All skills
simota avatar

/echo

@c805268
by shingo imotasimota/agent-skills85 stars
15

Simulating users to evaluate existing flows and generate synthetic demand: cognitive walkthroughs, feature requests, unmet needs, JTBD, and opportunity trees. Not real-user research.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/echo

This session only. Nothing lands on disk.

referencerecipes-index.md

≈755 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Echo Recipe Registry

The full Recipe table for echo. echo/SKILL.md carries only the dispatch allowlist; this file holds what is needed to execute a Recipe — activation condition and the files to read first.

Read this when a subcommand matched and you need its row, or when scanning what Recipes exist at all.


Recipe Subcommand Default? When to Use Read First
Walkthrough walkthrough ✓ Persona cognitive walkthrough, emotion scoring reference/process-workflows.md, reference/ux-frameworks.md
Confusion Points confusion Identify confusion points, cognitive load, mental model gaps reference/ux-frameworks.md, reference/output-templates.md
Emotion Map emotion Emotion map, detailed friction score analysis reference/ux-frameworks.md, reference/output-templates.md
Persona Switch persona Multi-persona comparison, cross-persona analysis reference/analysis-frameworks.md, reference/cognitive-persona-model.md
Heuristic Evaluation heuristic Nielsen 10 / domain-specific heuristic expert review with severity scoring and evaluator-panel reconciliation reference/heuristic-evaluation.md
SUS Scoring sus System Usability Scale authoring, scoring, and benchmark comparison with percentile / grade / adjective mapping reference/sus-scoring.md
Think-Aloud aloud Concurrent / retrospective think-aloud session moderation, prompt discipline, transcript coding, and finding extraction reference/think-aloud-protocol.md
Multi-Engine multi Tri-engine cognitive walkthrough (Codex + Antigravity + Claude in parallel) over a persona × step matrix. Pattern H scoring (confidence + perspective) plus cross-persona universality. Surfaces cross-persona-universal friction as the strongest synthetic UX signal and preserves single-engine divergent-voice insights. reference/tri-engine-walkthrough.md, _common/SUBAGENT.md, _common/MULTI_ENGINE_RECIPE.md
Council council Persona Council mode (v4 fold-in): parallel multi-persona evaluation against a machine-readable Persona Contract (situation/goal/fear/comprehension/success/disqualification). Strict "no subjective opinion" output discipline — behavior trace + disqualification trigger + correction proposal only. Persona weights: Primary (must-pass) / Secondary (must-not-degrade) / Non-target (don't optimize) / Risk (block on damage). Required for nexus growth-acceptance Phase 0 persona evaluation. Cost-capped per Org Tier (Solo: skip, SMB: max 3 personas, Enterprise: max 9). (inline below) + reference/cognitive-persona-model.md
Synthetic Demand demand Feature request, unmet need, challenge, roleplay, JTBD, 5 Whys, Opportunity Tree, or multi-engine demand; select `request need

Source: SKILL.md on GitHub

1 warning13d5 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    The 'echo' skill is a comprehensive UX evaluation tool that simulates user personas to perform cognitive walkthroughs and demand analysis. The analysis found no malicious patterns, obfuscation, or unauthorized data access. It uses standard inter-agent communication and platform-specific CLI tools for its multi-engine evaluation features.

  • Socket13d

    1 alert: gptAnomaly

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    3/11 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at c805268. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/echo