selftune 0.2.9 → 0.2.10

package/skill/Workflows/Evolve.md

@@ -7,6 +7,7 @@ natural-language queries without breaking existing triggers.
 ## When to Invoke
 
 Invoke this workflow when the user requests any of the following:
+
 - Improving or evolving a skill's trigger coverage
 - Fixing undertriggering or missed queries for a skill
 - Optimizing a skill description based on usage data
@@ -20,27 +21,27 @@ selftune evolve --skill <name> --skill-path <path> [options]
 
 ## Options
 
-| Flag | Description | Default |
-|------|-------------|---------|
-| `--skill <name>` | Skill name | Required |
-| `--skill-path <path>` | Path to the skill's SKILL.md | Required |
-| `--eval-set <path>` | Pre-built eval set JSON | Auto-generated from logs |
-| `--agent <name>` | Agent CLI to use (claude, codex, opencode) | Auto-detected |
-| `--dry-run` | Propose and validate without deploying | Off |
-| `--confidence <n>` | Minimum confidence threshold (0-1) | 0.6 |
-| `--max-iterations <n>` | Maximum retry iterations | 3 |
-| `--validation-model <model>` | Model for trigger-check validation LLM calls | `haiku` |
-| `--pareto` | Generate multiple candidates per iteration | Off |
-| `--candidates <n>` | Number of candidates per iteration (with `--pareto`) | 3 |
-| `--token-efficiency` | Optimize for token efficiency in proposals | Off |
-| `--with-baseline` | Include a no-skill baseline comparison | Off |
-| `--cheap-loop` | Use cheap models for loop, expensive for final gate | On |
-| `--full-model` | Use full-cost model throughout (disables cheap-loop) | Off |
-| `--verbose` | Print detailed progress during evolution | Off |
-| `--gate-model <model>` | Model for final gate validation | `sonnet` (when `--cheap-loop`) |
-| `--proposal-model <model>` | Model for proposal generation LLM calls | None |
-| `--sync-first` | Refresh source-truth telemetry before generating evals/failure patterns | Off |
-| `--sync-force` | Force a full source rescan during `--sync-first` | Off |
+| Flag                         | Description                                                             | Default                        |
+| ---------------------------- | ----------------------------------------------------------------------- | ------------------------------ |
+| `--skill <name>`             | Skill name                                                              | Required                       |
+| `--skill-path <path>`        | Path to the skill's SKILL.md                                            | Required                       |
+| `--eval-set <path>`          | Pre-built eval set JSON                                                 | Auto-generated from logs       |
+| `--agent <name>`             | Agent CLI to use (claude, codex, opencode)                              | Auto-detected                  |
+| `--dry-run`                  | Propose and validate without deploying                                  | Off                            |
+| `--confidence <n>`           | Minimum confidence threshold (0-1)                                      | 0.6                            |
+| `--max-iterations <n>`       | Maximum retry iterations                                                | 3                              |
+| `--validation-model <model>` | Model for trigger-check validation LLM calls                            | `haiku`                        |
+| `--pareto`                   | Generate multiple candidates per iteration                              | Off                            |
+| `--candidates <n>`           | Number of candidates per iteration (with `--pareto`)                    | 3                              |
+| `--token-efficiency`         | Optimize for token efficiency in proposals                              | Off                            |
+| `--with-baseline`            | Include a no-skill baseline comparison                                  | Off                            |
+| `--cheap-loop`               | Use cheap models for loop, expensive for final gate                     | On                             |
+| `--full-model`               | Use full-cost model throughout (disables cheap-loop)                    | Off                            |
+| `--verbose`                  | Print detailed progress during evolution                                | Off                            |
+| `--gate-model <model>`       | Model for final gate validation                                         | `sonnet` (when `--cheap-loop`) |
+| `--proposal-model <model>`   | Model for proposal generation LLM calls                                 | None                           |
+| `--sync-first`               | Refresh source-truth telemetry before generating evals/failure patterns | Off                            |
+| `--sync-force`               | Force a full source rescan during `--sync-first`                        | Off                            |
 
 ## Output Format
 
@@ -54,7 +55,7 @@ See `references/logs.md` for the audit log schema.
   "proposal_id": "evolve-pptx-1709125200000",
   "skill_name": "pptx",
   "iteration": 1,
-  "original_pass_rate": 0.70,
+  "original_pass_rate": 0.7,
   "proposed_pass_rate": 0.92,
   "regression_count": 0,
   "confidence": 0.85,
@@ -67,11 +68,11 @@ See `references/logs.md` for the audit log schema.
 
