failure-codifier

Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores. SSOT promotion to patterns.md or decisions.md is proposal-only — human-approval-required. Use when user mentions failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals. Do NOT load for: direct SSOT edits, auto-promotion, or implementation unrelated to failure analysis.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-structured body with executable commands and clean one-level-deep references; the read-only/proposal-only design keeps destructive-operation risk off the table. Slightly weaker on actionability and workflow clarity because the validation checklist and example proposal output are delegated to the reference rather than shown inline.

Suggestions

Add a short example of the failure-rule.v1 JSON proposal output (or a minimal field sketch) so Claude can act on dry-run results without opening the reference.

Inline the key review-checklist items (evidence_refs trace, confidence matches count, proposed_ssot_target appropriate) as a compact validation step before pointing to the full reference.

State explicitly that the workflow is read-only/non-destructive so the validation-cap rule is unambiguously satisfied rather than merely implied.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude's competence — no concept exposition, no padding — with concrete thresholds and file paths earning their tokens; every section adds only what Claude would not already know.	5 / 5
Actionability	Provides copy-paste ready commands ('./scripts/failure-codifier-propose.sh --dry-run', 'cd go && go test ./internal/failurecodifier/... -count=1') and concrete paths, but does not show the emitted JSON shape or an example proposal inline, leaving a minor gap.	4 / 5
Workflow Clarity	A clear recommended dry-run sequence with an explicit read-only/no-write guarantee and a separate test step; the detailed review checklist and validation feedback loop live in the referenced promotion-workflow.md, leaving minor checkpoint gaps inline.	4 / 5
Progressive Disclosure	Well-organized overview sections pointing to a single one-level-deep real reference (references/promotion-workflow.md) and concrete schema/core paths, with content appropriately split and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with concrete actions, explicit trigger guidance, and a clear negative-boundary clause that reduces conflict risk. The only minor gap is the absence of format/extension-based trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Extract recurring failure patterns', 'emit failure-rule.v1 proposals with confidence scores', 'SSOT promotion ... is proposal-only' — against named sources (breezing orchestration logs, Judgment Ledger), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (extract patterns, emit proposals with confidence scores) and when ('Use when user mentions ...'), supplemented by clear negative 'Do NOT load for' guidance.	5 / 5
Trigger Term Quality	Provides several natural phrases users would say ('failure codifier, failure patterns, self-learning loop, codify failures, or failure-rule proposals'), but lacks file-extension or format-based synonyms that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	Niche triggers tied to breezing orchestration and Judgment Ledger plus an explicit 'Do NOT load for' boundary yield a clear niche with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: Chachamaru127/claude-code-harness
Path: opencode/skills/failure-codifier/SKILL.md
Commit: 7d8deba

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.