菜单
Computes the simple interval between two named pitches (e.g. C to G is a perfect fifth). Calls the deterministic `ga_interval_compute` MCP tool — never recall an answer from training data.
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
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 | interval |
| description | Computes the simple interval between two named pitches (e.g. C to G is a perfect fifth). Calls the deterministic `ga_interval_compute` MCP tool — never recall an answer from training data. |
| triggers | ["interval between","interval from","what is the interval","distance from","distance between","how many semitones","semitones from","semitones between"] |
| license | internal |
| compatibility | {"agent-framework":">=1.0.0-preview","microsoft-extensions-ai":">=10.5.1"} |
| metadata | {"authoring-style":"tool-driven","origin":"first MCP-tool-driven canary; replaces direct C# IntervalSkill in the SKILL.md path","evidence-kinds":["tool_call"]} |
| allowed-tools | ["ga_interval_compute"] |
When a user asks for the interval, distance, or semitone count between two named pitches, you MUST call the ga_interval_compute MCP tool. Do NOT compute the answer from training knowledge — the tool is deterministic and the model is not.
The tool takes two arguments:
lowerNote — string, e.g. "C", "F#", "Bb". Case-insensitive.upperNote — string, same notation.The tool returns a structured result with these fields:
Name — short interval name (e.g. "P5", "m3").Quality — long form: "perfect", "major", "minor", "augmented", "diminished".Size — long form: "unison", "second", "third", ..., "octave".Semitones — integer 0–12.Error — non-null only when input could not be parsed.Map the user's phrasing to argument order:
lowerNote="C", upperNote="G".lowerNote="F#", upperNote="D". Pass both in order even when the lower is alphabetically later — the tool computes the simple interval correctly.lowerNote="A", upperNote="E". Read out the Semitones field to answer.Use the tool's Quality and Size words verbatim, then quote the short Name and Semitones count. Example:
From C to G is a perfect fifth (P5, 7 semitones).
If Error is non-null, surface the message verbatim and ask the user to clarify the note names.
If the user provides only one note, or names a chord rather than two notes (e.g. "interval of A", "what's the interval in a Cmaj7"), do NOT call the tool with placeholder values — ask for the missing pitch first. Example response: "Could you give me both notes? E.g. 'interval from C to G' or 'distance between F# and A'."
C and D (which gives a major second), then in the answer flag the octave assumption explicitly: "I'm treating 'high D' as D one octave above C, so the compound interval is a major ninth (M2 plus an octave). If you meant a different D, let me know." Always state which D you assumed.Common/GA.Business.ML/Agents/Mcp/IntervalMcpTools.csTests/Common/GA.Business.ML.Tests/Unit/IntervalMcpToolsTests.csCommon/GA.Business.ML/Agents/Skills/IntervalSkill.cs (regex-driven, no LLM round-trip — kept for the deterministic fast path)