Ready to supercharge your AI agents?

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

Get Started Free →

spk-start-command-map — measured AI agent skill | DecimalAI

priivacy-ai/spk-start-command-map

SkillScore92Maintained

Map Spec Kitty slash commands and CLI entry points to spk skills. Use when choosing /spec-kitty.* commands or explaining command-skill boundaries.

agent-toolingby priivacy-ai

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

Automatic

Coding pack

decimalai skills pull priivacy-ai-spk-start-command-map

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/priivacy-ai-spk-start-command-map/SKILL.md

Raw file: /s/priivacy-ai-spk-start-command-map/SKILL.md ↗ · machine-readable summary at /s/priivacy-ai-spk-start-command-map.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 2h ago

Yes — +71% lift-50% tokens0% turns92% of whole cases pass with skill (22/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-06	✗→✓	▲ Improved	-61%	0%
case-21	✗→✓	▲ Improved	-28%	0%
case-02	✗→✓	▲ Improved	-56%	0%
case-04	✗→✓	▲ Improved	-53%	0%
case-05	✗→✓	▲ Improved	-72%	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

priivacy-ai / spec-kitty

src/doctrine/skills/spk-start-command-map/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file

Skill contents

references/

SKILL.md

spk-start-command-map

Route command questions without conflating command wrappers and operating skills.

Flow

Read references/command-map.md.
Choose the command for execution and the spk-* skill for operating

guidance.

If the user asks for discovery rather than a command, route to

spk-meta-skill-map.

Boundary

/spec-kitty.* files are generated slash-command or prompt-command surfaces. spec-kitty.<command> Agent Skills are generated under .agents/skills/ for skill-native hosts. spk-* skills are user-facing operating guides. Keep the surfaces distinct: dotted names are executable command surfaces; hierarchical spk-* names are operating guidance.

Want to see if priivacy-ai/spk-start-command-map 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.