Ready to supercharge your AI agents?

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

Stage4 Refine Follow-up Skill · runtsang | DecimalAI

researchby runtsang

Stage4 Refine Follow-up Skill

runtsang/stage4-refine-followup

Source runtsang/rebuttalstudio ↗License Not recorded

Refine a Stage 4 follow-up response using condensed prior discussion context, current follow-up question, and the user's draft.

NewMaintained

Automatic

Writing & Editing pack

Last verified 8/27/2026

What it changes

Passed 0 of 22 test cases with the skill, and 22 of 22 without it.

Without skill100%

With skill0%

0 fixed10 passed either way6 still failing6 broke

Pass-rate lift: -100 pp
Tokens: +12%
Agent turns: 0%
Response time: -6%

Model gemini-3.6-flashMeasured 8/27/2026v110 of 22 cases passed with skill

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/runtsang-stage4-refine-followup/SKILL.md https://app.decimal.ai/s/runtsang-stage4-refine-followup/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add runtsang-stage4-refine-followup, 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/runtsang-stage4-refine-followup/ and pins it in .decimal/skills.lock

decimalai skills add runtsang-stage4-refine-followup

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

curl -fsSL --create-dirs -o .claude/skills/runtsang-stage4-refine-followup/SKILL.md https://app.decimal.ai/s/runtsang-stage4-refine-followup/SKILL.md

Raw file: /s/runtsang-stage4-refine-followup/SKILL.md ↗ · machine-readable summary at /s/runtsang-stage4-refine-followup.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md23 linessingle file

Stage4 Refine Follow-up Skill

Goal

Generate a polished follow-up response for multi-round reviewer discussion.

Inputs

condensed_markdown: condensed context from Stage4 condense skill.
followup_question: current reviewer follow-up question text.
draft: user-authored draft response.

Output

Return strict JSON:

{ "refinedText": "..." }

Rules

Keep claims grounded in provided context and draft.
Address the follow-up question directly in the opening lines.
Maintain respectful, concise academic tone.
Avoid fabrication of data/citations/experiments.
Preserve the core intent of user draft while improving clarity and flow.

Track record

Benchmark

0 / 22

test cases passed, vs 22 / 22 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

Imported

runtsang / rebuttalstudio

skills/stage4/refine/SKILL.md

View on GitHub ↗

Imported 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?

What's inside

Stage4 Refine Follow-up Skill

Goal

Inputs

Output

Rules

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills