@intentsolutionsio/skill-creator 5.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (39) hide show
  1. package/.claude-plugin/plugin.json +17 -0
  2. package/README.md +55 -0
  3. package/package.json +38 -0
  4. package/scripts/validate-skill.py +1132 -0
  5. package/skills/agent-creator/SKILL.md +305 -0
  6. package/skills/agent-creator/references/anthropic-agent-spec.md +89 -0
  7. package/skills/skill-creator/SKILL.md +267 -0
  8. package/skills/skill-creator/agents/analyzer.md +279 -0
  9. package/skills/skill-creator/agents/comparator.md +207 -0
  10. package/skills/skill-creator/agents/grader.md +228 -0
  11. package/skills/skill-creator/assets/eval_review.html +146 -0
  12. package/skills/skill-creator/eval-viewer/generate_review.py +471 -0
  13. package/skills/skill-creator/eval-viewer/viewer.html +1325 -0
  14. package/skills/skill-creator/references/advanced-eval-workflow.md +320 -0
  15. package/skills/skill-creator/references/anthropic-comparison.md +93 -0
  16. package/skills/skill-creator/references/ard-template.md +47 -0
  17. package/skills/skill-creator/references/creation-guide.md +305 -0
  18. package/skills/skill-creator/references/errors-template.md +27 -0
  19. package/skills/skill-creator/references/examples-template.md +40 -0
  20. package/skills/skill-creator/references/frontmatter-spec.md +531 -0
  21. package/skills/skill-creator/references/implementation-template.md +42 -0
  22. package/skills/skill-creator/references/output-patterns.md +193 -0
  23. package/skills/skill-creator/references/prd-template.md +55 -0
  24. package/skills/skill-creator/references/schemas.md +430 -0
  25. package/skills/skill-creator/references/source-of-truth.md +658 -0
  26. package/skills/skill-creator/references/validation-rules.md +528 -0
  27. package/skills/skill-creator/references/workflows.md +233 -0
  28. package/skills/skill-creator/scripts/__init__.py +0 -0
  29. package/skills/skill-creator/scripts/aggregate_benchmark.py +401 -0
  30. package/skills/skill-creator/scripts/generate_report.py +326 -0
  31. package/skills/skill-creator/scripts/improve_description.py +247 -0
  32. package/skills/skill-creator/scripts/package_skill.py +136 -0
  33. package/skills/skill-creator/scripts/quick_validate.py +103 -0
  34. package/skills/skill-creator/scripts/run_eval.py +344 -0
  35. package/skills/skill-creator/scripts/run_loop.py +329 -0
  36. package/skills/skill-creator/scripts/utils.py +47 -0
  37. package/skills/skill-creator/scripts/validate-skill.py +87 -0
  38. package/skills/skill-creator/templates/agent-template.md +99 -0
  39. package/skills/skill-creator/templates/skill-template.md +122 -0
@@ -0,0 +1,193 @@
1
+ # Skill Output Patterns
2
+
3
+ Reference for structuring skill output. Source: Anthropic best practices.
4
+
5
+ ---
6
+
7
+ ## Template Pattern
8
+
9
+ Generate output from predefined templates with variable substitution.
10
+
11
+ ### Strict Template (Low Degrees of Freedom)
12
+
13
+ Use when output format must be exact (API payloads, config files, compliance docs).
14
+
15
+ ```markdown
16
+ ## Instructions
17
+
18
+ Generate output using this exact template:
19
+
20
+ ```json
21
+ {
22
+ "name": "{project_name}",
23
+ "version": "{version}",
24
+ "scripts": {
25
+ "build": "{build_command}",
26
+ "test": "{test_command}"
27
+ }
28
+ }
29
+ ```
30
+
31
+ Replace placeholders with gathered values. Do not add extra fields.
32
+ ```
33
+
34
+ ### Flexible Template (Medium Degrees of Freedom)
35
+
36
+ Use when structure is defined but content is creative.
