@cleocode/skills 2.0.0

package/skills/ct-skill-creator/references/provider-deployment.md

@@ -0,0 +1,175 @@
+# Provider Deployment
+
+This reference covers multi-provider skill deployment: where each provider reads skills from, how symlinks enable a single source of truth, and how to add new skills to the CLEO ct-skills package.
+
+## Architecture
+
+Skills follow a single-source-of-truth model:
+
+```
+packages/ct-skills/skills/         <-- canonical location
+  ct-cleo/SKILL.md
+  ct-orchestrator/SKILL.md
+  ct-skill-creator/SKILL.md
+  ...
+  manifest.json                    <-- CLEO-only metadata
+```
+
+Providers read skills from their own vendor-specific directories. Symlinks point from each provider's skill directory back to the canonical location, so a single SKILL.md serves all providers.
+
+**SKILL.md** is the open standard -- every provider reads it. It contains only the 11 standard v2 fields (name, description, etc.) that all providers understand.
+
+**manifest.json** is CLEO-only metadata -- tier, tags, capabilities, dispatch routing. Non-CLEO providers ignore it entirely. This is why CLEO-specific fields must never appear in SKILL.md: providers that do not understand them may reject the skill or behave unpredictably.
+
+## Provider Path Table
+
+| Provider | Global Skills Path | Project Skills Path | Symlinks |
+|---|---|---|---|
+| claude-code | `$HOME/.claude/skills` | `.claude/skills` | Yes |
+| codex-cli | `$HOME/.agents/skills` | `.agents/skills` | Yes |
+| gemini-cli | `$HOME/.gemini/skills` | `.gemini/skills` | Yes |
+| cursor | `$HOME/.cursor/skills` | `.cursor/skills` | Yes |
+| github-copilot | `$HOME/.copilot/skills` | `.github/skills` | Yes |
+| windsurf | `$HOME/.codeium/windsurf/skills` | `.windsurf/skills` | No |
+| opencode | `$HOME/.config/opencode/skills` | `.opencode/skills` | Yes |
+| kimi-coding | `$HOME/.kimi/skills` | `.kimi/skills` | No |
+| antigravity | `$HOME/.antigravity/skills` | `.agent/skills` | Yes |
+
+**Global skills** are available across all projects for that provider. **Project skills** are scoped to the repository they live in.
+
+**Symlink support** indicates whether the provider follows symbolic links when reading skill directories. Providers without symlink support (windsurf, kimi-coding) require the skill directory to be copied rather than symlinked.
+
+## What Providers Read
+
+### Standard Providers (non-CLEO)
+
+Standard providers read SKILL.md only. They parse the YAML frontmatter for standard v2 fields and load the markdown body when the skill triggers. They have no awareness of manifest.json, dispatch-config.json, or any CLEO infrastructure.
+
+Fields they understand: `name`, `description`, `argument-hint`, `disable-model-invocation`, `user-invocable`, `allowed-tools`, `model`, `context`, `agent`, `hooks`, `license`.
+
+Fields they do not understand: `version`, `tier`, `core`, `category`, `protocol`, `dependencies`, `sharedResources`, `compatibility`, `tags`, `triggers`, `token_budget`, `capabilities`, `constraints`, `metadata`.
+
+### CLEO-Aware Providers
+
+CLEO-aware providers read both SKILL.md and manifest.json. The manifest provides dispatch routing, tier-based loading priorities, token budgets, and capability declarations that enable advanced features like skill chaining and orchestration.
+
+## Deployment Strategies
+
+### CLEO Package Skills
+
+Skills in `packages/ct-skills/skills/` are managed by CLEO infrastructure. They are deployed via the CLEO skill system and do not need manual symlink setup. The manifest.json, dispatch-config.json, and provider-skills-map.json coordinate deployment automatically.
