encode-lessons-in-structure
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
Skill by baranbingol1
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/baranbingol1-encode-lessons-in-structure
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/encode-lessons-in-structure
What's inside
- Skill name
encode-lessons-in-structure- Description
- Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
- License
- MIT
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Encode Lessons in Structure
Encode recurring fixes in mechanisms (tools, code, metadata, automation) instead of textual instructions. Every error, human correction, and unexpected outcome is a learning signal. Capture it, route it, and close the loop.
**Why:** Textual instructions are easy to miss. They require the reader to notice, remember, and comply. Structural mechanisms (lint rules, metadata flags, runtime checks, automation scripts) enforce the rule without cooperation.
**Pattern:**
When you catch yourself writing the same instruction a second time:
1. Ask: can this be a lint rule, a metadata flag, a runtime check, or a script?
2. If yes, encode it. Delete the instruction
3. If no (genuinely requires judgment), make the instruction more prominent and add an example of the failure mode
**Pick the strongest rung.** When more than one mechanism would work, choose the strongest the situation allows: an unrepresentable state that cannot compile, then a lint or banned API that fails CI, then a canonical helper, then a runtime check, then a skill edit, then a style-guide line. Agents copy whatever the surrounding code already does, and a weaker guard becomes the next template.
**Corollary:** Don't paper over symptoms. If the fix is structural, ONLY use the structural fix. The instruction IS the symptom.
**Feedback loop:**
- **Capture every correction.** When the human intervenes or tests fail, decide if it's a one-off or a pattern.
- **Route to the right layer.** One-off: a memory note. Recurring fix: a skill edit or lint rule. Systemic issue: a principle.
- **Close the loop.** Don't just record. Apply now or create a concrete todo (a bd issue for anything that outlives the session).
**Anti-patterns:**
- Acknowledging without recording ("I'll keep that in mind" does not persist)
- Recording without routing (a note about a lint rule that should exist is wasted unless the lint rule gets implemented)
- Fixing without generalizing (fixing one instance while leaving the recurring pattern intact)From baranbingol1/bbstack, MIT.
More from baranbingol1/bbstack
- 0.529score
implement
baranbingol1
Implement a piece of work from a spec, bd ticket, or direct request.
SkillBFreshness: BClaude Code +9 - 0.524score
diagnose
baranbingol1
Diagnosis loop for bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.521score
autoresearch
baranbingol1
Autonomous experiment loop that optimizes one measurable metric: try an idea, measure, keep wins, revert losses, repeat until a stop predicate is met.
SkillBFreshness: BClaude Code +9 - 0.521score
lazy-ladder
baranbingol1
Apply when implementing anything: writing, adding, refactoring, or fixing code, and when choosing libraries or dependencies.
SkillBFreshness: BClaude Code +9 - 0.518score
eval
baranbingol1
Blind-test how a skill or prompt change affects agent behavior before promoting it.
SkillBFreshness: BClaude Code +9 - 0.518score
bb
baranbingol1
Route a request to the right bbstack skill — the one name to remember.
SkillBFreshness: BClaude Code +9 - 0.516score
guard-the-context-window
baranbingol1
Apply during long-running work — implementation runs, orchestration, wiki generation, verification sweeps — when context is filling up: large outputs, long…
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
baranbingol1
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.499score
grilling
baranbingol1
Grill the user relentlessly about a plan, decision, or idea.
SkillBFreshness: BClaude Code +9 - 0.498score
explain-diff-html
baranbingol1
Use when the user asks for a rich explanation of a code change, diff, branch, or PR.
SkillBFreshness: BClaude Code +9 - 0.496score
boundary-discipline
baranbingol1
Apply when wiring validation, error handling, or framework adapters.
SkillBFreshness: BClaude Code +9 - 0.494score
demo
baranbingol1
Record a demo of a feature working — video, GIF, or annotated terminal transcript — using the repo's verification skill.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 28, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/baranbingol1/bbstack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from baranbingol1
- 0.529score
implement
baranbingol1
Implement a piece of work from a spec, bd ticket, or direct request.
SkillBFreshness: BClaude Code +9 - 0.524score
diagnose
baranbingol1
Diagnosis loop for bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.521score
autoresearch
baranbingol1
Autonomous experiment loop that optimizes one measurable metric: try an idea, measure, keep wins, revert losses, repeat until a stop predicate is met.
SkillBFreshness: BClaude Code +9 - 0.521score
lazy-ladder
baranbingol1
Apply when implementing anything: writing, adding, refactoring, or fixing code, and when choosing libraries or dependencies.
SkillBFreshness: BClaude Code +9 - 0.518score
bb
baranbingol1
Route a request to the right bbstack skill — the one name to remember.
SkillBFreshness: BClaude Code +9 - 0.518score
eval
baranbingol1
Blind-test how a skill or prompt change affects agent behavior before promoting it.
SkillBFreshness: BClaude Code +9
Cite this page
encode-lessons-in-structure skill. Agent Mart. https://agentmart.dev/skills/baranbingol1-encode-lessons-in-structure (last updated 2026-10-24)