langbot-skills-maintenance

Maintain the langbot-skills repository with low duplication. Use when adding, editing, or auditing LangBot skills, references, cases, troubleshooting entries, indexes, or periodic entropy-control checks for this skills repository.

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 well-structured, token-efficient body: concrete CLI commands, a clear routing table, and proper offloading of audit detail to an existing reference. The only weaknesses are deferred validation specifics ("Run the checks in `AGENTS.md`") and the absence of error-recovery guidance after checks fail.

Suggestions

Name the specific post-edit checks (or inline the key commands from AGENTS.md) in Workflow step 5 instead of deferring wholesale to AGENTS.md, so validation is self-contained.

Add a brief fix-and-retry loop after the validation steps (e.g., what to do when `bin/lbs index --check` or the AGENTS.md checks fail) to strengthen workflow feedback.

Dimension	Reasoning	Score
Conciseness	The ~35-line body is lean with zero padding: no explanations of concepts Claude already knows, and every line is a directive ("Prefer extending an existing reference...", "Do not hardcode local ports..."). Every token earns its place, matching the top anchor.	5 / 5
Actionability	Concrete executable commands are provided ("rg \"<feature\|error\|case id>\" skills", "bin/lbs case list", "bin/lbs index --check") alongside a precise asset-to-path classification table. Minor gaps: "Run the checks in `AGENTS.md`" defers without naming the checks, and the entropy rules are qualitative directives rather than executable steps.	4 / 5
Workflow Clarity	The 5-step Workflow has a clear sequence with validation checkpoints: search-before-add (step 3) and post-edit checks (step 5), plus "Use `bin/lbs index --check` to verify the committed index is current". It stops short of the top anchor because the post-edit checks are only referenced, not enumerated, and there is no fix-and-retry guidance when a check fails.	4 / 5
Progressive Disclosure	The body is a compact overview with well-organized sections (Workflow, Entropy Rules), and periodic-audit detail is correctly split into a real, clearly signaled one-level-deep reference: "For periodic repository audits, read `references/curation-workflow.md`", which exists in the bundle. Content is appropriately split with easy navigation.	5 / 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: third-person, concise, with an explicit 'Use when' trigger clause and concrete repo-specific vocabulary. The main 'what' statement is slightly thin ("maintain... with low duplication") and a few natural synonyms are absent, which keeps two dimensions at 4.

Dimension	Reasoning	Score
Specificity	"Maintain the langbot-skills repository with low duplication" names the domain, and "adding, editing, or auditing" plus the enumerated asset types (skills, references, cases, troubleshooting entries, indexes) give several concrete actions. The core 'what' verb is the single generic "maintain", so coverage has minor gaps rather than the comprehensive multi-action listing of the top anchor.	4 / 5
Completeness	It explicitly answers both: the what is "Maintain the langbot-skills repository with low duplication" and the when is a concrete "Use when adding, editing, or auditing..." clause listing specific triggers. This matches the top anchor of clear what AND when with concrete trigger phrases, and exceeds anchor 4 where the 'when' is only adequate.	5 / 5
Trigger Term Quality	Natural terms a repo contributor would say are present: "LangBot skills", "references", "cases", "troubleshooting entries", "indexes", "adding, editing, or auditing". A few natural variations are missing (e.g., "curation", "fixtures", "suites", "duplicates"), so it falls just short of the comprehensive synonym coverage of the top anchor.	4 / 5
Distinctiveness Conflict Risk	"langbot-skills repository" with repo-specific triggers (LangBot skills, cases, suites, fixtures, troubleshooting entries) carves out a clear niche with minimal overlap risk against generic skills. No generic phrasing like "helps with files" that would fire on unrelated requests.	5 / 5
	Total	18 / 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: langbot-app/LangBot
Path: skills/skills/langbot-skills-maintenance/SKILL.md
Commit: 40a3a94

Reviewed: 3 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.