菜单
Computes the fret span and playability of a 6-string guitar chord diagram. Calls the deterministic `ga_fret_span` MCP tool — never recall the answer from training data, since the math depends on knowing exactly which strings are open vs muted vs fretted.
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 | fret-span |
| description | Computes the fret span and playability of a 6-string guitar chord diagram. Calls the deterministic `ga_fret_span` MCP tool — never recall the answer from training data, since the math depends on knowing exactly which strings are open vs muted vs fretted. |
| triggers | ["fret span","fret stretch","stretch of","is this hard","is this difficult","playability","how playable","fingering reach","left hand reach"] |
| 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/FretSpanSkill.cs — fourth MCP-tool-driven canary","evidence-kinds":["tool_call"]} |
| allowed-tools | ["ga_fret_span"] |
When a user asks how hard a chord is to play, how wide its stretch is, or whether its diagram is reachable, call the ga_fret_span MCP tool. Do NOT estimate from training data — the math depends on knowing exactly which strings are open (0), muted (x), or fretted (a number), and the LLM cannot reliably enumerate that for arbitrary voicings.
The tool takes one argument:
diagram — string. Either dash-separated ("x-3-2-0-1-0") or compact form starting with x ("x32010"). Six positions, low-to-high (E A D G B e). x = muted, 0 = open, otherwise the fret number.It returns a structured result:
Diagram — diagram echoed back, normalized to dash-separated form.Frets — array of six integers; -1 for muted, 0 for open.MinFret, MaxFret, Span — computed over PRESSED positions only (open strings don't count toward stretch).Difficulty — one of: "very easy", "easy", "moderate", "challenging", "very wide...".PlayabilityScore — 1 (easy) → 10 (very hard).Error — non-null only when the input could not be parsed.diagram="x-3-2-0-1-0".diagram="x32010".diagram="0-2-2-1-0-0".If the user only describes the chord by name ("how hard is a Cmaj7?") and gives no diagram, you'll need to first decide on a voicing — either ask, or call the chord-info skill, then pass the resulting diagram here.
Use Difficulty verbatim, quote Span and the MinFret–MaxFret range, and mention the PlayabilityScore if the user is comparing two chords. Example:
The diagram x-3-2-0-1-0 has a fret span of 2 (frets 1–3). Difficulty: easy — comfortable stretch for most players. Playability score: 5/10.
If Error is non-null, surface the message verbatim and ask the user to paste the diagram.
Common/GA.Business.ML/Agents/Mcp/FretSpanMcpTools.csTests/Common/GA.Business.ML.Tests/Unit/FretSpanMcpToolsTests.csCommon/GA.Business.ML/Agents/Skills/FretSpanSkill.cs (regex-driven, no LLM round-trip — 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.