 The evolution process writes multiple audit entries:
 
-| Action | When | Key details |
-|--------|------|-------------|
-| `created` | Proposal generated | `details` contains `original_description:` prefix |
-| `validated` | Proposal tested against eval set | `eval_snapshot` with before/after pass rates |
-| `deployed` | Updated SKILL.md written to disk | `eval_snapshot` with final rates |
+| Action      | When                             | Key details                                       |
+| ----------- | -------------------------------- | ------------------------------------------------- |
+| `created`   | Proposal generated               | `details` contains `original_description:` prefix |
+| `validated` | Proposal tested against eval set | `eval_snapshot` with before/after pass rates      |
+| `deployed`  | Updated SKILL.md written to disk | `eval_snapshot` with final rates                  |
 
 ## Parsing Instructions
 
@@ -97,51 +98,45 @@ The evolution process writes multiple audit entries:
 
 Before running the evolve command, use the `AskUserQuestion` tool to present structured configuration options. If the user responds with "use defaults" or similar shorthand, skip to step 1 using the recommended defaults. If the user cancels, stop and do not continue.
 
-Use `AskUserQuestion` with these questions (max 4 per call — split if needed):
-
-**Call 1:**
-
-```json
-{
-  "questions": [
-    {
-      "question": "Execution Mode",
-      "options": ["Dry run — preview without deploying (recommended for first run)", "Live — validate and deploy if improved"]
-    },
-    {
-      "question": "Model Tier (see SKILL.md reference)",
-      "options": ["Fast (haiku) — cheapest, ~2s/call (recommended with cheap-loop)", "Balanced (sonnet) — good quality, ~5s/call", "Best (opus) — highest quality, ~10s/call"]
-    },
-    {
-      "question": "Cost Optimization",
-      "options": ["Cheap loop — haiku for iteration, sonnet for final gate (recommended)", "Single model — use one model throughout"]
-    },
-    {
-      "question": "Advanced Options",
-      "options": ["Defaults (0.6 confidence, 3 iterations, single candidate) (recommended)", "Stricter (0.7 confidence, 5 iterations)", "Pareto mode (multiple candidates per iteration)"]
-    }
-  ]
-}
-```
-
-If `AskUserQuestion` is not available, fall back to presenting these as inline numbered options.
+Ask one `AskUserQuestion` at a time in this order:
+
+1. `Execution Mode`
+   Options:
+   - `Dry run — preview without deploying (recommended for first run)`
+   - `Live — validate and deploy if improved`
+2. `Model Tier (see SKILL.md reference)`
+   Options:
+   - `Fast (haiku) — cheapest, ~2s/call (recommended with cheap-loop)`
+   - `Balanced (sonnet) — good quality, ~5s/call`
+   - `Best (opus) — highest quality, ~10s/call`
+3. `Cost Optimization`
+   Options:
+   - `Cheap loop — haiku for iteration, sonnet for final gate (recommended)`
+   - `Single model — use one model throughout`
+4. `Advanced Options`
+   Options:
+   - `Defaults (0.6 confidence, 3 iterations, single candidate) (recommended)`
+   - `Stricter (0.7 confidence, 5 iterations)`
+   - `Pareto mode (multiple candidates per iteration)`
+
+If `AskUserQuestion` is not available or Claude does not invoke it, fall back to presenting the same choices as inline numbered options.
 
 If the user cancels, stop -- do not proceed with defaults. If the user selects "use defaults", skip to step 1 with recommended defaults.
 