37
+
38
+ ```markdown
39
+ ## Instructions
40
+
41
+ Generate a report following this structure:
42
+
43
+ # {Title}
44
+
45
+ ## Summary
46
+ {2-3 sentence executive summary}
47
+
48
+ ## Findings
49
+ {Detailed findings - use tables, lists, or prose as appropriate}
50
+
51
+ ## Recommendations
52
+ {Prioritized list of action items}
53
+
54
+ Adapt section depth to the complexity of findings.
55
+ ```
56
+
57
+ ---
58
+
59
+ ## Examples Pattern
60
+
61
+ Provide input/output pairs that demonstrate expected behavior.
62
+
63
+ ### Inline Examples
64
+
65
+ ```markdown
66
+ ## Examples
67
+
68
+ ### Simple case
69
+ **Input**: `/skill-name auth.py`
70
+ **Output**:
71
+ ```
72
+ auth.py: 3 issues found
73
+ Line 15: SQL injection risk in query builder
74
+ Line 42: Hardcoded credential detected
75
+ Line 89: Missing input validation
76
+ ```
77
+
78
+ ### Complex case
79
+ **Input**: `/skill-name --deep src/`
80
+ **Output**:
81
+ ```
82
+ Deep scan: 12 files, 7 issues
83
+ CRITICAL (2): sql-injection, hardcoded-secret
84
+ WARNING (3): missing-validation, weak-hash, cors-wildcard
85
+ INFO (2): deprecated-api, unused-import
86
+ ```
87
+ ```
88
+
89
+ ### When to Use
90
+
91
+ - Always include at least 1 example
92
+ - Show both simple and complex cases
93
+ - Show edge cases (empty input, errors)
94
+ - Examples teach Claude the expected output format better than rules
95
+
96
+ ---
97
+
98
+ ## Visual Output Pattern
99
+
100
+ Generate HTML artifacts for rich visual output.
101
+
102
+ ```markdown
103
+ ## Instructions
104
+
105
+ ### Step 1: Gather Data
106
+ Collect the metrics and data points needed.
107
+
108
+ ### Step 2: Generate HTML Report
109
+ Create a self-contained HTML file with:
110
+ - Inline CSS (no external dependencies)
111
+ - Responsive layout
112
+ - Data tables with sorting
113
+ - Charts if applicable (use inline SVG)
114
+
115
+ ### Step 3: Write Output
116
+ Save to `{output_path}/report.html`
117
+
118
+ Example HTML structure:
119
+ ```html
120
+ <!DOCTYPE html>
121
+ <html>
122
+ <head>
123
+ <style>
124
+ body { font-family: system-ui; max-width: 900px; margin: 0 auto; padding: 2rem; }
125
+ table { width: 100%; border-collapse: collapse; }
126
+ th, td { padding: 8px; border: 1px solid #ddd; text-align: left; }
127
+ .critical { color: #dc3545; }
128
+ .warning { color: #ffc107; }
129
+ .pass { color: #28a745; }
130
+ </style>
131
+ </head>
132
+ <body>
133
+ <h1>{Report Title}</h1>
134
+ <!-- Content here -->
135
+ </body>
136
+ </html>
137
+ ```
138
+ ```
139
+
140
+ ### When to Use
141
+
142
+ - Dashboards and reports
143
+ - Documentation previews
144
+ - Visual diffs or comparisons
145
+ - Any output that benefits from formatting beyond plain text
146
+
147
+ ---
148
+
149
+ ## Structured Data Pattern
150
+
151
+ Output structured data (JSON, YAML, CSV) for programmatic consumption.