+
+### User Global Skills
+
+For standalone skills installed directly into a provider's global skill directory:
+
+```bash
+# Claude Code
+cp -r my-skill/ ~/.claude/skills/my-skill/
+
+# Gemini CLI
+cp -r my-skill/ ~/.gemini/skills/my-skill/
+
+# Codex CLI
+cp -r my-skill/ ~/.agents/skills/my-skill/
+```
+
+### Multi-Provider via Symlinks
+
+For skills that should be available across multiple providers, create the skill in one location and symlink to each provider's directory:
+
+```bash
+# Canonical location
+mkdir -p ~/shared-skills/my-skill
+# ... create SKILL.md and resources in ~/shared-skills/my-skill/
+
+# Symlink to each provider
+ln -s ~/shared-skills/my-skill ~/.claude/skills/my-skill
+ln -s ~/shared-skills/my-skill ~/.gemini/skills/my-skill
+ln -s ~/shared-skills/my-skill ~/.agents/skills/my-skill
+```
+
+For providers that do not support symlinks (windsurf, kimi-coding), copy the directory instead:
+
+```bash
+cp -r ~/shared-skills/my-skill ~/.codeium/windsurf/skills/my-skill
+cp -r ~/shared-skills/my-skill ~/.kimi/skills/my-skill
+```
+
+### Project-Level Skills
+
+Place the skill directory inside the project's provider-specific skill path:
+
+```bash
+# Claude Code project skill
+cp -r my-skill/ .claude/skills/my-skill/
+
+# Cursor project skill
+cp -r my-skill/ .cursor/skills/my-skill/
+```
+
+Project skills are committed to the repository and shared with all contributors.
+
+## Adding a New Skill to CLEO ct-skills
+
+To add a new skill to the CLEO package (`packages/ct-skills/`):
+
+1. **Create the skill directory**:
+   ```bash
+   mkdir -p packages/ct-skills/skills/my-new-skill
+   ```
+
+2. **Write SKILL.md with standard fields only**:
+   ```yaml
+   ---
+   name: my-new-skill
+   description: "Clear description of what the skill does and when to use it."
+   license: MIT
+   ---
+   # My New Skill
+
+   Instructions for using the skill...
+   ```
+   Include only v2 standard fields. No `version`, `tier`, `category`, or other CLEO-only fields.
+
+3. **Add entry to manifest.json** (`packages/ct-skills/skills/manifest.json`):
+   ```json
+   {
+     "name": "my-new-skill",
+     "version": "1.0.0",
+     "description": "Same description as SKILL.md",
+     "path": "skills/my-new-skill",
+     "tags": ["relevant", "tags"],
+     "status": "active",
+     "tier": 2,
+     "token_budget": 6000,
+     "references": [],
+     "capabilities": {
+       "inputs": [],
+       "outputs": [],
+       "dependencies": [],
+       "dispatch_triggers": ["trigger phrase"],
+       "compatible_subagent_types": ["general-purpose"],
+       "chains_to": [],
+       "dispatch_keywords": {
+         "primary": ["keyword1", "keyword2"],
+         "secondary": ["keyword3", "keyword4"]
+       }
+     },
+     "constraints": {
+       "max_context_tokens": 60000,
+       "requires_session": false,
+       "requires_epic": false
+     }
+   }
+   ```
+
+4. **Add entry to dispatch-config.json** (`packages/ct-skills/dispatch-config.json`):
+   Add the skill to relevant `by_task_type`, `by_keyword`, and/or `by_protocol` mappings if it should participate in dispatch routing.
+
+5. **Update totalSkills** in manifest.json `_meta.totalSkills` to reflect the new count.
+
+6. **Validate**: Run the skill validator to confirm the new skill passes all checks:
+   ```bash
+   python3 packages/ct-skills/skills/ct-skill-creator/scripts/quick_validate.py packages/ct-skills/skills/my-new-skill
+   ```

package/skills/ct-skill-creator/references/schemas.md

@@ -0,0 +1,430 @@
+# JSON Schemas
+
+This document defines the JSON schemas used by skill-creator.
+
+---
+
+## evals.json
+
+Defines the evals for a skill. Located at `evals/evals.json` within the skill directory.
+
+```json
+{
+  "skill_name": "example-skill",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "User's example prompt",
+      "expected_output": "Description of expected result",
+      "files": ["evals/files/sample1.pdf"],
+      "expectations": [
+        "The output includes X",
+        "The skill used script Y"
+      ]
+    }
+  ]
+}
+```
+
+**Fields:**
+- `skill_name`: Name matching the skill's frontmatter
+- `evals[].id`: Unique integer identifier
+- `evals[].prompt`: The task to execute
+- `evals[].expected_output`: Human-readable description of success
+- `evals[].files`: Optional list of input file paths (relative to skill root)
+- `evals[].expectations`: List of verifiable statements
+
+---
+
+## history.json
+
+Tracks version progression in Improve mode. Located at workspace root.
+
+```json
+{
+  "started_at": "2026-01-15T10:30:00Z",
+  "skill_name": "pdf",
+  "current_best": "v2",
+  "iterations": [
+    {
+      "version": "v0",
+      "parent": null,
+      "expectation_pass_rate": 0.65,
+      "grading_result": "baseline",
+      "is_current_best": false
+    },
+    {
+      "version": "v1",
+      "parent": "v0",
+      "expectation_pass_rate": 0.75,
+      "grading_result": "won",
+      "is_current_best": false
+    },
+    {
+      "version": "v2",
+      "parent": "v1",
+      "expectation_pass_rate": 0.85,
+      "grading_result": "won",
+      "is_current_best": true
+    }
+  ]
+}
+```
+
+**Fields:**
+- `started_at`: ISO timestamp of when improvement started
+- `skill_name`: Name of the skill being improved
+- `current_best`: Version identifier of the best performer
+- `iterations[].version`: Version identifier (v0, v1, ...)
+- `iterations[].parent`: Parent version this was derived from
+- `iterations[].expectation_pass_rate`: Pass rate from grading
+- `iterations[].grading_result`: "baseline", "won", "lost", or "tie"
+- `iterations[].is_current_best`: Whether this is the current best version
+
+---
+
+## grading.json
+
+Output from the grader agent. Located at `<run-dir>/grading.json`.
+
+```json
+{
+  "expectations": [
+    {
+      "text": "The output includes the name 'John Smith'",
+      "passed": true,
+      "evidence": "Found in transcript Step 3: 'Extracted names: John Smith, Sarah Johnson'"
+    },
+    {
+      "text": "The spreadsheet has a SUM formula in cell B10",
+      "passed": false,
+      "evidence": "No spreadsheet was created. The output was a text file."
+    }
+  ],
+  "summary": {
+    "passed": 2,
+    "failed": 1,
+    "total": 3,
+    "pass_rate": 0.67
+  },
+  "execution_metrics": {
+    "tool_calls": {
+      "Read": 5,
+      "Write": 2,
+      "Bash": 8
+    },
+    "total_tool_calls": 15,
+    "total_steps": 6,
+    "errors_encountered": 0,
+    "output_chars": 12450,
+    "transcript_chars": 3200
+  },
+  "timing": {
+    "executor_duration_seconds": 165.0,
+    "grader_duration_seconds": 26.0,
+    "total_duration_seconds": 191.0
+  },
+  "claims": [
+    {
+      "claim": "The form has 12 fillable fields",
+      "type": "factual",
+      "verified": true,
+      "evidence": "Counted 12 fields in field_info.json"
+    }
+  ],
+  "user_notes_summary": {
+    "uncertainties": ["Used 2023 data, may be stale"],
+    "needs_review": [],
+    "workarounds": ["Fell back to text overlay for non-fillable fields"]
+  },
+  "eval_feedback": {
+    "suggestions": [
+      {
+        "assertion": "The output includes the name 'John Smith'",
+        "reason": "A hallucinated document that mentions the name would also pass"
+      }
+    ],
+    "overall": "Assertions check presence but not correctness."
+  }
+}
+```
+
+**Fields:**
+- `expectations[]`: Graded expectations with evidence
+- `summary`: Aggregate pass/fail counts
+- `execution_metrics`: Tool usage and output size (from executor's metrics.json)
+- `timing`: Wall clock timing (from timing.json)
+- `claims`: Extracted and verified claims from the output
+- `user_notes_summary`: Issues flagged by the executor
+- `eval_feedback`: (optional) Improvement suggestions for the evals, only present when the grader identifies issues worth raising
+
+---
+
+## metrics.json
+
+Output from the executor agent. Located at `<run-dir>/outputs/metrics.json`.
+
+```json
+{
+  "tool_calls": {
+    "Read": 5,
+    "Write": 2,
+    "Bash": 8,
+    "Edit": 1,
+    "Glob": 2,
+    "Grep": 0
+  },
+  "total_tool_calls": 18,
+  "total_steps": 6,
+  "files_created": ["filled_form.pdf", "field_values.json"],
+  "errors_encountered": 0,
+  "output_chars": 12450,
+  "transcript_chars": 3200
+}
+```
+
+**Fields:**
+- `tool_calls`: Count per tool type
+- `total_tool_calls`: Sum of all tool calls
+- `total_steps`: Number of major execution steps
+- `files_created`: List of output files created
+- `errors_encountered`: Number of errors during execution
+- `output_chars`: Total character count of output files
+- `transcript_chars`: Character count of transcript
+
+---
+
+## timing.json
+
+Wall clock timing for a run. Located at `<run-dir>/timing.json`.
+
+**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.
+
+```json
+{
+  "total_tokens": 84852,
+  "duration_ms": 23332,
+  "total_duration_seconds": 23.3,
+  "executor_start": "2026-01-15T10:30:00Z",
+  "executor_end": "2026-01-15T10:32:45Z",
+  "executor_duration_seconds": 165.0,
+  "grader_start": "2026-01-15T10:32:46Z",
+  "grader_end": "2026-01-15T10:33:12Z",
+  "grader_duration_seconds": 26.0
+}
+```
+
+---
+
+## benchmark.json
+
+Output from Benchmark mode. Located at `benchmarks/<timestamp>/benchmark.json`.
+
+```json
+{
+  "metadata": {
+    "skill_name": "pdf",
+    "skill_path": "/path/to/pdf",
+    "executor_model": "claude-sonnet-4-20250514",
+    "analyzer_model": "most-capable-model",
+    "timestamp": "2026-01-15T10:30:00Z",
+    "evals_run": [1, 2, 3],
+    "runs_per_configuration": 3
+  },
+
+  "runs": [
+    {
+      "eval_id": 1,
+      "eval_name": "Ocean",
+      "configuration": "with_skill",
+      "run_number": 1,
+      "result": {
+        "pass_rate": 0.85,
+        "passed": 6,
+        "failed": 1,
+        "total": 7,
+        "time_seconds": 42.5,
+        "tokens": 3800,
+        "tool_calls": 18,
+        "errors": 0
+      },
+      "expectations": [
+        {"text": "...", "passed": true, "evidence": "..."}
+      ],
+      "notes": [
+        "Used 2023 data, may be stale",
+        "Fell back to text overlay for non-fillable fields"
+      ]
+    }
+  ],
+
+  "run_summary": {
+    "with_skill": {
+      "pass_rate": {"mean": 0.85, "stddev": 0.05, "min": 0.80, "max": 0.90},
+      "time_seconds": {"mean": 45.0, "stddev": 12.0, "min": 32.0, "max": 58.0},
+      "tokens": {"mean": 3800, "stddev": 400, "min": 3200, "max": 4100}
+    },
+    "without_skill": {
+      "pass_rate": {"mean": 0.35, "stddev": 0.08, "min": 0.28, "max": 0.45},
+      "time_seconds": {"mean": 32.0, "stddev": 8.0, "min": 24.0, "max": 42.0},
+      "tokens": {"mean": 2100, "stddev": 300, "min": 1800, "max": 2500}
+    },
+    "delta": {
+      "pass_rate": "+0.50",
+      "time_seconds": "+13.0",
+      "tokens": "+1700"
+    }
+  },
+
+  "notes": [
+    "Assertion 'Output is a PDF file' passes 100% in both configurations - may not differentiate skill value",
+    "Eval 3 shows high variance (50% ± 40%) - may be flaky or model-dependent",
+    "Without-skill runs consistently fail on table extraction expectations",
+    "Skill adds 13s average execution time but improves pass rate by 50%"
+  ]
+}
+```
+
+**Fields:**
+- `metadata`: Information about the benchmark run
+  - `skill_name`: Name of the skill
+  - `timestamp`: When the benchmark was run
+  - `evals_run`: List of eval names or IDs
+  - `runs_per_configuration`: Number of runs per config (e.g. 3)
+- `runs[]`: Individual run results
+  - `eval_id`: Numeric eval identifier
+  - `eval_name`: Human-readable eval name (used as section header in the viewer)
+  - `configuration`: Must be `"with_skill"` or `"without_skill"` (the viewer uses this exact string for grouping and color coding)
+  - `run_number`: Integer run number (1, 2, 3...)
+  - `result`: Nested object with `pass_rate`, `passed`, `total`, `time_seconds`, `tokens`, `errors`
+- `run_summary`: Statistical aggregates per configuration
+  - `with_skill` / `without_skill`: Each contains `pass_rate`, `time_seconds`, `tokens` objects with `mean` and `stddev` fields
+  - `delta`: Difference strings like `"+0.50"`, `"+13.0"`, `"+1700"`
+- `notes`: Freeform observations from the analyzer
+
+**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.
+
+---
+
+## comparison.json
+
+Output from blind comparator. Located at `<grading-dir>/comparison-N.json`.
+
+```json
+{
+  "winner": "A",
+  "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.",
+  "rubric": {
+    "A": {
+      "content": {
+        "correctness": 5,
+        "completeness": 5,
+        "accuracy": 4
+      },
+      "structure": {
+        "organization": 4,
+        "formatting": 5,
+        "usability": 4
+      },
+      "content_score": 4.7,
+      "structure_score": 4.3,
+      "overall_score": 9.0
+    },
+    "B": {
+      "content": {
+        "correctness": 3,
+        "completeness": 2,
+        "accuracy": 3
+      },
+      "structure": {
+        "organization": 3,
+        "formatting": 2,
+        "usability": 3
+      },
+      "content_score": 2.7,
+      "structure_score": 2.7,
+      "overall_score": 5.4
+    }
+  },
+  "output_quality": {
+    "A": {
+      "score": 9,
+      "strengths": ["Complete solution", "Well-formatted", "All fields present"],
+      "weaknesses": ["Minor style inconsistency in header"]
+    },
+    "B": {
+      "score": 5,
+      "strengths": ["Readable output", "Correct basic structure"],
+      "weaknesses": ["Missing date field", "Formatting inconsistencies", "Partial data extraction"]
+    }
+  },
+  "expectation_results": {
+    "A": {
+      "passed": 4,
+      "total": 5,
+      "pass_rate": 0.80,
+      "details": [
+        {"text": "Output includes name", "passed": true}
+      ]
+    },
+    "B": {
+      "passed": 3,
+      "total": 5,
+      "pass_rate": 0.60,
+      "details": [
+        {"text": "Output includes name", "passed": true}
+      ]
+    }
+  }
+}
+```
+
+---
+
+## analysis.json
+
+Output from post-hoc analyzer. Located at `<grading-dir>/analysis.json`.
+
+```json
+{
+  "comparison_summary": {
+    "winner": "A",
+    "winner_skill": "path/to/winner/skill",
+    "loser_skill": "path/to/loser/skill",
+    "comparator_reasoning": "Brief summary of why comparator chose winner"
+  },
+  "winner_strengths": [
+    "Clear step-by-step instructions for handling multi-page documents",
+    "Included validation script that caught formatting errors"
+  ],
+  "loser_weaknesses": [
+    "Vague instruction 'process the document appropriately' led to inconsistent behavior",
+    "No script for validation, agent had to improvise"
+  ],
+  "instruction_following": {
+    "winner": {
+      "score": 9,
+      "issues": ["Minor: skipped optional logging step"]
+    },
+    "loser": {
+      "score": 6,
+      "issues": [
+        "Did not use the skill's formatting template",
+        "Invented own approach instead of following step 3"
+      ]
+    }
+  },
+  "improvement_suggestions": [
+    {
+      "priority": "high",
+      "category": "instructions",
+      "suggestion": "Replace 'process the document appropriately' with explicit steps",
+      "expected_impact": "Would eliminate ambiguity that caused inconsistent behavior"
+    }
+  ],
+  "transcript_insights": {
+    "winner_execution_pattern": "Read skill -> Followed 5-step process -> Used validation script",
+    "loser_execution_pattern": "Read skill -> Unclear on approach -> Tried 3 different methods"
+  }
+}
+```

package/skills/ct-skill-creator/references/workflows.md

@@ -0,0 +1,28 @@
+# Workflow Patterns
+
+## Sequential Workflows
+
+For complex tasks, break operations into clear, sequential steps. It is often helpful to give Claude an overview of the process towards the beginning of SKILL.md:
+
+```markdown
+Filling a PDF form involves these steps:
+
+1. Analyze the form (run analyze_form.py)
+2. Create field mapping (edit fields.json)
+3. Validate mapping (run validate_fields.py)
+4. Fill the form (run fill_form.py)
+5. Verify output (run verify_output.py)
+```
+
+## Conditional Workflows
+
+For tasks with branching logic, guide Claude through decision points:
+
+```markdown
+1. Determine the modification type:
+   **Creating new content?** → Follow "Creation workflow" below
+   **Editing existing content?** → Follow "Editing workflow" below
+
+2. Creation workflow: [steps]
+3. Editing workflow: [steps]
+```

package/skills/ct-skill-creator/scripts/__init__.py

@@ -0,0 +1 @@
+