 After the user responds, parse their selections and map each choice to the corresponding CLI flags:
 
-| Selection | CLI Flag |
-|-----------|----------|
-| 1a (dry run) | `--dry-run` |
-| 1b (live) | _(no flag)_ |
-| 2a (haiku) | `--validation-model haiku` |
-| 2b (sonnet) | `--validation-model sonnet` |
-| 2c (opus) | `--validation-model opus` |
-| 3a (cheap loop) | `--cheap-loop` |
-| 3b (single model) | _(no flag)_ |
-| Custom confidence | `--confidence <value>` |
-| Custom iterations | `--max-iterations <value>` |
-| 6b (pareto) | `--pareto` |
+| Selection         | CLI Flag                    |
+| ----------------- | --------------------------- |
+| 1a (dry run)      | `--dry-run`                 |
+| 1b (live)         | _(no flag)_                 |
+| 2a (haiku)        | `--validation-model haiku`  |
+| 2b (sonnet)       | `--validation-model sonnet` |
+| 2c (opus)         | `--validation-model opus`   |
+| 3a (cheap loop)   | `--cheap-loop`              |
+| 3b (single model) | _(no flag)_                 |
+| Custom confidence | `--confidence <value>`      |
+| Custom iterations | `--max-iterations <value>`  |
+| 6b (pareto)       | `--pareto`                  |
 
 Show a confirmation summary to the user:
 
@@ -161,6 +156,7 @@ Build the CLI command string with all selected flags and continue to step 1.
 ### 1. Read Evolution Context
 
 Before running, read `~/.selftune/memory/context.md` for session context:
+
 - Active evolutions and their current status
 - Known issues from previous runs
 - Last update timestamp
@@ -197,6 +193,7 @@ evolution cannot reliably measure improvement.
 ### 4. Extract Failure Patterns
 
 The command groups missed queries by invocation type:
+
 - Missed explicit: description is broken (rare, high priority)
 - Missed implicit: description is too narrow (common, evolve target)
 - Missed contextual: description lacks domain vocabulary (evolve target)
@@ -227,6 +224,7 @@ For body evolution (`evolve body`), only the size constraint applies.
 
 An LLM generates a candidate description that would catch the missed
 queries. The candidate:
+
 - Preserves existing trigger phrases that work
 - Adds new phrases covering missed patterns
 - Maintains the description's structure and tone
@@ -234,6 +232,7 @@ queries. The candidate:
 ### 6. Validate Against Eval Set
 
 The candidate is tested against the full eval set:
+
 - Must improve overall pass rate
 - Must not regress more than 5% on previously-passing entries
 - Must exceed the `--confidence` threshold
@@ -246,14 +245,14 @@ with adjusted proposals.
 When summarizing an evolution run, include these aggregate metrics rather
 than only saying "passed" or "failed":
 
-| Metric | Meaning |
-|--------|---------|
-| `original_pass_rate` | Baseline pass rate before the proposal |
-| `proposed_pass_rate` | Pass rate after applying the proposal |
-| `regression_count` | Eval entries that passed before and failed after |
-| `net_change` | Total passes gained minus regressions introduced |
-| `iteration` / `iterations_used` | Which retry produced the current candidate |
-| `baseline_lift` | Additional lift over the no-skill baseline when `--with-baseline` is enabled |
+| Metric                          | Meaning                                                                      |
+| ------------------------------- | ---------------------------------------------------------------------------- |
+| `original_pass_rate`            | Baseline pass rate before the proposal                                       |
+| `proposed_pass_rate`            | Pass rate after applying the proposal                                        |
+| `regression_count`              | Eval entries that passed before and failed after                             |
+| `net_change`                    | Total passes gained minus regressions introduced                             |
+| `iteration` / `iterations_used` | Which retry produced the current candidate                                   |
+| `baseline_lift`                 | Additional lift over the no-skill baseline when `--with-baseline` is enabled |
 
 These metrics explain whether the proposal is genuinely better, merely
 different, or too risky to deploy.
@@ -264,6 +263,7 @@ If `--dry-run`, the proposal is printed but not deployed. The audit log
 still records `created` and `validated` entries for review.
 