152
+
153
+ ```markdown
154
+ ## Output Format
155
+
156
+ Results are written as JSON to `{output_path}/results.json`:
157
+
158
+ ```json
159
+ {
160
+ "scan_date": "2025-01-15",
161
+ "files_scanned": 42,
162
+ "issues": [
163
+ {
164
+ "file": "auth.py",
165
+ "line": 15,
166
+ "severity": "critical",
167
+ "rule": "sql-injection",
168
+ "message": "Unsanitized input in SQL query"
169
+ }
170
+ ],
171
+ "summary": {
172
+ "critical": 2,
173
+ "warning": 5,
174
+ "info": 3
175
+ }
176
+ }
177
+ ```
178
+
179
+ Additionally, a human-readable summary is printed to the conversation.
180
+ ```
181
+
182
+ ---
183
+
184
+ ## Choosing Output Patterns
185
+
186
+ | If the output is... | Use |
187
+ |---------------------|-----|
188
+ | Exact format required | Strict Template |
189
+ | Structured but flexible | Flexible Template |
190
+ | Best shown by example | Examples Pattern |
191
+ | Rich/visual | Visual Output (HTML) |
192
+ | Machine-readable | Structured Data (JSON/YAML) |
193
+ | Multiple audiences | Combine: JSON file + conversation summary |
@@ -0,0 +1,55 @@
1
+ # PRD Template
2
+
3
+ Standard Product Requirements Document for all marketplace skills. Every PRD.md MUST follow this exact structure. No sections added, no sections removed.
4
+
5
+ ---
6
+
7
+ ```markdown
8
+ # PRD: {Skill Name}
9
+
10
+ **Version:** {version from SKILL.md frontmatter}
11
+ **Author:** {author from SKILL.md frontmatter}
12
+ **Status:** Active
13
+ **Marketplace:** [tonsofskills.com](https://tonsofskills.com) by [Intent Solutions](https://intentsolutions.io)
14
+ **Portfolio:** [jeremylongshore.com](https://jeremylongshore.com)
15
+
16
+ ---
17
+
18
+ ## Problem Statement
19
+
20
+ {2-4 sentences. What problem does this skill solve? Why does the problem exist? What happens without this skill?}
21
+
22
+ ## Target Users
23
+
24
+ | User | Context | Primary Need |
25
+ |------|---------|-------------|
26
+ | {role} | {when they encounter the problem} | {what they need from this skill} |
27
+ | {role} | {when they encounter the problem} | {what they need from this skill} |
28
+
29
+ ## Success Criteria
30
+
31
+ 1. {Measurable outcome — time, quality, or completeness metric}
32
+ 2. {Measurable outcome}
33
+ 3. {Measurable outcome}
34
+
35
+ ## Functional Requirements
36
+
37
+ 1. {What the skill must do — numbered, specific, testable}
38
+ 2. {What the skill must do}
39
+ 3. {What the skill must do}
40
+
41
+ ## Non-Functional Requirements
42
+
43
+ - {Performance, security, compatibility, or operational constraint}
44
+ - {Constraint}
45
+
46
+ ## Dependencies
47
+
48
+ - {What must be installed, configured, or available}
49
+ - {External services, APIs, credentials}
50
+
51
+ ## Out of Scope
52
+
53
+ - {What this skill explicitly does NOT do}
54
+ - {Adjacent concerns handled by other skills}
55
+ ```
@@ -0,0 +1,430 @@
1
+ # JSON Schemas
2
+
3
+ This document defines the JSON schemas used by skill-creator.
4
+
5
+ ---
6
+
7
+ ## evals.json
8
+
9
+ Defines the evals for a skill. Located at `evals/evals.json` within the skill directory.
