gl-recon

Reconcile general ledger to subledger for a trade date or period — match at the position or transaction level, surface breaks, and classify each break by likely cause. Use for daily or month-end recon runs across asset classes.

Quality

86%

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

85%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 tightly written, well-structured instruction skill with a clear workflow and concrete comparison/bucket/output guidance. Its only gap is the absence of an explicit validation checkpoint in the workflow, which would lift workflow clarity and actionability.

Suggestions

Add an explicit validation checkpoint after Step 2 (e.g. 'Verify matched + break counts reconcile to total input lines before classifying') to close the workflow-clarity gap.

Provide one concrete code/command snippet or a small example input/output row pair to make the guidance copy-paste ready and lift actionability.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: assumes Claude knows reconciliation concepts and gives only the grain, columns, buckets, and causes that matter; no padding or explanation of basics, and every line earns its place.	5 / 5
Actionability	Concrete and executable in concept (explicit keys, comparison columns, bucket table, tolerance values, output spec) but is instruction-only with no code or commands, leaving minor gaps in copy-paste-ready execution detail.	4 / 5
Workflow Clarity	A clearly sequenced four-step process (normalize -> match -> classify -> output) with explicit tolerance defaults and output sorting; lacks an explicit validation/verify checkpoint, which is the minor gap below a 5.	4 / 5
Progressive Disclosure	A well-organized single-purpose skill under 50 lines with clear section headers and no need for external references; the only cross-skill pointer (hand off to 'break-trace') is clearly signaled and one level deep.	5 / 5
	Total	18 / 20 Passed

Description

88%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 that concretely states what the skill does and when to use it, with a clear niche and explicit trigger guidance. Slightly more trigger-term breadth (synonyms like 'recon', 'GL') would push it to the top.

Suggestions

Add common synonyms and abbreviations users say naturally, e.g. 'GL recon', 'subledger reconciliation', 'breaks', 'month-end close', so the trigger term coverage is comprehensive.

Consider naming the extract formats or sources (e.g. GL extract, custodian/subledger feeds) as explicit trigger terms a user might mention.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Reconcile general ledger to subledger', 'match at the position or transaction level', 'surface breaks, and classify each break by likely cause' — with comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly answers 'what' (reconcile GL to subledger, match, surface and classify breaks) and 'when' ('Use for daily or month-end recon runs across asset classes') with a concrete trigger clause.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('general ledger', 'subledger', 'reconciliation', 'trade date', 'breaks') but misses common synonyms like 'recon', 'GL', 'month-end close', and explicit file/scenario triggers, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — GL-to-subledger reconciliation — with distinct triggers that are unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/financial-services
Path: plugins/agent-plugins/gl-reconciler/skills/gl-recon/SKILL.md
Commit: 69cbc81

Reviewed: 10 days 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.