Skip to content

AGI-comming/functional-skill-creator / skills/fskill-creator/sub-skills/create

fskill-creator-create

Verified

Create lane for fskill-creator; normalizes user briefs into create_context for the main skill to generate functional skills.

functions/collect_create_brief.md

View on GitHub
# collect_create_brief

## Purpose

Normalize user requests into a `create_context` for creating or enhancing a functional skill.

## Input

| Field | Required | Description |
|---|---:|---|
| `skill_request` | yes | User-provided target skill description. |
| `target_skill_path` | no | Directory where the skill should be created or updated. |
| `skill_name` | no | User-explicit skill name. |
| `include_viewers` | no | Whether to generate `tools/log_viewer.mjs` and `tools/tester_viewer.mjs`. |

## Output

| Field | Description |
|---|---|
| `create_context.name` | Normalized skill name. |
| `create_context.goal` | One-paragraph description of the skill's goal. |
| `create_context.target_path` | Suggested target directory. |
| `create_context.external_inputs` | External inputs the skill should consume. |
| `create_context.expected_outputs` | Expected outputs or files. |
| `create_context.constraints` | User-stated constraints and non-goals. |
| `create_context.include_viewers` | `true`, `false`, or `unknown`. |
| `create_context.open_questions` | Blocking questions that cannot be safely inferred. |

## Logic

1. Extract the request's workflow, target user, expected outputs, and repo location.
2. If `skill_name` is missing, derive a lowercase kebab-case name.
3. If `include_viewers` is not provided, add an open question asking whether to generate viewer tools, briefly explaining that `log_viewer` views `logs/runs/*.jsonl` trace summaries and `tester_viewer` views `testcases/**/*.case.json` regression coverage.
4. Put uncertainty into `open_questions`; do not silently invent domain rules.
5. If target path is missing, suggest `skills/<skill_name>`.

## Errors

| Code | When |
|---|---|
| `[MISSING_SKILL_REQUEST]` | `skill_request` is empty. |
| `[AMBIGUOUS_GOAL]` | User request has no clear workflow or outcome. |

## Observability

Record normalized skill name, target path, open question count, and assumptions.
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: 471kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall