Claude Skill

using-practice

Use for durable questions, banks, papers, attempts, grading, flashcards, or scheduled review. Skip disposable one-off questions.

LLM Mart · 0 points · 10 views 0 listing impressions 0 install-command copies
Virus-scanned Reviewed automatically before listing.

Full trust report

Download JanYork-llm-wiki-cli-skills_using-practice-83cf9a7.zip · 1 KB
Part of janyork/llm-wiki-cli — 28 skills

Install

skills CLI npx skills add https://github.com/JanYork/llm-wiki-cli/tree/main/skills/using-practice
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install janyork-llm-wiki-cli@llmmart
Git git clone https://github.com/JanYork/llm-wiki-cli.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole janyork/llm-wiki-cli collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Using Practice

Practice preserves assessed work across context loss. Flashcards are Practice items. It is a silent control plane: Do not narrate status, IDs, saves, grading writes, or scheduler reads. Show only questions, answers, feedback, and meaningful progress.

Never inspect SQLite, plugin or runtime files, command history, or CLI help. Never reread Skill files or text-search for state. Use only the public commands here.

Enter or recover

Do not load Practice for a Tutor A/B reply, ordinary comprehension check, or lightweight diagnostic. Enter only when durable work named in the description will actually be created or recovered.

  1. Inspect LWC_READINESS.practice. If disabled, explain the durable local-data boundary and ask once before lwc --scope global config set --practice enabled; explicit enablement is consent. Enabling does not download; first status may lazily install the pinned, hash-verified runtime.
  2. Run lwc practice status once on entry, lost identity, compaction, or a pending/revision/owner error. Otherwise cache exact attempt/session/owner/latest revision; do not repeat status.
  3. Recover an in-progress attempt and saved responses before creating another. Use a new stable request_id per operation; retry that operation with the same request ID, owner, and if_revision.
  4. Cross-machine recovery requires the latest successful Sync receipt and exact-revision takeover; the old owner must stop writing.

Durable flow

  1. Resolve exact typed subject, goal, book, bank, set, paper, and item IDs. Precedence is explicit plan target, goal bank, then subject default. Invalid higher-precedence targets fail; never fuzzy-match.
  2. Generated items stay draft until prompt, answer, rubric, and exact source ref are re-read and verified. Formal papers use verified revisions and report shortages without weakening the blueprint.
  3. Start or resume the exact attempt. Save every response immediately with owner, request ID, and if_revision; submission freezes already durable responses. Abandonment preserves history. v1 accepts only choice, text, numeric, and flashcard self-rating; reject every other form.
  4. Grade objective items deterministically. Grade subjective items against the frozen rubric and store concise rationale, confidence, method, and review state. Learner overrides append history.
  5. Let the pinned scheduler compute review state and due dates. Respect time budget and retention target, expose deferred debt, and never edit due dates or silently control review.

Keep exact committed IDs and the failed next command when independent stores partially succeed; never claim they are one transaction. Never copy Practice records into the ordinary LWC Wiki or store hidden reasoning, prompts, logs, credentials, or secrets.

Files (llm-wiki-cli)
  • agents
    • openai.yaml 214 B
      interface:
        display_name: "LWC Practice"
        short_description: "Durable practice and scheduled review"
        default_prompt: "Use $using-practice for durable items, attempts, grading, flashcards, and review recovery."
      
  • SKILL.md 3 KB
    ---
    name: using-practice
    description: Use when creating or recovering a durable paper, attempt, grade, flashcard, scheduled review, mistake history, or goal-evidence record. Skip Tutor comprehension checks, lightweight diagnostics, and disposable questions.
    ---
    
    # Using Practice
    
    Practice preserves assessed work across context loss. Flashcards are Practice items.
    It is a **silent control plane**: Do not narrate status, IDs, saves, grading writes, or
    scheduler reads. Show only questions, answers, feedback, and meaningful progress.
    
    Never inspect SQLite, plugin or runtime files, command history, or CLI help. Never
    reread Skill files or text-search for state. Use only the public commands here.
    
    ## Enter or recover
    
    Do not load Practice for a Tutor A/B reply, ordinary comprehension check, or lightweight
    diagnostic. Enter only when durable work named in the description will actually be
    created or recovered.
    
    1. Inspect `LWC_READINESS.practice`. If disabled, explain the durable local-data
       boundary and ask once before
       `lwc --scope global config set --practice enabled`; explicit enablement is consent.
       Enabling does not download; first status may lazily install the pinned,
       hash-verified runtime.
    2. Run `lwc practice status` once on entry, lost identity, compaction, or a
       pending/revision/owner error. Otherwise cache exact attempt/session/owner/latest
       revision; do not repeat status.
    3. Recover an in-progress attempt and saved responses before creating another. Use a
       new stable `request_id` per operation; retry that operation with the same request ID,
       owner, and `if_revision`.
    4. Cross-machine recovery requires the latest successful Sync receipt and exact-revision
       takeover; the old owner must stop writing.
    
    ## Durable flow
    
    1. Resolve exact typed subject, goal, book, bank, set, paper, and item IDs. Precedence is
       explicit plan target, goal bank, then subject default. Invalid higher-precedence
       targets fail; never fuzzy-match.
    2. Generated items stay draft until prompt, answer, rubric, and exact source ref are
       re-read and verified. Formal papers use verified revisions and report shortages
       without weakening the blueprint.
    3. Start or resume the exact attempt. Save every response immediately with owner,
       request ID, and `if_revision`; submission freezes already durable responses.
       Abandonment preserves history. v1 accepts only choice, text, numeric, and flashcard
       self-rating; reject every other form.
    4. Grade objective items deterministically. Grade subjective items against the frozen
       rubric and store concise rationale, confidence, method, and review state. Learner
       overrides append history.
    5. Let the pinned scheduler compute review state and due dates. Respect time budget and
       retention target, expose deferred debt, and never edit due dates or silently control
       review.
    
    Keep exact committed IDs and the failed next command when independent stores partially
    succeed; never claim they are one transaction. Never copy Practice records into the
    ordinary LWC Wiki or store hidden reasoning, prompts, logs, credentials, or secrets.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related