10
+
11
+ ```json
12
+ {
13
+ "skill_name": "example-skill",
14
+ "evals": [
15
+ {
16
+ "id": 1,
17
+ "prompt": "User's example prompt",
18
+ "expected_output": "Description of expected result",
19
+ "files": ["evals/files/sample1.pdf"],
20
+ "expectations": [
21
+ "The output includes X",
22
+ "The skill used script Y"
23
+ ]
24
+ }
25
+ ]
26
+ }
27
+ ```
28
+
29
+ **Fields:**
30
+ - `skill_name`: Name matching the skill's frontmatter
31
+ - `evals[].id`: Unique integer identifier
32
+ - `evals[].prompt`: The task to execute
33
+ - `evals[].expected_output`: Human-readable description of success
34
+ - `evals[].files`: Optional list of input file paths (relative to skill root)
35
+ - `evals[].expectations`: List of verifiable statements
36
+
37
+ ---
38
+
39
+ ## history.json
40
+
41
+ Tracks version progression in Improve mode. Located at workspace root.
42
+
43
+ ```json
44
+ {
45
+ "started_at": "2026-01-15T10:30:00Z",
46
+ "skill_name": "pdf",
47
+ "current_best": "v2",
48
+ "iterations": [
49
+ {
50
+ "version": "v0",
51
+ "parent": null,
52
+ "expectation_pass_rate": 0.65,
53
+ "grading_result": "baseline",
54
+ "is_current_best": false
55
+ },
56
+ {
57
+ "version": "v1",
58
+ "parent": "v0",
59
+ "expectation_pass_rate": 0.75,
60
+ "grading_result": "won",
61
+ "is_current_best": false
62
+ },
63
+ {
64
+ "version": "v2",
65
+ "parent": "v1",
66
+ "expectation_pass_rate": 0.85,
67
+ "grading_result": "won",
68
+ "is_current_best": true
69
+ }
70
+ ]
71
+ }
72
+ ```
73
+
74
+ **Fields:**
75
+ - `started_at`: ISO timestamp of when improvement started
76
+ - `skill_name`: Name of the skill being improved
77
+ - `current_best`: Version identifier of the best performer
78
+ - `iterations[].version`: Version identifier (v0, v1, ...)
79
+ - `iterations[].parent`: Parent version this was derived from
80
+ - `iterations[].expectation_pass_rate`: Pass rate from grading
81
+ - `iterations[].grading_result`: "baseline", "won", "lost", or "tie"
82
+ - `iterations[].is_current_best`: Whether this is the current best version
83
+
84
+ ---
85
+
86
+ ## grading.json
87
+
88
+ Output from the grader agent. Located at `<run-dir>/grading.json`.
89
+
90
+ ```json
91
+ {
92
+ "expectations": [
93
+ {
94
+ "text": "The output includes the name 'John Smith'",
95
+ "passed": true,
96
+ "evidence": "Found in transcript Step 3: 'Extracted names: John Smith, Sarah Johnson'"
97
+ },
98
+ {
99
+ "text": "The spreadsheet has a SUM formula in cell B10",
100
+ "passed": false,
101
+ "evidence": "No spreadsheet was created. The output was a text file."
102
+ }
103
+ ],
104
+ "summary": {
105
+ "passed": 2,
106
+ "failed": 1,
107
+ "total": 3,
108
+ "pass_rate": 0.67
109
+ },
110
+ "execution_metrics": {
111
+ "tool_calls": {
112
+ "Read": 5,
113
+ "Write": 2,
114
+ "Bash": 8
115
+ },
116
+ "total_tool_calls": 15,
117
+ "total_steps": 6,
118
+ "errors_encountered": 0,
119
+ "output_chars": 12450,
120
+ "transcript_chars": 3200
121
+ },
122
+ "timing": {
123
+ "executor_duration_seconds": 165.0,
124
+ "grader_duration_seconds": 26.0,
125
+ "total_duration_seconds": 191.0
126
+ },
127
+ "claims": [
128
+ {
129
+ "claim": "The form has 12 fillable fields",
130
+ "type": "factual",
131
+ "verified": true,
132
+ "evidence": "Counted 12 fields in field_info.json"
133
+ }
134
+ ],
135
+ "user_notes_summary": {
136
+ "uncertainties": ["Used 2023 data, may be stale"],
137
+ "needs_review": [],
138
+ "workarounds": ["Fell back to text overlay for non-fillable fields"]
139
+ },
140
+ "eval_feedback": {
141
+ "suggestions": [
142
+ {
143
+ "assertion": "The output includes the name 'John Smith'",
144
+ "reason": "A hallucinated document that mentions the name would also pass"
145
+ }
146
+ ],
147
+ "overall": "Assertions check presence but not correctness."