 If deploying:
+
 1. The current SKILL.md is backed up to `SKILL.md.bak`
 2. The updated description is written to SKILL.md
 3. A `deployed` entry is logged to the evolution audit
@@ -271,6 +271,7 @@ If deploying:
 ### 8. Update Memory
 
 After evolution completes (deploy or dry-run), the memory writer updates:
+
 - `~/.selftune/memory/context.md` -- records the evolution outcome and current state
 - `~/.selftune/memory/decisions.md` -- logs the decision rationale and proposal details
 
@@ -281,13 +282,13 @@ even after a context window reset.
 
 The evolution loop stops when any of these conditions is met (priority order):
 
-| # | Condition | Meaning |
-|---|-----------|---------|
-| 1 | **Converged** | Pass rate >= 0.95 |
-| 2 | **Max iterations** | Reached `--max-iterations` limit |
-| 3 | **Low confidence** | Proposal confidence below `--confidence` threshold |
-| 4 | **Plateau** | Pass rate unchanged across 3 consecutive iterations |
-| 5 | **Continue** | None of the above -- keep iterating |
+| #   | Condition          | Meaning                                             |
+| --- | ------------------ | --------------------------------------------------- |
+| 1   | **Converged**      | Pass rate >= 0.95                                   |
+| 2   | **Max iterations** | Reached `--max-iterations` limit                    |
+| 3   | **Low confidence** | Proposal confidence below `--confidence` threshold  |
+| 4   | **Plateau**        | Pass rate unchanged across 3 consecutive iterations |
+| 5   | **Continue**       | None of the above -- keep iterating                 |
 
 ## Cheap Loop Mode
 
@@ -296,6 +297,7 @@ and only uses an expensive model (sonnet) for a final gate validation before
 deploying. This reduces cost while maintaining deployment quality.
 
 When `--cheap-loop` is set:
+
 - `--proposal-model` defaults to `haiku`
 - `--validation-model` defaults to `haiku`
 - `--gate-model` defaults to `sonnet`

package/skill/Workflows/EvolveBody.md

@@ -12,21 +12,23 @@ selftune evolve body --skill <name> --skill-path <path> --target <target> [optio
 
 ## Options
 
-| Flag | Description | Default |
-|------|-------------|---------|
-| `--skill <name>` | Skill name | Required |
-| `--skill-path <path>` | Path to the skill's SKILL.md | Required |
-| `--target <type>` | Evolution target: `routing` or `body` | Required |
-| `--teacher-agent <name>` | Agent CLI for proposal generation | Auto-detected |
-| `--student-agent <name>` | Agent CLI for validation | Same as teacher |
-| `--teacher-model <flag>` | Model flag for teacher (e.g. `opus`) | Agent default |
-| `--student-model <flag>` | Model flag for student (e.g. `haiku`) | Agent default |
-| `--eval-set <path>` | Pre-built eval set JSON | Auto-generated from logs |
-| `--dry-run` | Propose and validate without deploying | Off |
-| `--max-iterations <n>` | Maximum refinement iterations | 3 |
-| `--task-description <text>` | Context for the evolution goal | None |
-| `--validation-model <model>` | Model for trigger-check validation calls (overrides `--student-model` for validation) | None |
-| `--few-shot <paths>` | Comma-separated paths to example SKILL.md files | None |
+| Flag                         | Description                                                                           | Default                  |
+| ---------------------------- | ------------------------------------------------------------------------------------- | ------------------------ |
+| `--skill <name>`             | Skill name                                                                            | Required                 |
+| `--skill-path <path>`        | Path to the skill's SKILL.md                                                          | Required                 |
+| `--target <type>`            | Evolution target: `routing` or `body`                                                 | Required                 |
+| `--teacher-agent <name>`     | Agent CLI for proposal generation                                                     | Auto-detected            |
+| `--student-agent <name>`     | Agent CLI for validation                                                              | Same as teacher          |
+| `--teacher-model <flag>`     | Model flag for teacher                                                                | `opus`                   |
+| `--student-model <flag>`     | Model flag for student                                                                | `haiku`                  |
+| `--eval-set <path>`          | Pre-built eval set JSON                                                               | Auto-generated from logs |
+| `--dry-run`                  | Propose and validate without deploying                                                | Off                      |
+| `--max-iterations <n>`       | Maximum refinement iterations                                                         | 3                        |
+| `--task-description <text>`  | Context for the evolution goal                                                        | None                     |
+| `--validation-model <model>` | Model for trigger-check validation calls (overrides `--student-model` for validation) | None                     |
+| `--teacher-effort <level>`   | Effort level for teacher LLM: `low`, `medium`, `high`, `max`                          | `high`                   |
+| `--review`                   | Run `evolution-reviewer` subagent as Gate 4 before deployment                         | Off                      |
+| `--few-shot <paths>`         | Comma-separated paths to example SKILL.md files                                       | None                     |
 
