skill reinforcement

Engineering Community

Skill notes

What I Do

After ANY skill is used, this meta-skill triggers to: Analyze what worked and what didn't Identify new patterns or shortcuts discovered Update the skill file with learnings Prevent knowledge loss between sessions

When to Trigger

Invoke this skill automatically when: Any skill from .opencode/skill/*/SKILL.md completes A workflow succeeds or fails in a notable way New shortcuts or anti-patterns are discovered Token usage could be reduced with better patterns

Step 2: Identify Learnings

Ask these questions: What took longer than expected? → Document the fix What failed unexpectedly? → Add to "Common Issues" What shortcut was discovered? → Add to "Token Saving Tips" What assumption was wrong? → Correct in documentation

Step 3: Categorize the Learning

Category · Where to Add · Example New shortcut · "Token Saving Tips" · OTP visible in email preview Failure mode · "Common Issues" · Popup blocker breaks flow Better pattern · Main workflow · Check login state first Anti-pattern · "Anti-Patterns to Avoid" · Don't snapshot spam

Step 5: Validate the Update

Ensure updates are: Actionable - Not vague observations Specific - Include exact commands/patterns Formatted - Match existing style Non-redundant - Don't duplicate existing content

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
94 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@different-ai · MIT
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
External requests
Install commands
None (reference only)

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

01
Step 1: Capture the Context

After using a skill, note:

02
Step 2: Identify Learnings

Ask these questions: What took longer than expected? → Document the fix What failed unexpectedly? → Add to "Common Issues" What shortcut was discovered? → Add to "Token Saving Tips" What assumption was wrong? → Correct in documentation

03
Step 3: Categorize the Learning

Category · Where to Add · Example New shortcut · "Token Saving Tips" · OTP visible in email preview Failure mode · "Common Issues" · Popup blocker breaks flow Better pattern · Main workflow · Check login state first Anti-pattern · "Anti-Patterns to Avoid" · Don't snapshot spam

04
Step 4: Update the Skill File

Step 4: Update the Skill File

05
Step 5: Validate the Update

Ensure updates are: Actionable - Not vague observations Specific - Include exact commands/patterns Formatted - Match existing style Non-redundant - Don't duplicate existing content

Discussion

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