148
+ }
149
+ }
150
+ ```
151
+
152
+ **Fields:**
153
+ - `expectations[]`: Graded expectations with evidence
154
+ - `summary`: Aggregate pass/fail counts
155
+ - `execution_metrics`: Tool usage and output size (from executor's metrics.json)
156
+ - `timing`: Wall clock timing (from timing.json)
157
+ - `claims`: Extracted and verified claims from the output
158
+ - `user_notes_summary`: Issues flagged by the executor
159
+ - `eval_feedback`: (optional) Improvement suggestions for the evals, only present when the grader identifies issues worth raising
160
+
161
+ ---
162
+
163
+ ## metrics.json
164
+
165
+ Output from the executor agent. Located at `<run-dir>/outputs/metrics.json`.
166
+
167
+ ```json
168
+ {
169
+ "tool_calls": {
170
+ "Read": 5,
171
+ "Write": 2,
172
+ "Bash": 8,
173
+ "Edit": 1,
174
+ "Glob": 2,
175
+ "Grep": 0
176
+ },
177
+ "total_tool_calls": 18,
178
+ "total_steps": 6,
179
+ "files_created": ["filled_form.pdf", "field_values.json"],
180
+ "errors_encountered": 0,
181
+ "output_chars": 12450,
182
+ "transcript_chars": 3200
183
+ }
184
+ ```
185
+
186
+ **Fields:**
187
+ - `tool_calls`: Count per tool type
188
+ - `total_tool_calls`: Sum of all tool calls
189
+ - `total_steps`: Number of major execution steps
190
+ - `files_created`: List of output files created
191
+ - `errors_encountered`: Number of errors during execution
192
+ - `output_chars`: Total character count of output files
193
+ - `transcript_chars`: Character count of transcript
194
+
195
+ ---
196
+
197
+ ## timing.json
198
+
199
+ Wall clock timing for a run. Located at `<run-dir>/timing.json`.
200
+
201
+ **How to capture:** When a subagent task completes, the task notification includes `total_tokens` and `duration_ms`. Save these immediately — they are not persisted anywhere else and cannot be recovered after the fact.
202
+
203
+ ```json
204
+ {
205
+ "total_tokens": 84852,
206
+ "duration_ms": 23332,
207
+ "total_duration_seconds": 23.3,
208
+ "executor_start": "2026-01-15T10:30:00Z",
209
+ "executor_end": "2026-01-15T10:32:45Z",
210
+ "executor_duration_seconds": 165.0,
211
+ "grader_start": "2026-01-15T10:32:46Z",
212
+ "grader_end": "2026-01-15T10:33:12Z",
213
+ "grader_duration_seconds": 26.0
214
+ }
215
+ ```
216
+
217
+ ---
218
+
219
+ ## benchmark.json
220
+
221
+ Output from Benchmark mode. Located at `benchmarks/<timestamp>/benchmark.json`.
