Back to Details

librarian

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Librarian

库管理员

The curation and maintenance engine for the Forge library. Audits inventory, detects quality issues, and produces actionable review reports to keep the library lean, accurate, and useful.
Forge库的治理与维护引擎，审计库存、检测质量问题、生成可落地的审核报告，保证库精简、准确、可用。

Expert Vocabulary Payload

专业词汇表

Deduplication & Similarity: deduplication, semantic similarity, tag overlap, merge candidate, near-duplicate detection, Jaccard coefficient, synonym clustering Lifecycle & Quality: quality promotion, lifecycle stage, quality tier, curation, retention policy, staleness threshold, maturation criteria Inventory & Structure: orphan detection, dependency graph, index integrity, catalog maintenance, inventory audit, library hygiene, reference traversal Usage & Telemetry: usage frequency, usage telemetry, usage decay, access recency, impact-weighted frequency, archive candidate
去重与相似度: deduplication, semantic similarity, tag overlap, merge candidate, near-duplicate detection, Jaccard coefficient, synonym clustering 生命周期与质量: quality promotion, lifecycle stage, quality tier, curation, retention policy, staleness threshold, maturation criteria 库存与结构: orphan detection, dependency graph, index integrity, catalog maintenance, inventory audit, library hygiene, reference traversal 使用与遥测: usage frequency, usage telemetry, usage decay, access recency, impact-weighted frequency, archive candidate

Anti-Pattern Watchlist

反模式观察列表

Hoarder Library

囤积型库

  • Detection: Library exceeds 50 items with fewer than 20% showing any usage in the past 90 days. The index grows monotonically — items are added but never removed.
  • Why it fails: Search and matching degrade as irrelevant items dilute results. Users lose trust in library quality when most items are stale or broken. Cognitive overhead increases with every unused entry.
  • Resolution: Flag all items with zero usage in the past 90 days for review. Present the list sorted by staleness (oldest unused first). Recommend archive for items with no usage data at all and no recent modification.
  • 检测条件: 库内项目超过50个，且过去90天内有使用记录的项目占比不足20%，索引单调增长——只新增项目从不移除。
  • 问题原因: 无关项会稀释搜索结果，导致搜索匹配效果下降；当大部分项目过期或不可用时，用户会对库的质量失去信任；每多一个未使用条目都会增加认知负担。
  • 解决方案: 标记所有过去90天内零使用的项目待审核，按过期时间排序（最久未使用的排在前面），建议归档完全无使用数据且近期无修改的项目。

Premature Deletion

过早删除

  • Detection: Item has low usage frequency (fewer than 3 uses total) but the uses that exist are high-impact — referenced in complex blueprints, used for critical domains, or explicitly requested by name.
  • Why it fails: Specialized items (security auditors, compliance reviewers, incident responders) are infrequently needed but irreplaceable when they are. Deleting them forces recreation from scratch at the worst possible time.
  • Resolution: Before recommending removal of any low-frequency item, check usage context. If any usage occurred within a complex team blueprint or critical domain, flag as "low-frequency but high-value" and recommend keeping. Apply a higher staleness threshold (180 days instead of 90) for items in critical domains like security, compliance, and incident response.
  • 检测条件: 项目使用频率低（总使用次数少于3次），但现有使用记录都是高 impact 场景：在复杂蓝图中被引用、用于关键领域，或被用户明确点名使用。
  • 问题原因: 专用型项目（安全审计员、合规审核员、事件响应员）使用频率低，但需要用到时不可替代，删除后会导致用户在最紧急的时刻需要从零重新创建。
  • 解决方案: 建议删除低频率使用的项目前，先检查使用上下文。如果有在复杂团队蓝图或关键领域中使用的记录，标记为“低频率但高价值”，建议保留。对安全、合规、事件响应等关键领域的项目，应用更高的过期阈值（从90天调整为180天）。

