Skill Factory

Other Community v1.0.0

Skill notes

How It Works

Skill Factory operates in three stages:

Phase 1: Silent Observation

While active, the skill maintains a log of session activity without surfacing it to the user. What it tracks: Repeated actions — any command, sequence, or approach used more than once Multi-step workflows — sequences of 3+ steps that accomplish a coherent goal Tool combinations — two or more tools used together in a consistent pattern

Phase 2: Trigger Conditions

Skill creation is proposed when any of the following occur: Trigger · Example User explicitly requests · "save this as a skill", "remember this workflow" Slash command · /skill-factory propose Repeated pattern (2x+) · Same workflow appeared twice in the session

Phase 3: Proposal & Generation

When triggered, Skill Factory presents a structured proposal with the detected workflow, then generates a complete skill package: SKILL.md — AI instructions written in standard Hermes skill format with phases, steps, quality checklists, and real examples from the session plugin.py — A slash command that triggers the workflow directly, with hooks and tool registrations scaffolded from the detected pattern

Commands

Command · Description /skill-factory propose · Analyze current session and propose the top detected skill /skill-factory list · Show all skills generated in this session /skill-factory status · Show what patterns are currently being tracked /skill-factory queue · Show all detected patterns queued for proposal

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
100 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@amanning3390 · v1.0.0 · MIT
Token usage
Lean
Setup complexity
Plug-and-play
External API key
Not required
Operating systems
Unspecified (assume cross-platform)
Runtime requirements
Python >=3.10
Detected file/system behavior
  • Read-only
  • Write / modify
Network behavior
Local-only
Install commands
None (reference only)
01
Phase 1: Silent Observation

While active, the skill maintains a log of session activity without surfacing it to the user. What it tracks: Repeated actions — any command, sequence, or approach used more than once Multi-step workflows — sequences of 3+ steps that accomplish a coherent goal Tool combinations — two or more tools used together in a consistent pattern

02
Phase 2: Trigger Conditions

Skill creation is proposed when any of the following occur: Trigger · Example User explicitly requests · "save this as a skill", "remember this workflow" Slash command · `/skill-factory propose` Repeated pattern (2x+) · Same workflow appeared twice in the session

03
Phase 3: Proposal & Generation

When triggered, Skill Factory presents a structured proposal with the detected workflow, then generates a complete skill package: SKILL.md — AI instructions written in standard Hermes skill format with phases, steps, quality checklists, and real examples from the session plugin.py — A slash command that triggers the workflow directly, with hooks and tool registrations scaffolded from the detected pattern

Discussion

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