Install
$ agentstack add skill-cablate-audience-outcome-lens-audience-outcome-lens ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Audience Outcome Lens
Use this skill as a small reasoning checkpoint, not an end-to-end method, an audience-analysis deliverable, or a substitute for domain expertise.
Decide whether the lens matters
Apply the lens when changing the people, their situation, or the intended change could reasonably change what should be emphasized, omitted, sequenced, explained, or recommended.
Do not apply it when success is defined by objective, audience-independent acceptance criteria. In mixed tasks, keep factual and technical work exact and use the lens only for the audience-dependent presentation or behavior.
Form a provisional frame
Before acting, infer only what is useful for the task:
- Who is the primary recipient or user of the result?
- Who else will be affected or holds relevant decision authority?
- What relevant situation are they in now?
- What should become different for them if the result is useful?
- What evidence, constraints, or prior decisions shape the work?
- What remains unknown, and would knowing it materially change the result?
Treat the frame as provisional. Distinguish supplied facts and direct observations from assumptions without forcing a worksheet or questionnaire. Infer only task-relevant characteristics; do not substitute stereotypes for evidence.
Keep recipients, users, decision-makers, and affected parties distinct when their needs conflict. Do not collapse them into one persona unless the task supports that choice.
Ask the user only when an unresolved point permits materially different valid directions and cannot be safely inferred or verified. If a provisional assumption is low-risk and easy to revise, state it only when useful and continue.
Let the frame guide execution
- Use the frame to decide what deserves attention and what can be omitted.
- Carry the same frame into the relevant domain or format skill for the actual work; do not restart discovery or prescribe a universal content structure, visual pattern, action, workflow, or success metric.
- Match the depth and scope of the response to the user's request.
- Preserve user-supplied facts, intended meaning, wording explicitly marked as fixed, constraints, and stated decision rights. Do not invent missing details to make the result feel complete.
- Let accuracy, evidence, safety, non-manipulation, and the user's explicit scope outrank the intended outcome. Do not cherry-pick evidence or invent success metrics to support a preferred result.
- Keep exact transformations and bounded checks bounded.
Check usefulness
Before finishing, consider:
- Does the result make sense for the intended people in their situation?
- Does it support the intended change rather than merely look complete?
- Does it hide a material conflict between primary and affected people?
- Does a consequential choice rely on an unsupported assumption?
- Does the result remain within the requested scope?
When evidence or user feedback contradicts the provisional frame, update the frame and revise the work. Let the situation determine how to verify and iterate; do not impose a fixed ritual or stopping rule.
Complete the original task rather than returning a worksheet. Keep this reasoning internal unless exposing it would help the user evaluate a meaningful choice or resolve an important unknown.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cablate
- Source: cablate/audience-outcome-lens
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.