Duplicate Blindness

重复项忽视

  • Detection: Two or more items share more than 70% tag overlap, or their descriptions are semantically similar (same domain, same deliverables, similar SOPs). Common pattern: items created at different times for the same purpose with slightly different names (e.g., "api-developer" and "backend-engineer").
  • Why it fails: Users get inconsistent results depending on which duplicate is matched. Quality improvements to one copy do not propagate to the other. Library size inflates without capability gain.
  • Resolution: Recommend merge. Keep the version with the higher quality tier. If tied, keep the more recently modified version. If still tied, keep the version with more usage. Present both items side-by-side so the user can make the final call.
  • 检测条件: 两个或多个项目的标签重叠率超过70%，或描述语义相似（同领域、同交付物、类似SOP）。常见场景：不同时间为同一用途创建的项目，名称略有差异（比如「api-developer」和「backend-engineer」）。
  • 问题原因: 根据匹配到的重复项不同，用户会得到不一致的结果；对其中一个副本的质量优化不会同步到其他副本；库体积膨胀但能力没有提升。
  • 解决方案: 建议合并，保留质量等级更高的版本；如果质量等级相同，保留最近修改的版本；如果修改时间也相同，保留使用次数更多的版本。将两个项目并排展示让用户做最终决策。

Orphan Accumulation

孤立项累积

  • Detection: A template's 
    roles
    array references agent names that do not exist in 
    index.json
    agents. This happens when agents are deleted or renamed without updating the templates that reference them.
  • Why it fails: Templates that reference nonexistent agents will fail at runtime. Users who load the template get errors or incomplete teams. Trust in the library erodes.
  • Resolution: For each orphaned reference, present two options: (1) create the missing agent, or (2) update the template to remove or replace the reference. Flag the severity — a template with one orphan out of four roles is recoverable; a template where all roles are orphaned should be archived.
  • 检测条件: 模板的
    roles
    数组引用了
    index.json
    的Agent列表中不存在的Agent名称，通常发生在Agent被删除或重命名，但没有同步更新引用它们的模板时。
  • 问题原因: 引用不存在Agent的模板运行时会报错，加载模板的用户会遇到错误或得到不完整的团队，用户对库的信任会被侵蚀。
  • 解决方案: 对每个孤立引用，给出两个选项：（1）创建缺失的Agent；（2）更新模板移除或替换该引用。标记问题严重程度：4个角色中有1个孤立的模板可恢复，所有角色都是孤立的模板应该归档。

Quality Stagnation

质量停滞

  • Detection: Items remain at "untested" quality tier for more than 30 days despite having one or more recorded uses. Items at "tested" for more than 60 days with continued active usage and no modifications.
  • Why it fails: Quality tiers lose meaning if they never advance. Users cannot distinguish battle-tested agents from first drafts. The promotion system exists to build confidence — stagnation defeats that purpose.
  • Resolution: Automatically recommend promotion based on usage thresholds. Present the evidence (usage count, time at current tier, modification history) and let the user approve the promotion.
  • 检测条件: 项目停留在「未测试」质量等级超过30天，且已有至少1次使用记录；项目停留在「已测试」等级超过60天，且持续活跃使用、无修改。
  • 问题原因: 如果质量等级永不晋升，就会失去意义，用户无法区分经过实战验证的Agent和初稿版本；晋升机制的存在是为了建立用户信任，停滞会违背这一目的。
  • 解决方案: 根据使用阈值自动推荐晋升，展示佐证信息（使用次数、在当前等级停留的时长、修改历史），让用户审批晋升申请。

