	With skill
The response includes an option to pause and request further explanation for complex changes.	Missed	Passed

case-21 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md43 linessingle file

Decide

Prepare

Before a design walkthrough, inspect the relevant code and record concrete bugs, inconsistencies, and decision points in plans/<YYYYMMDD>-<topic>.md or the appropriate app-scoped plans/ directory. Preserve existing edits; never discard speculative or user-authored work without explicit approval.

Order decisions by dependency and leverage, not document order.

Decision walkthrough

For each decision:

Show ## Decision N: <title>.
Give two to four sentences of context grounded in real files or functions.
State the trade-off in one sentence.
Ask exactly one interactive question with two to four mutually exclusive options.
- Use ask_user when available. In Codex Plan mode, use request_user_input when that is the exposed interactive question tool.
- Never substitute a plain-text question when repository instructions require an interactive overlay.
- Keep labels to five words or fewer.
- Put the recommendation first and suffix its label with (Recommended).
- Explain each option and its trade-off in one sentence.
- Do not add an Other option when the client adds one automatically.
After the answer, write Logged: <decision>. and continue.

If the user acknowledges an issue without choosing, log the recommended choice and say they can correct the assumption.

At the end, provide a | # | Decision | Choice | table and offer to turn the audit into an implementation plan. Do not write implementation code during the decision walkthrough.

QA walkthrough

Use this mode when the user wants to review existing code step by step.

Identify the review unit: a commit, staged diff, PR, or explicit file set.
Break it into logical steps in dependency order.
Show one step per turn with:
- ## Step N: <title>
- One or two sentences explaining what changed and why
- A focused real-code excerpt with file and line references
- One interactive verdict question: Looks good — next step (Recommended), Push back — change this, and, only for non-trivial code, Pause — explain more
Wait for the verdict before showing the next step.

Track record

Benchmark

12 / 18

test cases passed, vs 7 / 18 without

Adoption

Users: 1
Times used: 1

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

Imported

superset-sh / superset

.agents/skills/decide/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Decide

Prepare

Decision walkthrough

QA walkthrough

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills