Skip to content

aiskillstore/marketplace / skills/0xrdan/learn-reset

learn-reset

Verified

Clear the knowledge base and start fresh

FileKindSize
SKILL.mdskill md2.2 KB
skill-report.jsonconfig19.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T14:09:28.292Z",
    "slug": "0xrdan-learn-reset",
    "source_url": "https://github.com/0xrdan/claude-router/tree/main/.claude-plugin/skills/learn-reset",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "b6da2ac5ffa5a098901f58f5fd5c504e452b615de1c121c7ca399b879b4533a1",
    "tree_hash": "17e7386932ab3ae2bc5246e52588d07605866f6b726c1fefbe6686ba00898387",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "learn-reset",
    "description": "Reset a learning knowledge base to a clean state after explicit user confirmation.",
    "summary": "Clears learned patterns, cache data, session notes, and learning state while preserving the knowledge directory structure.",
    "icon": "📦",
    "version": "1.0.1",
    "author": "0xrdan",
    "license": "MIT",
    "category": "productivity",
    "tags": [
      "knowledge-base",
      "reset",
      "learning",
      "cleanup",
      "workflow"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ]
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All 13 static external-command findings are false positives caused by markdown inline backticks and fenced example blocks, not executable code. I found one semantic concern: the skill clears knowledge files and resets state. Accidental use can cause data loss despite confirmation.",
    "remediation": [
      {
        "issue": "Destructive reset can remove accumulated knowledge.",
        "suggestion": "Require explicit user confirmation, show target files and counts, and recommend a backup or commit before reset.",
        "severity": "medium"
      },
      {
        "issue": "Reset scope depends on the assistant following the documented paths.",
        "suggestion": "Keep reset operations limited to the documented knowledge files and report every changed file after completion.",
        "severity": "low"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          },
          {
            "file": "SKILL.md",
            "line_start": 24,
            "line_end": 24
          },
          {
            "file": "SKILL.md",
            "line_start": 25,
            "line_end": 25
          },
          {
            "file": "SKILL.md",
            "line_start": 26,
            "line_end": 26
          },
          {
            "file": "SKILL.md",
            "line_start": 27,
            "line_end": 27
          },
          {
            "file": "SKILL.md",
            "line_start": 28,
            "line_end": 28
          },
          {
            "file": "SKILL.md",
            "line_start": 29,
            "line_end": 29
          },
          {
            "file": "SKILL.md",
            "line_start": 35,
            "line_end": 53
          },
          {
            "file": "SKILL.md",
            "line_start": 53,
            "line_end": 57
          },
          {
            "file": "SKILL.md",
            "line_start": 57,
            "line_end": 58
          },
          {
            "file": "SKILL.md",
            "line_start": 58,
            "line_end": 69
          },
          {
            "file": "SKILL.md",
            "line_start": 69,
            "line_end": 73
          },
          {
            "file": "SKILL.md",
            "line_start": 73,
            "line_end": 88
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 13,
        "line_end": 13,
        "snippet": "- Clears all entries from `knowledge/learnings/` files (patterns, quirks, decisions)"
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 24,
        "line_end": 24,
        "snippet": "- `knowledge/learnings/patterns.md`"
      },
      {
        "id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 25,
        "line_end": 25,
        "snippet": "- `knowledge/learnings/quirks.md`"
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 26,
        "line_end": 26,
        "snippet": "- `knowledge/learnings/decisions.md`"
      },
      {
        "id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 27,
        "line_end": 27,
        "snippet": "3. **Reset cache** - Clear `knowledge/cache/classifications.md`"
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 28,
        "line_end": 28,
        "snippet": "4. **Reset session** - Clear `knowledge/context/session.md`"
      },
      {
        "id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 29,
        "line_end": 29,
        "snippet": "5. **Reset state** - Reset `knowledge/state.json` to initial values"
      },
      {
        "id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 35,
        "line_end": 53,
        "snippet": "```yaml"
      },
      {
        "id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 53,
        "line_end": 57,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 57,
        "line_end": 58,
        "snippet": "Reset `knowledge/state.json` to:"
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 58,
        "line_end": 69,
        "snippet": "```json"
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 69,
        "line_end": 73,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 73,
        "line_end": 88,
        "snippet": "```"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 13 uses inline markdown backticks around a directory path. It does not contain Ruby backtick execution or any shell command."
      },
      {
        "id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 24 is a markdown bullet naming knowledge/learnings/patterns.md. The backticks are formatting around a file path, not executable syntax."
      },
      {
        "id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 25 is a markdown bullet naming knowledge/learnings/quirks.md. No command or dynamic execution context is present."
      },
      {
        "id": "external_commands:SKILL.md:26:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 26 is a markdown bullet naming knowledge/learnings/decisions.md. The backticks only mark inline code formatting."
      },
      {
        "id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 27 references a cache file path in markdown prose. It instructs clearing content but does not execute a shell command."
      },
      {
        "id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 28 references a session file path in markdown prose. The backticks are documentation formatting rather than code execution."
      },
      {
        "id": "external_commands:SKILL.md:29:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 29 names knowledge/state.json as a reset target. It is not Ruby or shell backtick execution."
      },
      {
        "id": "external_commands:SKILL.md:35:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 35 starts a fenced YAML example block. This is static documentation for the reset file format, not executable shell content."
      },
      {
        "id": "external_commands:SKILL.md:53:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 53 closes a markdown code fence. A closing fence is not a command execution primitive."
      },
      {
        "id": "external_commands:SKILL.md:57:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 57 references knowledge/state.json with inline markdown formatting. It does not execute or construct a command."