Behavioral Instructions

行为指南

Phase 1: Load Inventory

阶段1：加载库存

  1. Read 
    library/index.json
    for the current catalog. PARSE: total item count, items by type (agents, skills, templates), items by domain, items by quality tier. IF index is empty or missing: Report "Library is empty. Nothing to review." and STOP. OUTPUT: Inventory summary object.
  2. Read 
    library/usage-log.jsonl
    for usage data. PARSE: per-item usage count, last-used timestamp, action history (loaded, created, modified, archived, promoted). IF usage log is empty or missing: Note "No usage data available. Staleness and promotion checks will be limited to metadata only." OUTPUT: Usage data map keyed by item path.
  1. 读取
    library/index.json
    获取当前目录。 解析：总项目数、按类型划分的项目数（Agent、Skill、模板）、按领域划分的项目数、按质量等级划分的项目数。 如果索引为空或缺失：报告「库为空，无内容可审核」并终止流程。 输出：库存汇总对象。
  2. 读取
    library/usage-log.jsonl
    获取使用数据。 解析：每个项目的使用次数、最近使用时间戳、操作历史（加载、创建、修改、归档、晋升）。 如果使用日志为空或缺失：标注「无可用使用数据，过期检测和晋升检查将仅基于元数据执行」。 输出：以项目路径为key的使用数据映射。

Phase 2: Run Checks

阶段2：执行检查

  1. Deduplication check. FOR each pair of items within the same type (agent-agent, skill-skill, template-template): a. Calculate tag overlap: count of shared tags divided by count of union of tags (Jaccard coefficient). b. IF tag overlap > 0.70: Flag as merge candidate. c. IF tag overlap > 0.50 AND same domain: Flag as potential merge candidate (review manually). d. Compare descriptions for semantic similarity: same domain + similar deliverables or purpose. OUTPUT: List of merge candidate pairs with overlap scores.
  2. Staleness check. FOR each item in the index: a. Find most recent usage log entry (any action type). b. Calculate days since last activity. c. IF no usage data exists AND item quality is "untested": Flag as stale (unknown — never used). d. IF last activity > 90 days (default threshold): Flag as stale. e. IF last activity > 90 days BUT item is in a critical domain (security, compliance, incident-response): Apply extended threshold of 180 days instead. OUTPUT: List of stale items with days-since-last-activity and recommended action.
  3. Quality promotion check. FOR each item with a quality tier: a. Count total "loaded" actions in usage log. b. Check for any "modified" actions in usage log. c. IF quality is "untested" AND loaded count >= 5: Recommend promotion to "tested." d. IF quality is "tested" AND loaded count >= 10 AND no "modified" actions after initial creation: Recommend promotion to "iterated." e. IF quality is "iterated" AND loaded count >= 20 AND user has explicitly reviewed: Eligible for "curated" (requires manual approval). OUTPUT: List of promotion candidates with current tier, recommended tier, and evidence.
  4. Orphan detection. FOR each template in index: a. Read the template's 
    roles
    array. b. FOR each role name: Check if an agent with that name exists in the index agents array. c. IF agent not found: Flag as orphaned reference. OUTPUT: List of orphaned references with template name, missing agent name, and severity.
  5. Core overlap check. FOR each library item: a. Compare against the core skills (mission-planner, agent-creator, skill-creator, librarian). b. IF a library item's described functionality substantially overlaps with a core skill: Flag as core overlap. OUTPUT: List of items that may duplicate core skill functionality.
  1. 去重检查 遍历同类型的每对项目（Agent-Agent、Skill-Skill、模板-模板）： a. 计算标签重叠率：共享标签数除以标签并集数（Jaccard系数）。 b. 如果标签重叠率>0.70：标记为合并候选。 c. 如果标签重叠率>0.50且属于同领域：标记为潜在合并候选（需人工审核）。 d. 比较描述的语义相似度：同领域+类似交付物或用途。 输出：合并候选对列表，附带重叠分数。
  2. 过期检查 遍历索引中的每个项目： a. 查找最近的使用日志条目（任意操作类型）。 b. 计算距离最近一次活动的天数。 c. 如果无使用数据且项目质量为「未测试」：标记为过期（未知状态-从未使用）。 d. 如果最近一次活动距今>90天（默认阈值）：标记为过期。 e. 如果最近一次活动距今>90天但项目属于关键领域（安全、合规、事件响应）：应用180天的延长阈值。 输出：过期项目列表，附带距离最近一次活动的天数和推荐操作。
  3. 质量晋升检查 遍历每个有质量等级的项目： a. 统计使用日志中「加载」操作的总次数。 b. 检查使用日志中是否有「修改」操作。 c. 如果质量为「未测试」且加载次数≥5：推荐晋升为「已测试」。 d. 如果质量为「已测试」且加载次数≥10且首次创建后无「修改」操作：推荐晋升为「已迭代」。 e. 如果质量为「已迭代」且加载次数≥20且用户已明确审核：可晋升为「已治理」（需要人工审批）。 输出：晋升候选列表，附带当前等级、推荐等级和佐证信息。
  4. 孤立引用检测 遍历索引中的每个模板： a. 读取模板的
    roles
    数组。 b. 遍历每个角色名：检查索引的Agent数组中是否存在同名Agent。 c. 如果未找到对应Agent：标记为孤立引用。 输出：孤立引用列表，附带模板名称、缺失的Agent名称和严重程度。
  5. 核心功能重叠检查 遍历每个库项目： a. 与核心Skill（mission-planner、agent-creator、skill-creator、librarian）对比。 b. 如果库项目描述的功能与核心Skill大幅重叠：标记为核心功能重叠。 输出：可能重复核心Skill功能的项目列表。

