菜单
Identifies the most likely musical key of a chord progression and explains why. Calls the deterministic `ga_key_identify` MCP tool — never recall the analysis from training data, since the diatonic-set match is pitch-class arithmetic and the LLM is unreliable at it.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | key-identification |
| description | Identifies the most likely musical key of a chord progression and explains why. Calls the deterministic `ga_key_identify` MCP tool — never recall the analysis from training data, since the diatonic-set match is pitch-class arithmetic and the LLM is unreliable at it. |
| triggers | ["what key is","what key does","what key are","identify the key","key of these","key of the","key is this","what key am i","diatonic to"] |
| license | internal |
| compatibility | {"agent-framework":">=1.0.0-preview","microsoft-extensions-ai":">=10.5.1"} |
| metadata | {"authoring-style":"tool-driven","origin":"ported from Common/GA.Business.ML/Agents/Skills/KeyIdentificationSkill.cs — sixth MCP-tool-driven canary; first hybrid port (deterministic detection + LLM phrasing)","evidence-kinds":["tool_call"]} |
| allowed-tools | ["ga_key_identify"] |
When a user asks what key a chord progression is in, call ga_key_identify. Do NOT analyze the progression from training knowledge — the diatonic-set match is pitch-class arithmetic and the LLM is unreliable at it.
The tool takes one argument:
query — string. Either a bare chord list ("C Am F G") or the user's full question ("what key is C Am F G in?"). The tool extracts chord symbols from prose.It returns a structured result:
RecognizedChords — string array, what the parser actually saw (useful for catching typos).TopCandidates — array of KeyCandidateInfo. Keys tied at the highest match count.PartialMatches — up to 3 partial-match keys ranked behind the top set.TotalChords — total chords parsed.Error — non-null when no chords parsed or no candidates matched.Each KeyCandidateInfo has:
Key — canonical key name (e.g. "C major", "A minor").RelativeKey — name of the relative pair.MatchCount / TotalChords — N of M chords are diatonic in this key.DiatonicSet — the seven diatonic chords (I through vii°) in order.Your job is to explain the key choice in guitarist-friendly language. Use the structured tool result; do NOT add analysis the tool didn't compute.
When TopCandidates has exactly one entry: lead with the key name and the match score, give the Roman numeral function of each input chord, and mention the diatonic set.
The progression
Dm G Cis in C major (3/3 chords diatonic). In C major: Dm = ii, G = V, C = I — a classic ii-V-I cadence. The diatonic chords of C major are C – Dm – Em – F – G – Am – B°.
When TopCandidates has multiple entries (almost always 2 — the relative major/minor pair share a diatonic set): name both, then explain how to distinguish them by ear.
The progression
C Am F Gfits C major AND A minor equally — both contain all four chords. To tell them apart, listen for the tonic: if the progression keeps resolving to C as home, it's C major; if Am feels like home, it's A minor. The relative-key pair shares the diatonic set C – Dm – Em – F – G – Am – B°.
When PartialMatches has entries, optionally mention 1–2 of them with their match score: "Could also be partly heard as G major (3/4 diatonic — the F is the borrowed chord)."
If Error is non-null, surface the message verbatim and ask the user to write the chords as standard symbols.
These are hard constraints. Do NOT compute these from this catalog alone.
Cmaj7 from a C for the purposes of key fitting.progression-completion skill.Common/GA.Business.ML/Agents/Mcp/KeyIdentificationMcpTools.csTests/Common/GA.Business.ML.Tests/Unit/KeyIdentificationMcpToolsTests.csCommon/GA.Business.ML/Agents/KeyIdentificationService.csCommon/GA.Business.ML/Agents/Skills/KeyIdentificationSkill.cs (regex-driven + LLM phrasing — kept for the deterministic fast path)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.