[skills-eval] dotnet-ai: 5 skills, 12% pass — 1 P1, 3 to strengthen, 1 keep

## Context — cross-family skill evaluation: `dotnet-ai`

This issue is **self-contained**: it captures everything a skill author needs to act on the `dotnet-ai` plugin without opening the full report.

**What this measures.** Every runnable skill in `dotnet/skills` was run through [Vally](https://github.com/microsoft/evaluate) (0.7) on a **cross-family matrix**: 5 executor model families — `opus-4.8`, `gpt-5.5`, `sonnet-4.6`, `haiku-4.5`, `mai-flash` — each judged by a **different family** (judge ≠ executor; default judge = latest Opus, or GPT when Opus is the executor). For every skill, a **skilled** run is compared against a **baseline** (no-skill) run and scored per executor. This removes single-model and self-judging bias, so a skill that only helps one model family — or only its own family's judge — is visible.

- **Data source:** cross-family CI grid (run `29228914412` + backfills) — 5 executors × 85 runnable skills, **419 scored cells** over 84 skills.
- **Row grain:** one row per **skill**, aggregated across its (up to 5) executor cells. `avgN` is the mean trial count behind the cells (trials 1–17; higher = more statistically trustworthy). `thin-N` flags directional-only rows.

### `dotnet-ai` at a glance (portfolio scorecard)

| Plugin | Skills | Cells | Pass | Impact | Tie-trials | Err | avg ΔTok | avg ΔTurns | avg ΔTools | Headline |
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | --- |
| **dotnet-ai** | 5 | 25 | 12% | **0.489** | 10 | 0 | +16,639 | **−0.14** | **−0.48** | Underrated: high impact, efficient, low pass |

**Insights.** 5 skill(s); mean impact **0.49**; 1/5 help ≥1 frontier model. No frontier-validated exemplar. Weak-model-only wins (frontier misses): `mcp-csharp-create`.

**Address first:** `technology-selection` — cost.

### How to read the table

Each skill is scored **skilled vs. baseline** on these axes:

| Signal | Column | What it means | Good |
| --- | --- | --- | --- |
| Breadth | `Families ✓` (n/5) | How many of the **5 model families** the skill helps (per-family pass count, max `5/5`) | 4–5 / 5 |
| Where | `Passed on` | *Which* families passed. **Frontier = latest Opus + latest GPT** are **bold**; Sonnet 4.6 / Haiku 4.5 / MAI Flash are mid/low-weight | frontier ✓ |
| Magnitude | `Impact` (−1…+1) | How strongly the judge prefers *skilled* over *baseline* | ≥ 0.4 |
| Decisiveness | `Ties▵` | Trials where the judge saw **no difference** → skill is *inert* | low |
| Safety | `Loss▵` | Trials where **skilled was WORSE** than baseline → skill misfires | ~0 |
| Reliability | `Err` | Trials that errored/crashed in setup or judging | 0 |
| Efficiency | `ΔTok` / `ΔTurns` / `ΔTools` | Extra tokens / agent turns / tool calls vs baseline | ≤ 0 |
| Confidence | `avgN` | Mean trials behind the verdict; low N = directional only | ≥ 3 |
| Invocation | `Call%` | Share of skilled trials where the model actually **invoked the skill** | ~100% |

> **`Families ✓` is cell-level (max `5/5`); `Ties▵`/`Loss▵` are trial-level tallies summed across *all* families** (including the ones where the skill failed). A high `Families ✓` next to non-zero `Loss▵` is not a contradiction — see `Passed on` and the Action text for where losses landed.

