skill factory

Other Community

Skill notes

Parameter Parsing

Parse $ARGUMENTS for flags: Flag · Default · Description --dry-run · false · Analyze and report only, no file creation --no-team · false · Run sequentially without Agent Teams --target · (auto) · Specific pattern name to extract

Phase 1: Session Analysis

Collect what happened in this session: From collected changes, identify candidate patterns - repeatable workflows that appeared: Multi-step sequences - 3+ actions performed in consistent order Tool combinations - Specific tools used together (e.g., Grep + Read + Edit) Domain procedures - File types or directories accessed with specific operations

Phase 2: Similarity Check

For each selected pattern, check against existing inventory. Step 1: Scan inventory Step 2: Score similarity Step 3: Apply decision logic (see references/decision-tree.md) Present results to user:

Phase 3: Blueprint

For each CREATE/UPDATE/MERGE decision, design the skill structure.

CREATE Blueprint

Select template type from references/skill-templates.md: Workflow for sequential processes Task/Tool for operation collections Reference for domain knowledge Verification for automated checks

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Other
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@sangrokjung · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
Unspecified (assume cross-platform)
Runtime requirements
Python >=3.8
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
  • Env read
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Phase 1: Session Analysis

Collect what happened in this session: From collected changes, identify candidate patterns - repeatable workflows that appeared: Multi-step sequences - 3+ actions performed in consistent order Tool combinations - Specific tools used together (e.g., Grep + Read + Edit) Domain procedures - File types or directories accessed with specific operations

02
Phase 2: Similarity Check

For each selected pattern, check against existing inventory. Step 1: Scan inventory Step 2: Score similarity Step 3: Apply decision logic (see references/decision-tree.md) Present results to user:

03
Phase 3: Blueprint

For each CREATE/UPDATE/MERGE decision, design the skill structure.

04
Phase 4: Execution

Two paths based on `--no-team` flag and Agent Teams availability. Check Agent Teams availability: If `--no-team` is set or env var is missing/0, use Path B automatically.

05
Phase 5: Registration

After validation passes: Log creation - Append to `~/.claude/skill-factory.log`: Scope placement: `--scope global`: `~/.claude/skills/<name>/` `--scope project`: `.claude/skills/<name>/`

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.