Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

cogpros

@cogpros source repo

14 published skills

  1. ▌
    Field Report · cogpros bundle
    Manually invoked when the user asks for a "field report" or says "use field-report for this". Generates an interactive HTML report (textareas after every question, three export buttons, light/dark, localStorage) from a canonical template — 15 baseline features + 2 optional patterns. Do NOT auto-fire on description match; manual invocation only. NOT for: read-only audit logs with no user input, non-HTML outputs.
    0
    installs
  2. ▌
    Ghost Hours · cogpros bundle
    Use when (1) closing a work session and measuring what AI did for you, (2) logging a single completed task as a Ghost Hours entry, (3) running reports on accumulated sessions, (4) retrospecting an old entry with FW-R, (5) amending a prior entry, or (6) sharing de-identified data. Classifies sessions as speed (faster) or unlock (not possible without AI), with subtypes for restoration, bypass, and augmentation. Pairs objective metrics with Felt Weight of Completion. Research-compatible data format. Your session-close protocol can invoke this skill as its measurement step. Standalone invocation is correct for one-off task logging. NOT FOR: timing in-progress work, capacity planning, billable-hour tracking, pre-close audits of open items, or any use that exposes the agent's silent FW-C score to the user before retro. Cite: Pollock 2026.
    0
    installs
  3. ▌
    Closing Time · cogpros bundle
    The operator-issued end-of-session protocol for a CLI session: mechanical fact-sheet pre-fill, background repo sweep, capture, clarify, assay, a type-aware Ghost Hours walkthrough, record, seal. Use when the operator asks to close out the session. The Ghost Hours measurement (../../SKILL.md) runs as the Phase 3 sub-step inside this skill. NOT FOR: mid-session checkpointing, mid-session re-orientation, pre-close audit only, one-off log entries (use the ghost-hours skill directly).
    0
    installs
  4. ▌
    Closing Time Autofill · cogpros
    Compatibility alias for closing-time-cli-facts. Use when the operator invokes closing-time-autofill to delegate the whole CLI session close.
    0
    installs
  5. ▌
    Closing Time CLI Facts · cogpros
    Use when the operator delegates the whole CLI session close, including estimated appraisal and seal, in Claude Code, Codex, or Grok Build. Supports explicit session binding and honest agent attribution. Use closing-time for interactive appraisal.
    0
    installs
  6. ▌
    Closing Time Buzz Facts · cogpros bundle
    Use when the operator asks for closing time buzz, a Buzz fact sheet, or a Buzz-wide close. Read the community through a read-only Buzz CLI identity, capture the working-day evidence, appraise Ghost Hours, and save a local report and seal. For a terminal session alone use closing-time-cli-facts.
    0
    installs
  7. ▌
    Mimir · cogpros
    Primed seer. Three-phase protocol: breathe in (assess), breathe out (ask one question), shift (deliver insight). Runs go-deep cold in parallel for comparison.
    0
    installs
  8. ▌
    Prism · cogpros
    Parallel Review by Independent Specialist Models. Multi-agent review protocol that deploys 5+ specialist reviewers in parallel to eliminate confirmation bias and groupthink.
    0
    installs
  9. ▌
    Go Deep · cogpros
    Cold seer. One sharp answer that changes the altitude of the work. Not a list. Not a summary. The single most valuable addition right now.
    0
    installs
  10. ▌
    Crucible · cogpros
    Five-phase adversarial review protocol. PRISM finds issues. RED VIPER proves them. ASSAYER verifies alignment. Evidence decides.
    0
    installs
  11. ▌
    Audit Time · cogpros
    Token optimization audit of bootstrap files. Measure and reduce context weight of CLAUDE.md, MEMORY.md, skills registry, hooks, and plugins.
    0
    installs
  12. ▌
    Whats Next · cogpros
    Day Watch. Mid-session orientation. Checkpoint state, check what's done, check for loose ends. Return ONE next step. One sentence.
    0
    installs
  13. ▌
    System Audit · cogpros
    Full system audit for AI agent setups. Inventories skills, scripts, crons, hooks, agents. Scores health, measures context weight, maps dependencies, checks portability. Outputs a machine-readable manifest.
    0
    installs
  14. ▌
    Whoa Slow Down · cogpros
    Register shift. Explain the current topic like you're talking to a smart high school stoner. Analogies over jargon. Clarity over completeness.
    0
    installs