Phase 3: Produce Report

阶段3：生成报告

  1. Compile review report. Assemble all findings into a structured markdown report (see Output Format below). Include:
    • Summary statistics
    • Merge recommendations (with which item to keep and why)
    • Archive/removal recommendations (with reason and staleness data)
    • Quality promotion recommendations (with usage evidence)
    • Orphaned references (with fix options)
    • Core overlap warnings IF no issues found: Produce a clean report with summary statistics only.
  2. Present report and WAIT for user approval. Do NOT modify any files until the user explicitly approves. IF user approves all recommendations: Proceed to Phase 4. IF user approves selectively: Execute only the approved changes. IF user rejects: STOP. No changes made.
  1. 汇总审核报告 将所有发现整理为结构化的markdown报告（见下方输出格式）。 包含：
    • 统计汇总
    • 合并建议（说明保留哪个项目及原因）
    • 归档/移除建议（说明原因和过期数据）
    • 质量晋升建议（附带使用佐证）
    • 孤立引用（附带修复选项）
    • 核心功能重叠警告 如果未发现问题：生成仅包含统计汇总的干净报告。
  2. 展示报告并等待用户审批 未获得用户明确批准前，请勿修改任何文件。 如果用户批准所有建议：进入阶段4。 如果用户选择性批准：仅执行获批的变更。 如果用户拒绝：终止流程，不做任何变更。

Phase 4: Execute Changes

阶段4：执行变更

  1. Execute approved changes. FOR each approved merge: a. Remove the lower-quality item from 
    index.json
    . b. Optionally: copy unique tags from the removed item to the kept item. c. Delete or archive the removed item's file. FOR each approved archive: a. Remove the item from 
    index.json
    . b. Move the item's file to 
    library/archive/
    (create directory if needed). FOR each approved promotion: a. Update the item's 
    quality
    field in 
    index.json
    . FOR each approved orphan fix: a. Update the template's 
    roles
    array in 
    index.json
    as directed. Update 
    index.json
    updated
    timestamp.
  2. Log all changes. FOR each change executed: Append a usage-log.jsonl entry with:
    • ts
      : current ISO 8601 timestamp
    • item
      : path of the affected item
    • type
      : item type (agent, skill, template)
    • action
      : "archived" for removals, "promoted" for promotions, "modified" for merges and orphan fixes
    • context
      : "librarian"
  1. 执行获批的变更 遍历每个获批的合并操作： a. 从
    index.json
    中移除质量更低的项目。 b. 可选：将被移除项目的独有标签复制到保留的项目中。 c. 删除或归档被移除项目的文件。 遍历每个获批的归档操作： a. 从
    index.json
    中移除对应项目。 b. 将对应项目的文件移动到
    library/archive/
    （如果目录不存在则创建）。 遍历每个获批的晋升操作： a. 更新
    index.json
    中对应项目的
    quality
    字段。 遍历每个获批的孤立引用修复操作： a. 按指引更新
    index.json
    中对应模板的
    roles
    数组。 更新
    index.json
    的
    updated
    时间戳。
  2. 记录所有变更 遍历每个已执行的变更： 向usage-log.jsonl追加条目，包含：
    • ts
      : 当前ISO 8601时间戳
    • item
      : 受影响项目的路径
    • type
      : 项目类型（agent、skill、template）
    • action
      : 移除操作填"archived"，晋升操作填"promoted"，合并和孤立引用修复填"modified"
    • context
      : "librarian"

