Profile My skills Saved My plugins Edit profile Submit a skill

← all publishers

Emasoft

@emasoft source repo

9 published skills

  1. ▌
    Pss Usage · emasoft bundle
    Use when interpreting element suggestions or troubleshooting PSS. Used by pss-agent-profiler. Trigger with /pss-status.
    1 install
  2. ▌
    Pss Authoring · emasoft bundle
    Use when writing skills for PSS discovery or improving suggestion accuracy. Used by pss-agent-profiler. Trigger with /pss-authoring.
    1 install
  3. ▌
    Pss Agent Toml · emasoft bundle
    Use when creating .agent.toml profiles. Trigger with /pss-setup-agent. Loaded by pss-agent-profiler. AI selects elements, validates coherence.
    1 install
  4. ▌
    Pss CLI Reference · emasoft bundle
    Use when the user wants to query the PSS index, search/list/inspect elements, run lifecycle or history queries, build a plugin from a profile, or anywhere a `pss …` CLI command is needed. Loaded by pss-agent-profiler.
    1 install
  5. ▌
    Pss Benchmark Agent · emasoft bundle
    Use when running benchmark competitions or improving scoring accuracy. Used by pss-agent-profiler. Trigger with /pss-benchmark.
    1 install
  6. ▌
    Pss Agent Archetypes · emasoft bundle
    Use when creating an agent that orchestrates several skills, choosing between ALL-IN-ONE, ONE-FOR-ALL and PLUGIN-OMNI, or deciding whether to preload skills into an agent's frontmatter. Covers the preload-vs-access distinction and the `fork` terminology trap. Trigger with /pss-make-agent.
    1 install
  7. ▌
    Pss Design Alignment · emasoft bundle
    Use when augmenting an .agent.toml with project requirements. Loaded by pss-agent-profiler. Trigger with /pss-change-agent-profile --requirements.
    1 install
  8. ▌
    Text Categorization Improver · emasoft bundle
    Use when improving categorization, scoring, or matching accuracy via parallel experimentation. Used by pss-agent-profiler. Trigger with /text-categorization-improver.
    1 install
  9. ▌
    Verification Before Completion · emasoft
    Use before reporting any task as done, fixed, passing, or complete — to verify the claim by running it and reading the real output rather than asserting from intent.
    1 install