Best Claude Skills for Efficiency (2026)
Most "best skills" lists are copied README summaries. This one isn't: we installed all 76 efficiency skills in our catalog, ran each against a baseline and scored four criteria. 27 passed cleanly, average score 8.5/10. The one to start with: Kill Dev Process.
Ranked by SkillProof Score · how we score
- 1
Kill Dev Process
Classifies and safely kills orphaned dev servers/browsers with a hard exclusion list for databases and the IDE.
From our test: Ran the actual step-1 investigation commands on a live dev machine: they surfaced postgres on :5432 and Claude's own IDE Helper node processes mixed in with real dev servers - exactly the kind of…
- 2
Clean Cache
Tiered, confirmation-gated cache cleanup for Flutter/Android/iOS/Node workspaces — verified not to touch lockfiles or source.
From our test: Actually ran the bundled scan-and-delete bash commands against a throwaway workspace with a fake node_modules, android build/, and .dart_tool/: L1 cleanup wiped only the build artifacts and left…
- 3
Agent Prompt Engineering
A five-part checklist (role, paths, deliverables, constraints, comms) for writing sub-agent prompts that need zero follow-up.
From our test: Drafted a spawn prompt for a 3-agent marketing-site redesign both ways: the baseline copy-agent prompt was one vague sentence ('improve the copy'), the skill-directed version had absolute file paths…
- 4
Tidy Skill
Read-only hygiene audits that stop agents littering repos with plan.md/todo.md junk.
From our test: Ran score_repo_hygiene.py on a throwaway repo with plan.md/todo.md/summary.md in root — it returned a real 57/100 'Needs tidy-up' score with a dimension breakdown and named the 3 suspicious files…
- 5
ACM Config
Interactive Q&A that writes a validated ~/.claude/claudikins-acm.conf for the Claudikins context-handoff tool.
From our test: Fully self-contained single-file skill; its real value is enforcing an exact serialization contract (file path, variable names, and a minutes-to-seconds conversion for SNOOZE_DURATION) that the…
- 6
SkillOpt-Sleep
Offline nightly sleep-cycle that mines past sessions and gates CLAUDE.md/SKILL.md edits.
From our test: Compared a naive direct-rewrite approach against the skill's stage-then-gate-then-adopt flow with backups; reading the actual gate code confirmed the harmful-edit block is implemented exactly as…
- 7
Golang Benchmark
Statistically rigorous Go benchmarking, pprof profiling, and benchstat regression workflow
From our test: Installed Go 1.26.5 and benchstat (installation command from Dependencies worked verbatim) and ran the documented workflow on a real module: naive concatenation vs. strings.Builder, ReportAllocs +…
- 8
Token Doctor
Reads your local Claude Code/Cowork transcripts and prints a real cost-shape diagnosis in the terminal.
From our test: Actually ran the two deterministic scripts against real local Claude transcripts on this machine and got genuine numbers back: $72.01 across 3 conversations, 77% of spend in one marathon session…
- 9
Free My CPU
Read-only CPU/load/Docker audit workflow with safety-tiered remediation, never kills anything unasked.
From our test: Ran both the plain ad hoc audit and the skill's macOS command set on a real machine live — the skill version alone flagged WindowServer/Chrome as the actual top CPU consumers and classified load as…
- 10
Analyze Costs
Cloud cost analysis and savings via Harness CCM, plus anomaly and commitment checks.
From our test: Best-documented skill in this batch: frontmatter states upfront it needs harness-mcp-v2, and the body ships a troubleshooting section covering '24-48h initial sync' and 'no recommendations' edge…
How this ranking works
Each skill gets a fresh install in Claude Code, three trigger phrasings, and the same task run with and without it. Scores: installation (5), trigger reliability (5), output vs baseline (10), documentation honesty (5) — normalized to a 10-point SkillProof Score. Full rubric on the methodology page. Queue-verdict skills sit at the bottom until testing completes.
New here? Start with how to install Claude skills — or grab the whole setup in one command with a curated pack ($10).
On a different AI tool? These tested instructions adapt: see our conversion guides for Cursor rules, Copilot instructions, Windsurf and Custom GPTs.