Correct

Text instructions decay; structure reruns. This skill converts a repeated agent mistake into an enforcement the mistake cannot survive.

When to use

the same class of error appears twice or more (wrong import path, missed codegen step, broken invariant, slop pattern)
retrospective findings in .omc/notepads/ or review history name recurring friction

Workflow

Collect. Mine the evidence — resolve OMC's state root first (the checkout's .omc/ by default; OMC_STATE_DIR or a parent .omc-workspace moves it, and a package-subdirectory launch must not read a stray checkout-local .omc): the notepads under <state-root>/notepads/*/problems.md, the verification ledger at <state-root>/state/verification-ledger.tsv, review comments, recent fix commits. Group by root cause, not by symptom.
Rank. Frequency × cost. Take the top mistakes; one at a time.
Pick the highest enforcement level that works:
1. linter rule / compiler error — the mistake stops compiling
2. type-level guard — the mistake stops type-checking
3. runtime check or assertion — the mistake fails loudly at the boundary
4. script or codemod — the correct action is one command
5. project skill text — the last resort; note why every higher level failed
Implement the enforcement with its exception path documented (how a legitimate case opts out).
Prove it fires. Reproduce the mistake deliberately and show the enforcement catching it, with real output. An enforcement you have not seen fire is a hypothesis (an external benchmark-checklist discipline applies).
Record honestly: the ledger verdict matches what the repro actually exercised — a lint rule or type guard firing is enforcement-verified, a runtime check exercised by a test is unit-test-verified, a proof is formally-verified. Never record a stronger verdict than the evidence.

Rules

Never weaken an enforcement to make a test pass; the enforcement is the requirement now.
Record what was encoded in the state-root ledger (<state-root>/state/verification-ledger.tsv per the collection step) with the verdict the repro actually exercised (see workflow step 6) and the repro command as evidence.
Text added at level 5 references this skill, so the next occurrence tries to climb the ladder again.

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

82/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

88

Quality

85

Clarity

79

Completeness

74

Summary

A structured methodology for converting repeated agent mistakes into enforced constraints, using a five-level escalation from linter rules to text documentation. The skill provides a workflow to identify recurring errors, rank them by frequency and impact, select the appropriate enforcement mechanism, implement it with exception handling, verify it catches the mistake, and record verification results in a ledger.

Detected Capabilities

file readledger parsingverification documentationenforcement specification

Trigger Keywords

Phrases that agents use to match this skill to user intent.

eliminate recurring mistakesenforce code patternslinter rule enforcementverification ledgermistake-to-guard conversion

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.com

Use Cases

Eliminate recurring code patterns by enforcing them at compile/lint time
Create escalating guardrails for common mistakes (import paths, codegen steps, invariant violations)
Build a verified ledger of enforced constraints and their evidence
Convert retrospective code review findings into automated checks
Systematically harden a codebase against repeated error classes

Quality Notes

Methodology is well-scoped to the problem domain (error elimination) with explicit workflow steps that an agent can follow sequentially
Five-level enforcement hierarchy is concrete and actionable: linter → type → runtime → script → text
Emphasis on proof and verification ('prove it fires') is a strong quality signal — enforcements must be demonstrated to work, not assumed
Rules section explicitly forbids weakening enforcement to pass tests, which maintains the integrity of the system
Ledger record format is specified (.tsv with verdict field) providing a structured output the agent can produce
Scope boundaries are well-defined: operates on `.omc/` state root, notepads, verification ledger, and review history — all localized to project context
Exception handling requirement (documenting how legitimate cases opt out) is a mature constraint design principle
Instructions reference specific file paths (.omc/notepads/, state/verification-ledger.tsv) grounding the workflow in concrete artifacts

Model: claude-haiku-4-5-20251001Analyzed: Nov 8, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

correct