Ready to supercharge your AI agents?

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

Get Started Free →

A5c AI/Finishing A Development Branch — measured AI agent skill | DecimalAI

a5c-ai/finishing-a-development-branch

SkillScore59Maintained

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.

by a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

decimalai skills pull a5c-ai-finishing-a-development-branch

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-finishing-a-development-branch/SKILL.md

Raw file: /s/a5c-ai-finishing-a-development-branch/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-finishing-a-development-branch.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9d ago

Yes — +45% lift-60% tokens0% turns59% of whole cases pass with skill (13/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-05	✗→✓	▲ Improved	-72%	0%
case-08	✗→✓	▲ Improved	-73%	0%
case-09	✗→✓	▲ Improved	-78%	0%
case-10	✗→✓	▲ Improved	-77%	0%
case-11	✗→✓	▲ Improved	-69%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

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

a5c-ai / babysitter

library/methodologies/superpowers/skills/finishing-a-development-branch/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

Process

Verify all tests pass (STOP if they fail)
Determine base branch
Present exactly 4 options
Execute chosen option
Clean up worktree (Options 1 and 4 only)

Agents Used

Process agents referenced in workflow processes

Tool Use

Referenced by executing-plans and subagent-driven-development processes.

Want to see if a5c-ai/finishing-a-development-branch would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.