CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

offer-claims-registry

Use when the user asks to "register this claim", "log our current offers", or "where is the proof for this figure"; curates claim wording, evidence, disclosures, terms, review dates, and live offers through the append-only claims event stream. Not for scoring claim vetoes — use the relevant auditor; not for writing ad copy — use ad-creative-builder. 广告声明台账/优惠信息登记/证据溯源

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 dense, competent protocol skill: an 8-step procedure with genuine verification checkpoints, a correct capability/security model (append-only stream, host-capability principal, untrusted drafts), and no wasted tokens. Its weaknesses are that executable details depend on reference files not present in the bundle (leaving proposal/event schemas undefined here), and that most referenced paths do not resolve to real files, weakening the progressive-disclosure structure.

Suggestions

Inline a minimal proposal.json example (or point to the bundle-local claims-ledger-schema.md for it) so the registry-events.py append command is executable without the missing ../../references/registry-event-protocol.md.

Fix or consolidate the reference list: registry-event-protocol.md and runtime-invocation.md are each listed three times (Runtime Reads, Procedure step 1, Reference Materials) — list them once, and remove or ship the four referenced files that are absent from the bundle.

Add an explicit error-recovery loop after step 8 (e.g., "if `verify claims` fails or a revision check rejects the append, re-read the projection, rebase the proposal on the current revision, and retry once") to close the feedback-loop gap for this append-only, destructive-adjacent workflow.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — no basic-concept explanations anywhere — but the two protocol files are listed three times ("Runtime Reads", Procedure step 1, "Reference Materials"), a minor redundancy that keeps it at anchor 4 rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

One concrete executable command exists ("python3 \"$AARON_SKILLS_ROOT/scripts/registry-events.py\" append claims <proposal.json>") plus an exact NEEDS_INPUT fallback, but the proposal.json and event schemas that make these runnable live in ../../references/registry-event-protocol.md and runtime-invocation.md, which are absent from the bundle — matching anchor 3's 'missing key details' rather than anchor 4's mostly-executable guidance.

3 / 5

Workflow Clarity

The 8-step Procedure is clearly sequenced with real checkpoints ("then `verify claims`" in step 8, optimistic revision checks, the step 2 NEEDS_INPUT early exit), so the destructive/batch cap does not apply; it falls short of anchor 5 because there is no explicit error-recovery loop (nothing says what to do when `verify claims` or a revision check fails).

4 / 5

Progressive Disclosure

The overview/reference split is well signaled, but scored against the actual bundle: only references/claims-ledger-schema.md exists, while ../../references/registry-event-protocol.md, ../../references/runtime-invocation.md, ../../references/measurement-protocol.md, and ../../SECURITY.md are referenced paths with no corresponding files — anchor 3 ('references present but' with real gaps in organization) rather than anchor 4's mostly-appropriate placement.

3 / 5

Total

14

/

20

Passed

Description

95%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: explicit "Use when" triggers with natural quoted phrasings, a concrete capability statement in third person, and explicit not-for boundaries that route adjacent tasks to other skills. The only weakness is that all capabilities compress into a single verb ("curates") with an object list, slightly thinning the action inventory, and the trailing bilingual summary duplicates content already covered.

DimensionReasoningScore

Specificity

"curates claim wording, evidence, disclosures, terms, review dates, and live offers through the append-only claims event stream" enumerates six concrete registry objects, but they all hang on the single verb "curates", so it matches anchor 4 (several specific actions with minor gaps) rather than anchor 5's multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both: what ("curates claim wording, evidence, disclosures, terms, review dates, and live offers through the append-only claims event stream") and when ("Use when the user asks to 'register this claim'...") with concrete trigger phrases — a direct match for anchor 5; anchor 4's weaker 'when' does not apply.

5 / 5

Trigger Term Quality

Quotes natural verbatim phrases users would actually say — "register this claim", "log our current offers", "where is the proof for this figure" — plus bilingual keywords, matching anchor 5's comprehensive coverage of natural terms including synonyms. Not anchor 4 because it supplies ready-made user phrasings rather than just topical keywords.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (claims/offer registry) and adds explicit negative boundaries — "Not for scoring claim vetoes — use the relevant auditor; not for writing ad copy — use ad-creative-builder" — routing adjacent intents elsewhere, matching anchor 5's minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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: 9 suspicious

Warning

Total

13

/

16

Passed

Repository

aaron-he-zhu/aaron-marketing-skills

Path

protocol/offer-claims-registry/SKILL.md

Reviewed

Table of Contents

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.