      },
      {
        "id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 58 starts a fenced JSON example block. The content is a target state example, not executable code."
      },
      {
        "id": "external_commands:SKILL.md:69:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 69 closes a markdown code fence. It has no shell execution behavior."
      },
      {
        "id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 73 starts a plain output-format example block. It documents user-facing output and does not contain an executable command."
      }
    ],
    "semantic_findings": [
      {
        "title": "Destructive Knowledge Reset",
        "description": "The skill is designed to clear accumulated knowledge files and reset state. It asks for confirmation, but successful use can permanently remove local assistant learning data.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 29
          },
          {
            "file": "SKILL.md",
            "line_start": 92,
            "line_end": 95
          }
        ],
        "confidence": 0.9,
        "confidence_reasoning": "The destructive behavior is explicitly documented in the warning and reset instructions. Confirmation reduces accidental use but does not remove data-loss impact."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Destructive Knowledge Reset",
        "description": "The skill is designed to clear accumulated knowledge files and reset state. It asks for confirmation, but successful use can permanently remove local assistant learning data.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 29
          },
          {
            "file": "SKILL.md",
            "line_start": 92,
            "line_end": 95
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.9,
        "confidence_reasoning": "The destructive behavior is explicitly documented in the warning and reset instructions. Confirmation reduces accidental use but does not remove data-loss impact."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 96,
    "audit_model": "codex",
    "audited_at": "2026-07-04T14:09:28.292Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Reset Learning Knowledge Safely",
    "value_statement": "Accumulated learning files can become stale or noisy over time. This skill guides Claude, Codex, and Claude Code through a confirmed reset that preserves the file structure.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "learn reset",
      "knowledge base reset",
      "AI learning cleanup",
      "assistant memory reset",
      "classification cache",
      "learning state",
      "productivity skill"
    ],
    "actual_capabilities": [
      "Prompts the assistant to request confirmation before resetting knowledge files.",
      "Clears learned patterns, quirks, and decisions while keeping the file structure.",
      "Clears the classification cache and current session context.",
      "Resets learning state values such as extraction count and query counters.",
      "Provides a completion summary with counts of cleared entries."
    ],
    "limitations": [
      "It cannot recover cleared entries after confirmation.",
      "It does not remove old knowledge from git history.",
      "It only describes the reset workflow; the assistant performs file edits.",
      "It assumes the expected knowledge directory and files already exist."
    ],
    "use_cases": [
      {
        "title": "Start A Clean Learning Cycle",
        "description": "Reset noisy learning data before collecting new patterns for a project.",
        "target_user": "Developer using assistant learning files"
      },
      {
        "title": "Remove Stale Project Notes",
        "description": "Clear old decisions and quirks after a major refactor or architecture change.",
        "target_user": "Project maintainer"
      },
      {
        "title": "Prepare A Shared Workspace",
        "description": "Empty personal learning state before handing a workspace to another contributor.",
        "target_user": "Team lead"
      }
    ],
    "prompt_templates": [
      {
        "title": "Basic Reset",
        "prompt": "Use learn-reset to clear the learning knowledge base. Ask me to confirm before changing files.",
        "scenario": "Beginner reset request"
      },
      {
        "title": "Reset With Counts",
        "prompt": "Use learn-reset and report how many patterns, quirks, decisions, and cache entries were cleared.",
        "scenario": "Routine cleanup"
      },
      {
        "title": "Reset Before New Phase",
        "prompt": "Use learn-reset after confirmation, then leave the knowledge structure ready for a new project phase.",
        "scenario": "Project transition"
      },
      {
        "title": "Audited Reset Workflow",
        "prompt": "Use learn-reset with a careful review. Show the files you will clear, wait for confirmation, reset them, and summarize the final state.",
        "scenario": "Advanced controlled reset"
      }
    ],
    "output_examples": [
      {
        "input": "Reset my learning knowledge base.",
        "output": "The assistant asks for confirmation, clears learning entries after approval, resets state, and reports the number of cleared items."
      },
      {
        "input": "Clear stale learning notes before the next sprint.",
        "output": [
          "The assistant lists the reset targets for review.",
          "After confirmation, it clears patterns, quirks, decisions, cache, and session context.",
          "It finishes with a short reset summary."
        ]
      },
      {
        "input": "Start fresh but keep the knowledge folders.",
        "output": "The assistant preserves the knowledge directory structure and replaces learned content with empty baseline files."
      }
    ],
    "best_practices": [
      "Review the learning files before confirming a reset.",
      "Keep project backups or git commits before clearing knowledge.",
      "Run the reset when starting a new phase or after noisy learning has accumulated."
    ],
    "anti_patterns": [
      "Do not use this skill when you need to preserve historical insights.",
      "Do not reset without explicit confirmation from the workspace owner.",
      "Do not assume it removes old content from repository history."
    ],
    "faq": [
      {
        "question": "Does this skill delete the knowledge directory?",
        "answer": "No. It preserves the directory structure and clears selected learning content."
      },
      {
        "question": "Will it ask before changing files?",
        "answer": "Yes. The skill instructs the assistant to request confirmation before resetting knowledge."
      },
      {
        "question": "Can cleared knowledge be restored?",
        "answer": "Only if you have a backup, commit, or other saved copy."
      },
      {
        "question": "Does it clear git history?",
        "answer": "No. Previous commits may still contain old knowledge."
      },
      {
        "question": "Which tools can use this skill?",
        "answer": "The report lists support for Claude, Codex, and Claude Code."
      },
      {
        "question": "When should I use it?",
        "answer": "Use it when accumulated learning data is stale, noisy, or no longer useful."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 96
    }
  ]
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall