apollo-cost-tuning

Optimize Apollo.io costs and credit usage. Use when managing Apollo credits, reducing API costs, or optimizing subscription usage. Trigger with phrases like "apollo cost", "apollo credits", "apollo billing", "reduce apollo costs", "apollo usage".

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/apollo-pack/skills/apollo-cost-tuning/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

The body is highly actionable with complete, executable code and a clear step sequence, but it is weakened by redundancy with the unused reference file and by the absence of explicit validation checkpoints in the batch enrichment workflow.

Suggestions

Link to references/implementation-guide.md from the body and move the full module implementations there, keeping only a concise overview and one representative snippet inline.

Add an explicit validation/retry loop to the Step 6 pipeline — e.g. verify bulk_match response counts against the batch, handle partial failures, and re-run failed items.

Reconcile the divergent credit models between the body (search is free, enrichment = 1 credit) and the reference (search = 1 credit/result) so they do not contradict each other.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no basics explained), but it inlines six substantial TypeScript modules that overlap heavily with the bundled implementation-guide.md, so it could be tightened by offloading full implementations to the reference.	2 / 3
Actionability	Each step provides complete, executable TypeScript (CreditTracker, dedup, lead-scorer, budget-aware axios client, pipeline) with real endpoints and env vars — copy-paste ready, matching the level-3 anchor.	3 / 3
Workflow Clarity	Steps 1-6 are clearly sequenced and budget enforcement acts as a guard, but the batch enrichment pipeline (batches of 10) has no explicit validation/verification or fix-and-retry feedback loop, which caps workflow clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	A bundle file (references/implementation-guide.md) exists, but the body never references or links to it and instead duplicates overlapping implementations inline — structure is present but content that should be separate is inline, matching the level-2 anchor.	2 / 3
	Total	9 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 explicit what/when guidance and well-chosen natural trigger phrases. The only weakness is that the capability statement stays at a single broad action rather than enumerating the concrete cost-optimization techniques the skill actually performs.

Suggestions

Expand the capability sentence to list 2-3 concrete actions, e.g. "Deduplicate before enriching, score leads before spending credits, and enforce daily credit budgets."

The description uses an oddly folded multi-line YAML string with line breaks mid-sentence; collapse it to a single flowing paragraph to avoid parsing/whitespace artifacts.

Dimension	Reasoning	Score
Specificity	The description states "Optimize Apollo.io costs and credit usage" which names the domain and a broad action, but it does not list multiple distinct concrete actions (e.g. dedup, scoring, budget enforcement) the way a level-3 anchor like "Extract text and tables, fill forms, merge documents" does.	2 / 3
Completeness	It answers both "what" ("Optimize Apollo.io costs and credit usage") and "when" ("Use when managing Apollo credits, reducing API costs, or optimizing subscription usage") with explicit trigger guidance, matching the level-3 anchor.	3 / 3
Trigger Term Quality	It explicitly enumerates natural phrases a user would say — "apollo cost", "apollo credits", "apollo billing", "reduce apollo costs", "apollo usage" — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The Apollo-specific niche and explicit "apollo"-prefixed trigger phrases make it unlikely to fire for unrelated skills, matching the clear-niche level-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/apollo-pack/skills/apollo-cost-tuning/SKILL.md
Commit: 8585d6d

Reviewed: 2 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.