 ## Evolution Targets
 
@@ -46,11 +48,12 @@ teacher generates a complete replacement, validated through 3 gates.
 
 Every proposal passes through three sequential gates:
 
-| Gate | Type | What it checks | Cost |
-|------|------|---------------|------|
-| **Gate 1: Structural** | Pure code | YAML frontmatter present, `# Title` exists, `## Workflow Routing` preserved if original had one | Free |
-| **Gate 2: Trigger Accuracy** | Student LLM | YES/NO trigger check per eval entry on the extracted description | Cheap |
-| **Gate 3: Quality** | Student LLM | Body clarity and completeness score (0.0-1.0) | Cheap |
+| Gate                          | Type        | What it checks                                                                                  | Cost     |
+| ----------------------------- | ----------- | ----------------------------------------------------------------------------------------------- | -------- |
+| **Gate 1: Structural**        | Pure code   | YAML frontmatter present, `# Title` exists, `## Workflow Routing` preserved if original had one | Free     |
+| **Gate 2: Trigger Accuracy**  | Student LLM | YES/NO trigger check per eval entry on the extracted description                                | Cheap    |
+| **Gate 3: Quality**           | Student LLM | Body clarity and completeness score (0.0-1.0)                                                   | Cheap    |
+| **Gate 4: Reviewer** (opt-in) | Subagent    | `evolution-reviewer` multi-turn review — reads files, checks evidence, APPROVE/REJECT verdict   | Moderate |
 
 If any gate fails, the teacher receives structured feedback and generates
 a refined proposal. This repeats up to `--max-iterations` times.
@@ -62,32 +65,32 @@ a refined proposal. This repeats up to `--max-iterations` times.
 Before running evolve-body, use the `AskUserQuestion` tool to present structured configuration options.
 If the user says "use defaults" or similar, skip to step 1 with recommended defaults. If the user cancels, abort the workflow -- do not proceed with defaults.
 
-Use `AskUserQuestion` with these questions:
-
-```json
-{
-  "questions": [
-    {
-      "question": "Evolution Target",
-      "options": ["Routing table — optimize workflow routing only (recommended)", "Full body — rewrite entire SKILL.md (more aggressive)"]
-    },
-    {
-      "question": "Execution Mode",
-      "options": ["Dry run — preview without deploying (recommended)", "Live — validate and deploy if improved"]
-    },
-    {
-      "question": "Teacher Model (generates proposals)",
-      "options": ["Balanced (sonnet) — good quality (recommended)", "Best (opus) — highest quality, slower"]
-    },
-    {
-      "question": "Student Model & Iterations",
-      "options": ["Fast (haiku) + 3 iterations (recommended)", "Balanced (sonnet) + 3 iterations", "Fast (haiku) + 5 iterations"]
-    }
-  ]
-}
-```
-
-If `AskUserQuestion` is not available, fall back to presenting these as inline numbered options.
+Ask one `AskUserQuestion` at a time in this order:
+
+1. `Evolution Target`
+   Options:
+   - `Routing table — optimize workflow routing only (recommended)`
+   - `Full body — rewrite entire SKILL.md (more aggressive)`
+2. `Execution Mode`
+   Options:
+   - `Dry run — preview without deploying (recommended)`
+   - `Live — validate and deploy if improved`
+3. `Teacher Model (generates proposals)`
+   Options:
+   - `Best (opus + high effort) — thinking-enabled, highest quality (recommended)`
+   - `Balanced (sonnet) — good quality, faster`
+4. `Student Model & Iterations`
+   Options:
+   - `Fast (haiku) + 3 iterations (recommended)`
+   - `Balanced (sonnet) + 3 iterations`
+   - `Fast (haiku) + 5 iterations`
+5. `Teacher Effort (thinking depth for proposal generation)`
+   Options:
+   - `High — extended thinking for better proposals (recommended)`
+   - `Max — maximum thinking depth (Opus 4.6 only, slower)`
+   - `Medium — standard reasoning`
+
+If `AskUserQuestion` is not available or Claude does not invoke it, fall back to presenting the same choices as inline numbered options.
 
