CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

76

Quality

93%

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

87%

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

A tight, actionable reconciliation procedure with a clear step sequence and no unnecessary padding. The only gap is the absence of an explicit validation/control-total checkpoint in a batch recon workflow.

Suggestions

Add an explicit tie-out/validation step after matching — e.g., confirm matched count plus all break buckets equals the input totals on both GL and subledger sides, and flag any unmatched control total before classifying.

Specify what to do when the bucket classification is ambiguous or a break fits multiple causes, so the resolver receives an unambiguous handoff rather than a single forced tag.

Include a quick verification checkpoint before output (e.g., assert the break report row count equals the sum of non-matched buckets) to catch extraction or join errors in the batch run.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: it states the common key, comparison columns, coercion rules, tolerance defaults, and output format without explaining recon concepts Claude already knows, so every token earns its place.

3 / 3

Actionability

Provides concrete, specific guidance — exact keys ('security_id + account + trade_date'), typed coercion rules, a full-outer-join, numeric tolerances ('0.01' on amounts, '0' on quantity), and a precise sort order — which is highly actionable for an instruction-only skill.

3 / 3

Workflow Clarity

The four-step Normalize → Match → Classify → Output sequence is clear, but recon is a batch operation and there is no explicit validation/control-total checkpoint (e.g., verify matched + breaks tie to GL and subledger totals), which caps workflow clarity at 2 per the batch-operation guideline.

2 / 3

Progressive Disclosure

The body is under 50 lines with no external bundle files, and content is organized into four well-signaled sections, so progressive disclosure scores 3 on well-organized sections alone.

3 / 3

Total

11

/

12

Passed

Description

100%

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

The description is concise, third-person, and explicitly covers both capabilities and use triggers with domain-natural terms. It is a strong, low-conflict trigger description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Reconcile general ledger to subledger', 'match at the position or transaction level', 'surface breaks', and 'classify each break by likely cause' — matching the score-3 anchor for several specific actions.

3 / 3

Completeness

Explicitly answers both 'what' (reconcile, match, surface breaks, classify) and 'when' via the 'Use for daily or month-end recon runs across asset classes' clause, matching the score-3 what-and-when anchor.

3 / 3

Trigger Term Quality

Uses natural terms the target audience would say — 'reconcile', 'general ledger', 'subledger', 'recon', 'breaks', 'trade date', 'month-end' — giving good coverage rather than opaque jargon.

3 / 3

Distinctiveness Conflict Risk

The GL-to-subledger reconciliation niche with explicit recon-run triggers is clearly distinct and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
anthropics/financial-services
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.