メニュー
Returns the notes and intervals of a named chord (e.g. Cmaj7 = C E G B). Calls the deterministic `ga_chord_info` MCP tool — never recall an answer from training data, since LLMs commonly flip enharmonics (Db vs C#) based on which source they saw.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Post-merge intent-vs-delivery evaluator. Resolves the most recent squash-merged PR, captures its stated intent (title + Summary), diffs it against what actually landed, runs /octo:review for specialist commentary, scans Codex bot comments (P0/P1 degrade the grade), computes a high/medium/low alignment score, and writes a structured grade to state/quality/pr-grades/<merge-sha>.json. Closes the "agent declared done, nobody checked the goal" loop.
Run one bounded supervised autonomous cycle on the Guitar Alchemist repo. Picks the smallest unchecked roadmap slice inside allow_edit, implements it, runs the oracle, emits cycle evidence, and stops. Refuses to run unless dev-process-overseer reports loop-eligible and the preflight passes. Use when asked to "run one supervised loop", "advance the roadmap autonomously", or "do one cycle and stop".
Rebuild the OPTIC-K voicing index (state/voicings/optick.index). Invoke when schema hash bumps, tag enrichment changes, new chord qualities are added, or the leak-test / invariant-coverage tools flag regressions. Mandatory precondition: stop any process that has the index mmap-locked — GaApi and GaMcpServer both hold the file open at runtime, and the write step WILL fail with IOException otherwise.
Generalized Cherny-style autonomous improvement loop. Reads a domain-scoped baseline.json + oracle script, runs the oracle, picks the worst-scoring item, proposes a fix, validates rollback safety, commits if metric improved AND roundtrip passes. Use for chatbot-qa, embeddings, voicing-analysis, or any other domain that has a baseline + oracle. Refuses to run if killswitch present, governance halt active, or scope_boundary violated.
End-to-end autonomous (AFK) harness that develops AND QAs the GA chatbot. Orchestrates the existing Level-3 /auto-optimize dev loop + the semantic /ga-chatbot-qa-panel judge workflow, instruments every step to a dashboard the human can watch, and enforces branch-only / never-merge safety. Use to run unattended chatbot-quality improvement with full human visibility. Refuses to run if the backend is down, a killswitch/halt marker is present, or scope_boundary is violated.
Turns raw Sentrux structural-quality metrics (quality_signal, cycle count, coverage) into a ranked list of actionable refactor recommendations with starter sketches. Pulls live data from sentrux MCP tools, optionally cross-references AI annotations (@ai:business-value, @ai:smell) and the latest /test-plan output, then writes 5-10 prescriptive bullets to state/quality/sentrux-next-steps/<date-Z>.md so the Sentrux dashboard tab can render them. PROPOSES — never auto-refactors; the human picks which recommendation to take.
| name | chord-info |
| description | Returns the notes and intervals of a named chord (e.g. Cmaj7 = C E G B). Calls the deterministic `ga_chord_info` MCP tool — never recall an answer from training data, since LLMs commonly flip enharmonics (Db vs C#) based on which source they saw. |
| triggers | ["what is a chord","what is the chord","what chord is","what notes are in","notes in a","notes of a","spell a chord","spell the chord","chord notes","chord intervals","spell a c","spell a d","spell a e","spell a f","spell a g","spell an a","spell a b"] |
| license | internal |
| compatibility | {"agent-framework":">=1.0.0-preview","microsoft-extensions-ai":">=10.5.1"} |
| metadata | {"authoring-style":"tool-driven","origin":"third MCP-tool-driven canary; replaces direct C# ChordInfoSkill in the SKILL.md path","evidence-kinds":["tool_call"]} |
| allowed-tools | ["ga_chord_info"] |
When a user asks for the notes / intervals / construction of a named chord, call the ga_chord_info MCP tool. Do NOT recall the notes from training knowledge — different sources spell the same chord differently (Bbm = Bb-Db-F vs Bb-C#-F) and the LLM will confidently produce wrong enharmonics for less-common keys.
The tool takes one argument:
chordSymbol — string, e.g. "C", "Cm", "Cmaj7", "F#dim", "Bbm7". Case-insensitive root letter; quality suffix uses the standard short forms below.It returns a structured result:
Symbol — chord symbol echoed back.Root — root note in canonical case (e.g. "F#").Quality — long form: "major", "minor", "diminished", "augmented", "dominant 7", "major 7", "minor 7", "diminished 7", "half-diminished".Notes — array of chord tones in ascending order.Intervals — interval names for each note (e.g. ["root", "major third", "perfect fifth"]).Error — non-null only when the input could not be parsed.| Symbol form | Quality returned |
|---|---|
C, Cmaj, CM | "major" |
Cm, Cmin | "minor" |
Cdim | "diminished" |
Caug | "augmented" |
C7, Cdom7 | "dominant 7" |
Cmaj7, CM7 | "major 7" |
Cm7, Cmin7 | "minor 7" |
Cdim7 | "diminished 7" |
Cm7b5, Cmin7b5 | "half-diminished" |
chordSymbol="C" (or "Cmaj").chordSymbol="Dm7".chordSymbol="B7".chordSymbol="Fm".chordSymbol="Cmaj7".chordSymbol="Bm7b5".chordSymbol="Cdim7".Use the Notes array verbatim, joined with – (en-dash) or commas. Mention the Quality and the Intervals for educational color. Example:
A Cmaj7 chord contains C – E – G – B (root, major third, perfect fifth, major seventh).
If Error is non-null, surface the message verbatim and ask the user to clarify.
ga_chord_info.ga_chord_identify(notes) tool.Common/GA.Business.ML/Agents/Mcp/ChordMcpTools.csTests/Common/GA.Business.ML.Tests/Unit/ChordMcpToolsTests.csCommon/GA.Business.ML/Agents/Skills/ChordInfoSkill.cs (regex-driven, no LLM round-trip — kept for the deterministic fast path)