 After the user responds, show a confirmation summary:
 
@@ -95,7 +98,8 @@ After the user responds, show a confirmation summary:
 Configuration Summary:
   Target:        routing
   Mode:          dry-run
-  Teacher model: sonnet
+  Teacher model: opus
+  Teacher effort: high
   Student model: haiku
   Iterations:    3
   Few-shot:      none
@@ -106,6 +110,7 @@ Proceeding...
 ### 1. Parse Current Skill
 
 The command reads SKILL.md and splits it into sections using `parseSkillSections()`:
+
 - Frontmatter (YAML between `---` markers)
 - Title (first `# Heading`)
 - Description (text between title and first `## Section`)
@@ -125,6 +130,7 @@ pipeline. See `references/invocation-taxonomy.md`.
 ### 4. Generate Proposal (Teacher)
 
 The teacher LLM generates a proposal based on the target:
+
 - **routing**: Optimized `## Workflow Routing` markdown table
 - **body**: Complete SKILL.md body replacement
 
@@ -138,6 +144,7 @@ failure details and generates a refined proposal.
 ### 6. Deploy or Preview
 
 If `--dry-run`, prints the proposal without deploying. Otherwise:
+
 1. Creates a timestamped backup of the current SKILL.md
 2. Applies the change: `replaceSection()` for routing, `replaceBody()` for body
 3. Records audit entries
@@ -146,13 +153,17 @@ If `--dry-run`, prints the proposal without deploying. Otherwise:
 ## Common Patterns
 
 **"Evolve the routing table for the Research skill"**
+
 > `selftune evolve body --skill Research --skill-path ~/.claude/skills/Research/SKILL.md --target routing`
 
 **"Rewrite the entire skill body"**
+
 > `selftune evolve body --skill Research --skill-path ~/.claude/skills/Research/SKILL.md --target body --dry-run`
 
 **"Use a stronger model for generation"**
+
 > `selftune evolve body --skill pptx --skill-path /path/SKILL.md --target body --teacher-model opus --student-model haiku`
 
 **"Preview what would change"**
+
 > Always start with `--dry-run` to review the proposal before deploying.

package/skill/Workflows/Grade.md

@@ -11,13 +11,13 @@ selftune grade --skill <name> [options]
 
 ## Options
 
-| Flag | Description | Default |
-|------|-------------|---------|
-| `--skill <name>` | Skill name to grade | Required |
-| `--expectations "..."` | Explicit expectations (semicolon-separated) | Auto-derived |
-| `--evals-json <path>` | Pre-built eval set JSON file | None |
-| `--eval-id <n>` | Specific eval ID to grade from the eval set | None |
-| `--agent <name>` | Agent CLI to use (claude, codex, opencode) | Auto-detected |
+| Flag                   | Description                                 | Default       |
+| ---------------------- | ------------------------------------------- | ------------- |
+| `--skill <name>`       | Skill name to grade                         | Required      |
+| `--expectations "..."` | Explicit expectations (semicolon-separated) | Auto-derived  |
+| `--evals-json <path>`  | Pre-built eval set JSON file                | None          |
+| `--eval-id <n>`        | Specific eval ID to grade from the eval set | None          |
+| `--agent <name>`       | Agent CLI to use (claude, codex, opencode)  | Auto-detected |
 
