bid-strategy-planner

Use when the user asks to "pick a bid strategy", "set a tCPA/tROAS target", or "plan the learning-phase entry"; produces a bid-strategy choice (tCPA / tROAS / max-conversions / manual CPC), the starting target math, a portfolio grouping map, and a learning-phase entry plan. Not for splitting the budget across campaigns — use budget-optimizer; not for in-flight pacing/scale moves — use budget-pacing-monitor; not for scoring the account — use ad-account-auditor. 出价策略/tCPA目标/tROAS/学习期

Quality

85%

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

71%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.

The body is a well-structured, operational plan skill: concrete selection rules, target math, a decision gate, and clean one-level-deep references to a real bundle file. Its main weakness is repetition of sibling-skill boundary disclaimers across four sections, which slightly undermines token efficiency.

Suggestions

Consolidate the budget-optimizer / budget-pacing-monitor / ad-account-auditor boundary disclaimers into one place (e.g. the intro or Next Best Skill) and reference it rather than restating in Instructions steps 5–6 and the Skill Contract.

Tighten the 'Done when' criteria so they state acceptance conditions without re-narrating the step content already covered in Instructions.

Add a short explicit verification step to the workflow (e.g. 'Before saving, confirm every input metric is labeled Measured/User-provided/Estimated and no figure is invented') to close the feedback loop and lift workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but the sibling-skill boundaries (budget-optimizer / budget-pacing-monitor / ad-account-auditor) are restated in the intro, Skill Contract, Instructions steps 5–6, and Next Best Skill, and the 'Done when' criteria repeat the step content — tighter than anchor 4's 'minor instances', matching anchor 3's 'could be tightened'.	3 / 5
Actionability	Provides concrete executable guidance — a 6-step selection rule (revenue+volume→tROAS, fixed-CPA+volume→tCPA, etc.), target formulas (starting_tCPA ≈ trailing_CPA × 1.0–1.1), a Measured/User-provided/Estimated labeling scheme, and a save path — with minor gaps where full thresholds defer to the reference file, matching anchor 4.	4 / 5
Workflow Clarity	A clear numbered 6-step sequence is paired with a Decision Gate ('Stop and ask' vs 'Continue silently') and 'Done when' criteria serving as checkpoints, plus an explicit 'flag scaling risk' handoff; not a 5 because there is no explicit verify-output feedback loop, matching anchor 4's 'clear sequence with most checkpoints present'.	4 / 5
Progressive Disclosure	SKILL.md is a lean overview that offloads the bulk of detail (selection matrix, formulas, portfolio template, learning-phase checklist) to references/bid-strategy-matrix.md — a real, well-organized, one-level-deep file — with a dedicated Reference Materials section signaling each path, matching anchor 5.	5 / 5
	Total	16 / 20 Passed

Description

100%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.

This is an exemplary description: it states concrete capabilities, opens with natural quoted trigger phrases, answers both what and when explicitly, and draws clear negative boundaries against three sibling skills. No first/second-person voice issues; no vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete outputs — 'a bid-strategy choice (tCPA / tROAS / max-conversions / manual CPC), the starting target math, a portfolio grouping map, and a learning-phase entry plan' — giving comprehensive coverage of concrete actions, matching the 5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' ('produces a bid-strategy choice... starting target math, a portfolio grouping map, and a learning-phase entry plan') and 'when' ('Use when the user asks to...') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Quotes natural user utterances as triggers — '"pick a bid strategy"', '"set a tCPA/tROAS target"', '"plan the learning-phase entry"' — plus domain keywords (出价策略/tCPA目标/tROAS/学习期); these are phrases a user would actually say, matching the 5 anchor.	5 / 5
Distinctiveness Conflict Risk	Explicit negative boundaries name three sibling skills — 'Not for splitting the budget... use budget-optimizer; not for in-flight pacing... use budget-pacing-monitor; not for scoring the account... use ad-account-auditor' — giving a clear niche with minimal conflict risk, matching the 5 anchor.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 15 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/orchestrate/bid-strategy-planner/SKILL.md
Commit: 64562bc

Reviewed: 3 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.