CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-parity

Use when building or extending a golden-master/differential conformance harness against a reference implementation — ports, rewrites, legacy capture. Defines the two-tier oracle, determinism engineering at capture time, the divergence-fencing pattern, and the golden ratchet. testing-strategy says WHERE goldens belong; this skill says HOW to build a harness that never flickers and never lies.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An exceptionally well-engineered instruction skill: every rule is paid for with a rationale, each failure mode has a named technique, and destructive operations are fenced with explicit validation. Minor room remains in trimming anecdotes and splitting a section or two into reference files.

DimensionReasoningScore

Conciseness

Dense, rule-per-line prose that assumes Claude's competence ('Missing golden = panic, not skip', 'pin the root (`branch~N`) explicitly'); only minor anecdotal padding (the gitweb war story and the overturned-'impossible' aside) keeps it from the leanest anchor.

4 / 5

Actionability

For an instruction-only skill the guidance is maximally actionable: a volatility-class → named-technique lookup table, a 3-step endpoint wiring recipe, a 4-step divergence-fencing pattern, and concrete commands ('.gitattributes goldens/** binary', 'git diff goldens/', 'scripts/golden-audit.bb').

5 / 5

Workflow Clarity

Sub-workflows are explicitly sequenced with validation checkpoints and feedback loops: 'After ANY re-capture: git diff goldens/ and account for every changed byte', 'Re-run the WHOLE golden suite after fixture changes', and an ordered three-diagnosis procedure for failing goldens; re-blessing (the destructive path) is gated behind human-approved commits.

5 / 5

Progressive Disclosure

Seven well-labeled sections with a table and numbered patterns make navigation easy, and the single-file scope is appropriate; at ~125 lines it exceeds the under-50-line simple-skill exception, so a 5 would require some content (e.g., the determinism table) split into a reference file.

4 / 5

Total

18

/

20

Passed

Description

87%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 description with an explicit trigger clause, concrete named techniques, and deliberate boundary-setting against a sibling skill. Keyword coverage is good though it omits a few common synonyms for this testing niche.

DimensionReasoningScore

Specificity

Names several concrete capabilities — 'building or extending a golden-master/differential conformance harness', 'the two-tier oracle, determinism engineering at capture time, the divergence-fencing pattern, and the golden ratchet' — though these are technique names rather than an exhaustive action list, matching the 'several specific actions; minor gaps' anchor.

4 / 5

Completeness

Explicitly answers both: 'Use when building or extending a golden-master/differential conformance harness against a reference implementation — ports, rewrites, legacy capture' (when) and 'Defines the two-tier oracle… HOW to build a harness that never flickers and never lies' (what), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrases like 'ports, rewrites, legacy capture', 'golden-master', and 'reference implementation' give good keyword coverage, but common synonyms such as 'characterization tests' or 'snapshot testing' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (golden-master harness construction) with explicit disambiguation — 'testing-strategy says WHERE goldens belong; this skill says HOW' — minimizing conflict risk with the nearest related skill.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/golden-audit.bb)

Warning

Total

15

/

16

Passed

Repository

igouss/gitweb-rs

Path

.claude/skills/golden-parity/SKILL.md

Reviewed

Table of Contents

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.