 ## Output Format
 
@@ -30,14 +30,10 @@ for the full schema. Key fields:
   "skill_name": "pptx",
   "transcript_path": "~/.claude/projects/.../abc123.jsonl",
   "graded_at": "2026-02-28T12:00:00Z",
-  "expectations": [
-    { "text": "...", "passed": true, "evidence": "..." }
-  ],
+  "expectations": [{ "text": "...", "passed": true, "evidence": "..." }],
   "summary": { "passed": 2, "failed": 1, "total": 3, "pass_rate": 0.67 },
   "execution_metrics": { "tool_calls": {}, "total_tool_calls": 6, "errors_encountered": 0 },
-  "claims": [
-    { "claim": "...", "type": "factual", "verified": true, "evidence": "..." }
-  ],
+  "claims": [{ "claim": "...", "type": "factual", "verified": true, "evidence": "..." }],
   "eval_feedback": { "suggestions": [], "overall": "..." }
 }
 ```
@@ -82,6 +78,7 @@ fields. See `references/logs.md` for the telemetry format.
 ### 2. Read the Transcript
 
 Parse the JSONL file at `transcript_path`. Extract:
+
 - User messages (what was asked)
 - Assistant tool calls (what the agent did)
 - Tool results (what happened)
@@ -99,6 +96,7 @@ Ensure at least one Process expectation and one Quality expectation.
 
 Search both the telemetry record and the transcript for evidence per
 expectation. Mark as:
+
 - **PASS** if evidence exists and supports the expectation
 - **FAIL** if evidence is absent or contradicts the expectation
 
@@ -123,6 +121,7 @@ Write the full grading result to `grading.json` in the current directory.
 ### 8. Report Results
 
 Report to the user:
+
 - Pass rate (e.g., "2/3 passed, 67%")
 - Failed expectations with evidence
 - Notable claims
@@ -133,19 +132,23 @@ Keep the summary concise. The full details are in `grading.json`.
 ## Common Patterns
 
 **User asks to grade a skill session**
+
 > Run `selftune grade --skill <name>` with default expectations. Results are
 > written to `grading.json`. Read that file and report the pass rate and any
 > failures to the user.
 
 **User provides specific expectations**
+
 > Run `selftune grade --skill <name> --expectations "expect1;expect2;expect3"`.
 > Parse results and report.
 
 **User wants to grade from an eval set**
+
 > Run `selftune grade --skill <name> --evals-json path/to/evals.json`.
 > Optionally add `--eval-id N` for a specific scenario.
 
 **Agent detection override needed**
+
 > The grader auto-detects the agent CLI. If detection fails or the user
 > specifies an agent, pass `--agent <name>` to override.
 

package/skill/Workflows/ImportSkillsBench.md

@@ -18,12 +18,12 @@ selftune eval import --dir <path> --skill <name> --output <path> [options]
 
 ## Options
 
-| Flag | Description | Default |
-|------|-------------|---------|
-| `--dir <path>` | Path to SkillsBench tasks directory | Required |
-| `--skill <name>` | Target skill to match tasks against | Required |
-| `--output <path>` | Output eval set JSON file | Required |
-| `--match-strategy <type>` | Matching strategy: `exact` or `fuzzy` | `exact` |
+| Flag                      | Description                           | Default  |
+| ------------------------- | ------------------------------------- | -------- |
+| `--dir <path>`            | Path to SkillsBench tasks directory   | Required |
+| `--skill <name>`          | Target skill to match tasks against   | Required |
+| `--output <path>`         | Output eval set JSON file             | Required |
+| `--match-strategy <type>` | Matching strategy: `exact` or `fuzzy` | `exact`  |
 
 ## Match Strategies
 
@@ -108,10 +108,13 @@ corpus. Use the merged set with `selftune evolve --eval-set merged-evals.json`.
 ## Common Patterns
 
 **"Import SkillsBench tasks for Research"**
+
 > `selftune eval import --dir /path/tasks --skill Research --output bench-evals.json`
 
 **"Use fuzzy matching for broader coverage"**
+
 > `selftune eval import --dir /path/tasks --skill pptx --output bench-evals.json --match-strategy fuzzy`
 
 **"Enrich my eval set with external benchmarks"**
+
 > Import with `eval import`, then pass the output to `evolve --eval-set`.