proof-point-packager

Use when the user asks to "package our proof points", "build reusable stat cards and case snippets", or "put proof where each pillar makes its claim"; turns claims-ledger-approved proofs into reusable proof modules — stat cards, case snippets, testimonial blocks, comparison proofs — each pinned to a message-house pillar and the ledger claim ID it substantiates, and flags any pillar making a claim with no approved proof behind it. Never adjudicates a proof: unverified or ledger-absent proofs are marked '[needs source]' and routed to the claims candidates. Not for adjudicating or substantiating claims — use offer-claims-registry; not for fabricating a benchmark to fill a gap — a missing proof is flagged, not invented; not for scoring narrative quality — use narrative-quality-auditor. 证据模块/证据卡/客户案例/主张对齐

Quality

92%

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

85%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 a clear, validated workflow and good progressive-disclosure structure, but loses a conciseness point to heavy repetition of the scope-guard and routing rules across multiple sections.

Suggestions

State each scope-guard rule once — 'packages, it does not adjudicate' and 'never writes memory/claims/claims-ledger.md directly' each recur 4–5 times across the intro, Scope guard, Skill Contract, Instructions, and Save Results; consolidate into a single 'What this skill does not do' list.

Break the long Scope guard run-on sentence into a tight bulleted list of boundaries, each with a single cross-reference to the owning skill.

Merge the repeated TALE E/L framing from the opening paragraph and the Skill Contract into one statement to cut roughly a third of the body length.

Dimension	Reasoning	Score
Conciseness	The content is specific and free of basic-concept padding, but the scope-guard language ('packages, it does not adjudicate', 'never writes memory/claims/claims-ledger.md directly') is restated 4–5 times across the intro, Scope guard, Skill Contract, Instructions, and Save Results, so it could be materially tightened.	2 / 3
Actionability	Gives concrete, executable guidance for an instruction-only skill — exact paths (memory/claims/claims-ledger.md, memory/events/claims.ndjson), routing (operation: propose to registry-events.py), module schemas (stat card = one metric + Measured/User-provided source + as-of date), and a 6-step workflow.	3 / 3
Workflow Clarity	A clear 6-step sequence with an early NEEDS_INPUT stop in step 1 and an explicit Self-check validation checklist in step 6, plus 'Done when' criteria — matching the anchor for clear sequence with validation checkpoints.	3 / 3
Progressive Disclosure	The body is an organized overview with well-signaled one-level-deep references (skill-contract.md §Handoff/Save/Termination, CONNECTORS.md, SECURITY.md) each given a one-line description; no local bundle files exist to score against, and the external references are cleanly navigable.	3 / 3
	Total	11 / 12 Passed

Description

100%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.

The description is maximally specific, complete, and distinctive with explicit user-facing triggers and clear scope boundaries. Its only weakness is verbosity — the field is dense and could be tightened without losing any scored capability, though none of the four dimensions drop below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'turns claims-ledger-approved proofs into reusable proof modules — stat cards, case snippets, testimonial blocks, comparison proofs — each pinned to a message-house pillar and the ledger claim ID…flags any pillar making a claim with no approved proof' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Clearly answers both what (packages proofs into named module types, pins each to a pillar and claim ID, flags gaps) and when ('Use when the user asks to…'), with explicit triggers — the strongest completeness anchor.	3 / 3
Trigger Term Quality	Explicit user-quoted triggers ('package our proof points', 'build reusable stat cards and case snippets', 'put proof where each pillar makes its claim') plus keyword tags '证据模块/证据卡/客户案例/主张对齐' give good coverage of natural terms a marketing user would say.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche and disambiguates with explicit 'Not for…' redirects ('use offer-claims-registry', 'use narrative-quality-auditor'), making conflict with adjacent skills unlikely.	3 / 3
	Total	12 / 12 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: 33 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: narrative/land/proof-point-packager/SKILL.md
Commit: 4a77c48

Reviewed: 9 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.