skill optimizer lawvable

Engineering Community

Skill notes

Triggers

self-improve - Analyze session and propose improvements self-improve [skill-name] - Target a specific skill self-improve on - Enable automatic mode (hook) self-improve off - Disable automatic mode self-improve status - Show automatic mode status

Step 1: Identify the Skill

If skill name not provided, list available skills from skills/ directory and ask:

Step 2: Detect Signals

Scan the conversation for signals - moments where the user expressed feedback: Signal Type · Examples Correction · "No", "That's not right", "It's missing X", "Always do Y", user rewrites output Success · "Perfect", "Yes", "Exactly", user accepts without changes Edge case · User needed a workaround, skill couldn't handle the request

Step 3: Evaluate Each Signal for Quality

For each correction signal, evaluate if it can become a good skill instruction. Quality Criteria 1. COMPLETE The instruction includes all information needed to apply it. No need to look elsewhere or make assumptions. Grade · Example

Step 4: Grade the Signal

Criteria Met · Action All 4 criteria pass · Add to skill directly Less than 4 criteria · Ask for clarification (see Step 5)

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Engineering
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
@lawve-ai · no license declared
Token usage
Lean
Setup complexity
Plug-and-play
External API key
Not required
Operating systems
Unspecified (assume cross-platform)
Runtime requirements
No explicit requirements detected
Detected file/system behavior
  • Read-only
  • Write / modify
Network behavior
Local-only
Install commands
None (reference only)

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

01
Step 1: Identify the Skill

If skill name not provided, list available skills from `skills/` directory and ask:

02
Step 2: Detect Signals

Scan the conversation for signals - moments where the user expressed feedback: Signal Type · Examples Correction · "No", "That's not right", "It's missing X", "Always do Y", user rewrites output Success · "Perfect", "Yes", "Exactly", user accepts without changes Edge case · User needed a workaround, skill couldn't handle the request

03
Step 3: Evaluate Each Signal for Quality

For each correction signal, evaluate if it can become a good skill instruction. Quality Criteria 1. COMPLETE The instruction includes all information needed to apply it. No need to look elsewhere or make assumptions. Grade · Example

04
Step 4: Grade the Signal

Criteria Met · Action All 4 criteria pass · Add to skill directly Less than 4 criteria · Ask for clarification (see Step 5)

05
Step 5: Ask for Clarification

When feedback doesn't meet all criteria, ask for what's missing using the `AskUserQuestion` tool: If the user provides clarification → Update the instruction and proceed to Step 6. If the user prefers the original → Proceed to Step 6 with the original instruction.

06
Step 6: Propose Changes

Step 6: Propose Changes

07
Step 7: If Approved

Update SKILL.md Read `skills/[skill-name]/SKILL.md` Add each instruction in the appropriate section Each instruction must be readable and applicable on its own Update `skills/[skill-name]/CHANGELOG.md`

08
Step 8: Save Observations

For signals that couldn't be processed, offer to save: If yes, append to `skills/[skill-name]/OBSERVATIONS.md`

Discussion

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