222
+
223
+ ```json
224
+ {
225
+ "metadata": {
226
+ "skill_name": "pdf",
227
+ "skill_path": "/path/to/pdf",
228
+ "executor_model": "claude-sonnet-4-20250514",
229
+ "analyzer_model": "most-capable-model",
230
+ "timestamp": "2026-01-15T10:30:00Z",
231
+ "evals_run": [1, 2, 3],
232
+ "runs_per_configuration": 3
233
+ },
234
+
235
+ "runs": [
236
+ {
237
+ "eval_id": 1,
238
+ "eval_name": "Ocean",
239
+ "configuration": "with_skill",
240
+ "run_number": 1,
241
+ "result": {
242
+ "pass_rate": 0.85,
243
+ "passed": 6,
244
+ "failed": 1,
245
+ "total": 7,
246
+ "time_seconds": 42.5,
247
+ "tokens": 3800,
248
+ "tool_calls": 18,
249
+ "errors": 0
250
+ },
251
+ "expectations": [
252
+ {"text": "...", "passed": true, "evidence": "..."}
253
+ ],
254
+ "notes": [
255
+ "Used 2023 data, may be stale",
256
+ "Fell back to text overlay for non-fillable fields"
257
+ ]
258
+ }
259
+ ],
260
+
261
+ "run_summary": {
262
+ "with_skill": {
263
+ "pass_rate": {"mean": 0.85, "stddev": 0.05, "min": 0.80, "max": 0.90},
264
+ "time_seconds": {"mean": 45.0, "stddev": 12.0, "min": 32.0, "max": 58.0},
265
+ "tokens": {"mean": 3800, "stddev": 400, "min": 3200, "max": 4100}
266
+ },
267
+ "without_skill": {
268
+ "pass_rate": {"mean": 0.35, "stddev": 0.08, "min": 0.28, "max": 0.45},
269
+ "time_seconds": {"mean": 32.0, "stddev": 8.0, "min": 24.0, "max": 42.0},
270
+ "tokens": {"mean": 2100, "stddev": 300, "min": 1800, "max": 2500}
271
+ },
272
+ "delta": {
273
+ "pass_rate": "+0.50",
274
+ "time_seconds": "+13.0",
275
+ "tokens": "+1700"
276
+ }
277
+ },
278
+
279
+ "notes": [
280
+ "Assertion 'Output is a PDF file' passes 100% in both configurations - may not differentiate skill value",
281
+ "Eval 3 shows high variance (50% ± 40%) - may be flaky or model-dependent",
282
+ "Without-skill runs consistently fail on table extraction expectations",
283
+ "Skill adds 13s average execution time but improves pass rate by 50%"
284
+ ]
285
+ }
286
+ ```
287
+
288
+ **Fields:**
289
+ - `metadata`: Information about the benchmark run
290
+ - `skill_name`: Name of the skill
291
+ - `timestamp`: When the benchmark was run
292
+ - `evals_run`: List of eval names or IDs
293
+ - `runs_per_configuration`: Number of runs per config (e.g. 3)
294
+ - `runs[]`: Individual run results
295
+ - `eval_id`: Numeric eval identifier
296
+ - `eval_name`: Human-readable eval name (used as section header in the viewer)
297
+ - `configuration`: Must be `"with_skill"` or `"without_skill"` (the viewer uses this exact string for grouping and color coding)
298
+ - `run_number`: Integer run number (1, 2, 3...)
299
+ - `result`: Nested object with `pass_rate`, `passed`, `total`, `time_seconds`, `tokens`, `errors`
300
+ - `run_summary`: Statistical aggregates per configuration
301
+ - `with_skill` / `without_skill`: Each contains `pass_rate`, `time_seconds`, `tokens` objects with `mean` and `stddev` fields
302
+ - `delta`: Difference strings like `"+0.50"`, `"+13.0"`, `"+1700"`
303
+ - `notes`: Freeform observations from the analyzer
304
+
305
+ **Important:** The viewer reads these field names exactly. Using `config` instead of `configuration`, or putting `pass_rate` at the top level of a run instead of nested under `result`, will cause the viewer to show empty/zero values. Always reference this schema when generating benchmark.json manually.
306
+
307
+ ---
308
+
309
+ ## comparison.json
310
+
311
+ Output from blind comparator. Located at `<grading-dir>/comparison-N.json`.
312
+
313
+ ```json
314
+ {
315
+ "winner": "A",
316
+ "reasoning": "Output A provides a complete solution with proper formatting and all required fields. Output B is missing the date field and has formatting inconsistencies.",
317
+ "rubric": {
318
+ "A": {
319
+ "content": {
320
+ "correctness": 5,
321
+ "completeness": 5,
322
+ "accuracy": 4
323
+ },
324
+ "structure": {
325
+ "organization": 4,
326
+ "formatting": 5,
327
+ "usability": 4
328
+ },
329
+ "content_score": 4.7,
330
+ "structure_score": 4.3,
331
+ "overall_score": 9.0
332
+ },
333
+ "B": {
334
+ "content": {
335
+ "correctness": 3,
336
+ "completeness": 2,
337
+ "accuracy": 3
338
+ },
339
+ "structure": {
340
+ "organization": 3,
341
+ "formatting": 2,
342
+ "usability": 3
343
+ },
344
+ "content_score": 2.7,
345
+ "structure_score": 2.7,
346
+ "overall_score": 5.4
347
+ }
348
+ },
349
+ "output_quality": {
350
+ "A": {
351
+ "score": 9,
352
+ "strengths": ["Complete solution", "Well-formatted", "All fields present"],
353
+ "weaknesses": ["Minor style inconsistency in header"]
354
+ },
355
+ "B": {
356
+ "score": 5,
357
+ "strengths": ["Readable output", "Correct basic structure"],
358
+ "weaknesses": ["Missing date field", "Formatting inconsistencies", "Partial data extraction"]
359
+ }
360
+ },
361
+ "expectation_results": {
362
+ "A": {
363
+ "passed": 4,
364
+ "total": 5,
365
+ "pass_rate": 0.80,
366
+ "details": [
367
+ {"text": "Output includes name", "passed": true}
368
+ ]
369
+ },
370
+ "B": {
371
+ "passed": 3,
372
+ "total": 5,
373
+ "pass_rate": 0.60,
374
+ "details": [
375
+ {"text": "Output includes name", "passed": true}
376
+ ]
377
+ }
378
+ }
379
+ }
380
+ ```
381
+
382
+ ---
383
+
384
+ ## analysis.json
385
+
386
+ Output from post-hoc analyzer. Located at `<grading-dir>/analysis.json`.
387
+
388
+ ```json
389
+ {
390
+ "comparison_summary": {
391
+ "winner": "A",
392
+ "winner_skill": "path/to/winner/skill",
393
+ "loser_skill": "path/to/loser/skill",
394
+ "comparator_reasoning": "Brief summary of why comparator chose winner"
395
+ },
396
+ "winner_strengths": [
397
+ "Clear step-by-step instructions for handling multi-page documents",
398
+ "Included validation script that caught formatting errors"
399
+ ],
400
+ "loser_weaknesses": [
401
+ "Vague instruction 'process the document appropriately' led to inconsistent behavior",
402
+ "No script for validation, agent had to improvise"
403
+ ],
404
+ "instruction_following": {
405
+ "winner": {
406
+ "score": 9,
407
+ "issues": ["Minor: skipped optional logging step"]
408
+ },
409
+ "loser": {
410
+ "score": 6,
411
+ "issues": [
412
+ "Did not use the skill's formatting template",
413
+ "Invented own approach instead of following step 3"
414
+ ]
415
+ }
416
+ },
417
+ "improvement_suggestions": [
418
+ {
419
+ "priority": "high",
420
+ "category": "instructions",
421
+ "suggestion": "Replace 'process the document appropriately' with explicit steps",
422
+ "expected_impact": "Would eliminate ambiguity that caused inconsistent behavior"
423
+ }
424
+ ],
425
+ "transcript_insights": {
426
+ "winner_execution_pattern": "Read skill -> Followed 5-step process -> Used validation script",
427
+ "loser_execution_pattern": "Read skill -> Unclear on approach -> Tried 3 different methods"
428
+ }
429
+ }
430
+ ```