report-generator

Use when the user asks to "create a campaign report", "build an executive summary", or "deliver client results"; produces audience-tailored influencer marketing reports (executive, client, internal team) with data tables, narrative, key learnings, and recommendations. Not for raw metric computation — use performance-analyzer. 达人营销报告/结案汇报

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./influencer/report/report-generator/SKILL.md

Quality

Content

67%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, actionable reporting skill with a clear sequenced workflow, explicit missing-artifact fallbacks, and appropriate offloading of templates to a real reference file. Its main weakness is verbosity from repeated authorization/ref-handling prose that could be consolidated.

Suggestions

Consolidate the repeated opaque-ref / WARM-save / authorization rules (currently restated in the Skill Contract, step 2, step 6, and Done-when #5) into a single stated-once section to reduce token weight while preserving the safeguards.

Add an explicit validate→fix→retry checkpoint for the save/distribute path (e.g., re-confirm artifact refs and audience authorization before persistence) to lift workflow clarity above its current checkpoint level.

Consider moving the dense Skill Contract policy block into a referenced contract file so the SKILL.md body stays a lean overview, improving both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the Skill Contract and step 6 repeat the opaque-ref / WARM-save / authorization rules at length several times across sections; this safety prose could be tightened or consolidated without losing the safeguards.	3 / 5
Actionability	Provides a concrete 7-step procedure, a worked report excerpt with a real markdown table, and specific guidance on pairing metrics with source-dated context; minor gaps remain because much of the actionable detail (full templates, charts) lives in the referenced file rather than inline.	4 / 5
Workflow Clarity	A clear 7-step sequence with explicit fallback checkpoints (return a partial shell plus NEEDS_INPUT when an artifact is absent; emit a bound decision: unknown placeholder when the Retro Card is missing/mismatched) and a "Done when" checklist, but it lacks a formal validate→fix→retry feedback loop.	4 / 5
Progressive Disclosure	Good structure with well-signaled one-level-deep references to the real bundle file references/report-templates.md and a clear Reference Materials index; the dense inline Skill Contract / authorization policy is arguably content that could be factored into a reference, leaving minor organization gaps.	4 / 5
	Total	15 / 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, well-formed description that explicitly covers what the skill does, when to trigger it via natural quoted phrases, and how it differs from sibling skills. Minor room for improvement in adding more natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates several concrete deliverable components — "data tables, narrative, key learnings, and recommendations" across three audience types — but they are sub-parts of one overarching action ("produces ... reports") rather than multiple distinct operations, leaving minor coverage gaps versus a fully comprehensive action list.	4 / 5
Completeness	Explicitly answers both "what" ("produces audience-tailored influencer marketing reports ... with data tables, narrative, key learnings, and recommendations") and "when" ("Use when the user asks to ...") with concrete trigger phrases, plus a negative boundary ("Not for raw metric computation").	5 / 5
Trigger Term Quality	Quotes three natural trigger phrases a user would actually say ("create a campaign report", "build an executive summary", "deliver client results") plus audience keywords, but misses common synonyms such as "wrap-up report", "post-campaign report", or "results deck".	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (audience-tailored influencer marketing reporting) and explicitly distinguishes itself from a sibling skill ("Not for raw metric computation — use performance-analyzer"), minimizing wrong-skill conflict risk.	5 / 5
	Total	18 / 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: 20 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: influencer/report/report-generator/SKILL.md
Commit: 888dd38

Reviewed: 6 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.