Review social posts before publication or assess the maturity of a social program. Check claims, disclosures, engagement practices, reuse permissions, and metric definitions, with separate results for publishing checks and operational assessments.
Use when the user asks to "audit our social presence" or "is this batch safe to publish"; runs either the typed ECHO asset gate or a separate program-maturity profile, with channel-truth, claim, disclosure, manipulation, UGC-rights, and denominator checks. Not for creator deliverables — use creator-content-auditor; not for launch readiness — use launch-readiness-auditor. 社媒资产门/运营成熟度/发布前放行
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Run one ECHO profile on one unit. The asset-gate audits a publish package and its governing records; program-maturity profiles audit a channel portfolio/window. Social outcomes remain measured metrics, not part of either rubric score.
Run ECHO asset-gate on this five-post batch against channel/claims/UGC records.
Audit the last 90 days with program-maturity-community; report outcomes separately.
Reads: one asset package or one channel portfolio/window, current governance projections, and dated evidence. Writes: only a permissioned v3 artifact. Done when: one profile is complete or its Unknowns are explicit, with no publication, queue, registry, or engagement side effect.
channel-registry, offer-claims-registry, and permission/consent state own truth. This skill judges frozen state and never manufactures permissions or updates canonical records.
| Need | Preferred evidence |
|---|---|
| Channel truth | Current channel projection, account control, dated rules |
| Asset craft | Exact rendered/caption/package version and narrative canon |
| Claims/disclosures | Approved claims plus market/platform relationship facts |
| Hosting/rights | Permission events, advocacy evidence, response/moderation logs |
| Observability | Native exports, GA4/GSC, denominator definitions, locked panels |
| Public signal | Compliant public connectors; adjacent sources labeled proxy |
../../../references/auditor-runbook.md../../../references/scoring-semantics.md../../../references/echo-benchmark.md../../../references/runtime-invocation.mdreferences/auditor-runtime.mdRead ../../../references/auditor-runbook.md, scoring-semantics.md, echo-benchmark.md, and the ECHO catalog entry. Standalone installs use bundled immutable references/auditor-runtime.md; never fetch mutable main. Before deterministic calls, follow runtime-invocation.md, resolve AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}", and require the scorer, validator, and typed catalogs. If unavailable, return score_state: NOT_SCORED / score_confidence: not_scored with no gate verdict or persistent artifact.
Declare target, profile, assessment_mode, program_archetype, channels, market, window, and observation date. Use assessment_mode: asset plus program_archetype: not-applicable for asset-gate; use assessment_mode: program plus the exact community|b2c|founder archetype for a maturity profile. Profile and context must match.
asset-gate: score E1, C1–C10, H1/H2, and O1. An observed asset with no performance rate/metric claim passes O1; missing asset access is Unknown.program-maturity-community: score E/H/O with community weights.program-maturity-b2c: score E/H/O with feed-led weights.program-maturity-founder: score E/H/O with founder-led weights.Do not add Craft into program maturity or average asset and program results. Every observed state needs source/date/type/confidence. Closed-platform data requires user export; missing private evidence is Unknown.
Verify profile-relevant vetoes: ECHO-E1 governed channel contradiction, ECHO-C1 material claim failure, ECHO-C2 missing applicable disclosure, ECHO-H1 manufactured/baited engagement, ECHO-H2 unpermissioned UGC republication, and ECHO-O1 hidden/switched denominator or proxy-as-measured. Run the typed scorer.
DONE/SHIP, final 88.DONE_WITH_CONCERNS/FIX, final 59.DONE/BLOCK, no final score.NEEDS_INPUT/UNDECIDED, no score.State asset-gate or exact maturity profile in every result. On trace request, qualify all ECHO IDs, especially ECHO-O1 versus ROAS-O1 and ECHO-E1 versus TALE-E1.
Begin with the auditor-runbook's exact typed conversation header. Never replace status, verdict, or score_state with prose; list each explicitly missing qualified item as ``ID: `unknown``` before findings.
Show verdict, unit/profile/context/date, score or coverage/interval, confidence, included-item detail, verified critical controls, Unknown inputs, and fixes. For asset batches, identify the exact asset/location. Never publish or unpause a queue based only on the audit; separate explicit approval is required.
Persist only after explicit authorization to memory/audits/social/YYYY-MM-DD-<topic>.md. Preserve the scorer's orthogonal status and verdict; validate the complete v3 draft with validate-audit-artifact.py against the intended relative path, persist only through one full-content Write, and revalidate the target per the auditor runbook. Edit/shell/MCP mutations of the reserved sink are unsupported. Do not autonomously write channel state, permissions, claims, queues, or hot cache.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Audit paid advertising accounts before increasing spend by comparing campaign exports with your own sales or lead records. Review 20 criteria covering measurement, spending, and safety, then receive a decision and prioritized fixes.
Create paid-ad headlines, descriptions, and opening hooks that match the destination page. Build a matrix of messaging angles and variants, check format limits, and flag unsupported claims or policy risks before handing the set off for review.
Plan advertising and landing page experiments with a clear hypothesis, controlled variants, sample sizes, and duration. Interpret exported results by separating statistical evidence from meaningful business impact, applying an action rule only when its owner approved it in advance.
Design employee and founder sharing programs with voluntary participation, personalized share kits, disclosure lines, and staggered posting windows. Get roster and Slack or Teams distribution specifications, plus safeguards against identical coordinated posts and organized engagement exchanges.
Reconcile paid advertising conversions with GA4 or ecommerce order records. Identify duplicate and unmatched claims, align attribution windows and currencies, compare how models assign credit, and assess additional orders when test and control data are available.
Turn customer interviews and won or lost deal notes into a map of buyer beliefs, recurring objections, and reasons to switch or stay. Each finding includes its evidence, with suggested ways to address objections and clear labels for assumptions.