Ready to supercharge your AI agents?

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

Get Started Free →

perf-code-paths — measured AI agent skill | DecimalAI

agent-sh/perf-code-paths

SkillScore79Maintained

Use when mapping code paths, entrypoints, and likely hot files before profiling.

codingby agent-sh

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

Automatic

Coding pack

decimalai skills pull agent-sh-perf-code-paths

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/agent-sh-perf-code-paths/SKILL.md

Raw file: /s/agent-sh-perf-code-paths/SKILL.md ↗ · machine-readable summary at /s/agent-sh-perf-code-paths.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

24 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 28h ago

Yes — +63% lift-40% tokens0% turns79% of whole cases pass with skill (19/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-22%	0%
case-02	✗→✓	▲ Improved	-32%	0%
case-04	✗→✓	▲ Improved	-57%	0%
case-05	✗→✓	▲ Improved	-30%	0%
case-06	✗→✓	▲ Improved	-65%	0%

Showing 5 of 24 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

agent-sh / agentsys

.kiro/skills/perf-code-paths/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

perf-code-paths

Identify likely implementation paths for a performance scenario.

Follow docs/perf-requirements.md as the canonical contract.

Required Steps

Use repo-intel if available; otherwise use grep for entrypoints and handlers.
List top candidate files/symbols tied to the scenario.
Include imports/exports or call chains when relevant.

Output Format

keywords: <comma-separated list>
paths:
  - file: <path>
    symbols: [<symbol1>, <symbol2>]
    evidence: <short reason>

Constraints

Focus only on supported languages (Rust, Java, JS/TS, Go, Python).
Keep to the most relevant 10-15 files.

Want to see if agent-sh/perf-code-paths 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.