**Action buckets** (each skill has one primary action; `[flags]` note secondary concerns):

| Bucket | Priority | Meaning |
| --- | --- | --- |
| FIX-RELIABILITY | 🔴 P0 | Errored trials / no verdict — stabilize the harness before trusting the score |
| FIX-DISCOVERY | 🔴 P0 | Model doesn't invoke it (`Call% < 50%`) — a triggering/description problem |
| FIX-REGRESSION | 🔴 P0 | Skilled is worse than baseline on many trials — the skill misfires |
| ADD-DECISIVENESS | 🟠 P1 | Called ~100% but ties dominate, ~0 impact — inert; needs sharper behavioral steps |
| TRIM-COST | 🟠 P1 | Passes but with heavy token/turn overhead — trim verbosity |
| EXEMPLAR | 🟢 keep | Broad, strong, reliable win — use as a template |
| EFFICIENT-WIN | 🟢 protect | Wins *and* cuts turns/tools — the ideal shape |
| KEEP-POLISH | 🟢 | Solid majority win; minor polish + more trials |
| STRENGTHEN | 🟡 P2 | Marginal/mixed lift — sharpen triggers & success criteria |

### Per-skill actions

| Skill | Families ✓ | Passed on (frontier **bold**) | Impact | Ties▵ | Loss▵ | Err | avgN | Call% | ΔTok | ΔTurns | ΔTools | Action |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `mcp-csharp-test` | 0/5 | — | 0.65 | 0 | 1 | 0 | 2.8 | 87% | -36,898 | -0.73 | -0.87 | **STRENGTHEN** · 🟡 **Marginal/mixed** (passes 0/5). Diagnosis: misses both frontier models — likely assumes context they solve unaided. Try: (1) sharpen the trigger so it fires only where it wins; (2) add 1–2 opinionated, concrete steps that change behaviour; (3) add trials to separate signal from noise. If frontier models never benefit, scope it explicitly to weaker models or reconsider its value. *([both-frontier-miss])* |
| `technology-selection` | 1/5 | **GPT** | 0.57 | 1 | 0 | 0 | 3.6 | 100% | +208,946 | +3.73 | +3.47 | **TRIM-COST** · 🟠 **Passes but heavy (+208,946 tok).** Value is real; cost isn't justified. Trim: (1) cut redundant/whole-file reads — point to specific sections; (2) replace "explore everything" with a targeted checklist; (3) move deep reference material behind links instead of inlining it. *([frontier-miss], [costly])* |
| `mcp-csharp-publish` | 0/5 | — | 0.56 | 1 | 1 | 0 | 3 | 100% | -18,308 | -0.93 | -1.47 | **STRENGTHEN** · 🟡 **Marginal/mixed** (passes 0/5). Diagnosis: mostly *ties* — too generic/non-prescriptive. Try: (1) sharpen the trigger so it fires only where it wins; (2) add 1–2 opinionated, concrete steps that change behaviour; (3) add trials to separate signal from noise. If frontier models never benefit, scope it explicitly to weaker models or reconsider its value. *([both-frontier-miss])* |
| `mcp-csharp-create` | 2/5 | Sonnet, Haiku | 0.40 | 2 | 2 | 0 | 2.6 | 100% | -94,279 | -4.3 | -5.53 | **EFFICIENT-WIN** · ✅ **Better *and* cheaper.** Wins on Sonnet, Haiku while saving 4.3 turns, 5.53 tools, 94,279 tok. What's good: it adds value without bloat — the ideal shape. Protect the brevity; don't let it grow. ⚠️ **But both frontier models miss and regress** — this may only be helping mid/low-weight models. Treat as a weak-model win, not a universal one; check the frontier trajectories before templating. *([both-frontier-miss], [frontier-regressed], [efficient])* |
| `mcp-csharp-debug` | 0/5 | — | 0.27 | 6 | 1 | 0 | 3 | 100% | +23,734 | +1.53 | +2 | **STRENGTHEN** · 🟡 **Marginal/mixed** (passes 0/5). Diagnosis: mostly *ties* — too generic/non-prescriptive. Try: (1) sharpen the trigger so it fires only where it wins; (2) add 1–2 opinionated, concrete steps that change behaviour; (3) add trials to separate signal from noise. If frontier models never benefit, scope it explicitly to weaker models or reconsider its value. *([both-frontier-miss], [frontier-regressed])* |

---

_{Generated from the cross-family Call-to-Action report (`CALL-TO-ACTION.md` §4–§5; companion `IMPACT-ANALYSIS.md`). Regenerate the underlying tables with `node deep-metrics.mjs "$env:TEMP\cf-ci" agg-ci` → `node gen-cta-tables.mjs agg-ci`. Numbers are directional where `avgN` is low; treat single-trial cells as hypotheses to confirm with more runs.}