AGI-comming/functional-skill-creator / skills/fskill-creator
fskill-creator
VerifiedCreate, maintain, or migrate functional skills; supports creating from a requirement brief and migrating an existing legacy skill directory into a functional skill structure.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.2 KB |
| functions/add_runtime_capabilities.md | markdown | 2.4 KB |
| functions/assemble_skill_files.md | markdown | 2.2 KB |
| functions/design_skill_structure.md | markdown | 2.7 KB |
| functions/draft_skill_artifacts.md | markdown | 2.4 KB |
| functions/normalize_skill_blueprint.md | markdown | 2.8 KB |
| functions/resolve_task_mode.md | markdown | 1.9 KB |
| functions/validate_skill.md | markdown | 2.5 KB |
| logs/runs/.gitkeep | other | 1 B |
| references/script-rules.md | markdown | 1.3 KB |
| references/shared-glossary.md | markdown | 1.9 KB |
| scripts/.gitkeep | other | 1 B |
| scripts/init_skill.mjs | script | 24.8 KB |
| scripts/init_skill.test.mjs | script | 3.7 KB |
| scripts/lint_skill.mjs | script | 2.1 KB |
| scripts/test_cases.mjs | script | 5.4 KB |
| scripts/test_cases.test.mjs | script | 1.4 KB |
| testcases/unit/design_skill_structure.basic.case.json | config | 2.0 KB |
functions/normalize_skill_blueprint.md
View on GitHub# normalize_skill_blueprint
## Purpose
Converge create / migrate / enhance pre-analysis results into a unified `skill_blueprint` for the shared artifact pipeline.
## Input
| Field | Required | Description |
|---|---:|---|
| `task_context` | yes | Task mode and lane requirements from `resolve_task_mode`. |
| `create_context` | conditional | Create/enhance lane output. |
| `migration_context` | conditional | Migrate lane output, including behavior map, proposal, and source evidence. |
| `target_skill_path` | no | User-specified or lane-output-derived target path. |
| `include_report` | no | Whether to generate report log runtime; defaults to `true`. |
| `include_unittest` | no | Whether to generate unittest / testcase runner; defaults to `true`. |
## Output
| Field | Description |
|---|---|
| `skill_blueprint.mode` | `create`, `migrate`, `enhance`, or `validate`. |
| `skill_blueprint.name` | Target skill name. |
| `skill_blueprint.goal` | Core goal of the target skill. |
| `skill_blueprint.target_path` | Target skill directory. |
| `skill_blueprint.external_inputs` | External inputs for the target skill. |
| `skill_blueprint.expected_outputs` | Output or file scope of the target skill. |
| `skill_blueprint.required_behaviors` | Behaviors that must be preserved or implemented. |
| `skill_blueprint.constraints` | User constraints, non-goals, and platform constraints. |
| `skill_blueprint.source_evidence` | Migration source or requirement source evidence. |
| `skill_blueprint.include_report` | Whether to generate report log runtime. |
| `skill_blueprint.include_unittest` | Whether to generate unittest / testcase runner. |
| `skill_blueprint.open_questions` | Questions still needing user confirmation. |
## Logic
1. Create/enhance lane reads goal, inputs, outputs, constraints, and open questions from `create_context`.
2. Migrate lane reads must-preserve behaviors, source evidence, and target structure from `migration_context.behavior_map`, `migration_context.migration_proposal`, and `migration_context.reference_plan`.
3. Explicit `target_skill_path` input takes highest priority; otherwise use the suggested path from lane output.
4. Include flag defaults:
- `include_report=true`
- `include_unittest=true`
5. Migration mode must preserve `source_evidence`; add `[MIGRATION_EVIDENCE_MISSING]` warning when evidence is absent.
6. Do not stuff raw PRD, raw legacy markdown, or full source code into the blueprint; keep only reviewable summaries and references.
## Errors
| Code | When |
|---|---|
| `[MISSING_LANE_CONTEXT]` | Required lane output is missing for the current mode. |
| `[BLUEPRINT_TARGET_UNRESOLVED]` | Target skill path cannot be determined. |
| `[BLUEPRINT_GOAL_UNRESOLVED]` | Target skill goal cannot be determined. |
## Observability
Record mode, target path, required behavior count, source evidence count, include choices, and open question count.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |