qstack-encode-lessons-in-structure
/qstack-encode-lessons-in-structure
Turn a recurring correction or repeated instruction into the strongest practical structural guardrail. Use when the same mistake returns, prose is being repeated, or a rule could become a type, schema, lint, check, or script.
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 1
No signals detected. Repository changed on 18.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Turn a recurring correction or repeated instruction into the strongest practical structural guardrail. Use when the same mistake returns, prose is being repeated, or a rule could become a type, schema, lint, check, or script.
Original author description
Turn a recurring correction or repeated instruction into the strongest practical structural guardrail. Use when the same mistake returns, prose is being repeated, or a rule could become a type, schema, lint, check, or script.
How it works
- Route the lesson
SKILL.md preview
--- name: qstack-encode-lessons-in-structure description: > Turn a recurring correction or repeated instruction into the strongest practical structural guardrail. Use when the same mistake returns, prose is being repeated, or a rule could become a type, schema, lint, check, or script. license: MIT --- # Encode lessons in structure Text asks every future reader to notice, remember, and comply. A structural mechanism applies the lesson without relying on memory. ## Route the lesson 1. Identify the concrete correction and evidence that it recurs. Keep a true one-off as local context instead of turning it into a universal rule. 2. Choose the strongest practical mechanism: - a state or type that cannot represent the invalid case; - a schema, lint, banned API, or CI check that fails before merge; - one canonical helper or generator that removes duplicate choices; - a runtime boundary check with a clear failure; - a written instruction only when human judgment is irreducible. 3. Implement the mechanism only when the user's request authorizes that edit. Otherwise propose the exact target and expected failure behavior. 4. Remove prose or duplicate paths that the new mechanism supersedes. Keep one source of truth, but only after proving the mechanism covers the old rule. 5. Exercise the known failure and show that the mechanism catches it. Route recurring fixes to a local skill or tool and systemic rules to the smallest shared layer that can enforce them. Recording a lesson without a mechanism that enforces it does not stop the next occurrence. Do not invent recurrence; cite the correction or failure that shows the pattern. Analysis alone does not authorize edits, commits, pushes, publishing, deployment, or external messages. Adapted from Lauren Tan's PStack [`principle-encode-lessons-in-structure`](https://github.com/cursor/plugins/blob/60c641e4fad674784b30abcf9f8915dea39df38d/pstack/skills/principle-encode-lessons-in-structure/SKILL.md) at commit `60c641e4fad674784b30abcf9f8915dea39df38d` under the MIT License. See [third-party notices](../../THIRD_PARTY_NOTICES.md).
Files in this package (2)
- SKILL.md 2 KB
- agents/openai.yaml 1 KB
Versions
The database has no other skills named qstack-encode-lessons-in-structure.
Database snapshot: 13.11.2026 · package version c9619a239eff (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 96principle-encode-lessons-in-structure
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. - 96principle-encode-lessons-in-structure
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. - 96principle-encode-lessons-in-structure
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. - 90mistake-to-constraint
Use when a mistake repeats. Encode it as the strongest guard — type or runtime, lint, test, directory convention, then a rules line — and log it in CONSTRAINTS.md. - 100principle-encode-lessons-in-structure
Use when you catch yourself repeating an instruction or the user corrects the same thing again. Convert the lesson into a check that breaks on violation (a lint rule, type, runtime assertion, or script) in place of more prose. - 96principle-encode-lessons-in-structure
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.