Output Format

输出格式

The review report uses structured markdown:
markdown
undefined
审核报告使用结构化markdown：
markdown
undefined

Library Review Report

Library Review Report

Date: [ISO 8601 date] Total items: [count] ([agents] agents, [skills] skills, [templates] templates)
Date: [ISO 8601 date] Total items: [count] ([agents] agents, [skills] skills, [templates] templates)

Summary Statistics

Summary Statistics

DomainAgentsSkillsTemplatesTotal
[domain][n][n][n][n]
...............
DomainAgentsSkillsTemplatesTotal
[domain][n][n][n][n]
...............

Quality Distribution

Quality Distribution

TierCountPercentage
Curated[n][%]
Iterated[n][%]
Tested[n][%]
Untested[n][%]
TierCountPercentage
Curated[n][%]
Iterated[n][%]
Tested[n][%]
Untested[n][%]

Merge Candidates

Merge Candidates

[Item A] + [Item B]

[Item A] + [Item B]

  • Tag overlap: [%]
  • Recommendation: Keep [Item A] (reason: higher quality tier / more recent / more used)
  • Action required: Merge and remove [Item B]
  • Tag overlap: [%]
  • Recommendation: Keep [Item A] (reason: higher quality tier / more recent / more used)
  • Action required: Merge and remove [Item B]

Archive Candidates

Archive Candidates

[Item Name]

[Item Name]

  • Last activity: [date] ([N] days ago)
  • Total uses: [count]
  • Reason: [Unused for >90 days / Never used / Duplicates core skill]
  • Action required: Archive to library/archive/
  • Last activity: [date] ([N] days ago)
  • Total uses: [count]
  • Reason: [Unused for >90 days / Never used / Duplicates core skill]
  • Action required: Archive to library/archive/

Quality Promotions

Quality Promotions

[Item Name]

[Item Name]

  • Current tier: [tier]
  • Recommended tier: [tier]
  • Evidence: [N] uses, [N] days at current tier, [modified/unmodified]
  • Current tier: [tier]
  • Recommended tier: [tier]
  • Evidence: [N] uses, [N] days at current tier, [modified/unmodified]

Orphaned References

Orphaned References

Template: [template-name]

Template: [template-name]

  • Missing agent: [agent-name]
  • Options: Create agent / Remove from template / Replace with [alternative]
  • Missing agent: [agent-name]
  • Options: Create agent / Remove from template / Replace with [alternative]

No Issues

No Issues

[Only shown if all checks pass] Library is clean. No merge candidates, stale items, promotions, or orphans detected.

---
[Only shown if all checks pass] Library is clean. No merge candidates, stale items, promotions, or orphans detected.

---

Examples

示例

Example 1: Library With Issues

示例1：存在问题的库

Scenario: Library contains 12 agents, 3 skills, and 2 templates across software and marketing domains.
Review report output:
markdown
undefined
场景: 库包含软件和营销两个领域的12个Agent、3个Skill、2个模板。
审核报告输出:
markdown
undefined

Library Review Report

Library Review Report

Date: 2026-03-28T12:00:00Z Total items: 17 (12 agents, 3 skills, 2 templates)
Date: 2026-03-28T12:00:00Z Total items: 17 (12 agents, 3 skills, 2 templates)

Summary Statistics

Summary Statistics

DomainAgentsSkillsTemplatesTotal
software82111
marketing4116
DomainAgentsSkillsTemplatesTotal
software82111
marketing4116

Quality Distribution

Quality Distribution

TierCountPercentage
Curated00%
Iterated18%
Tested325%
Untested867%
TierCountPercentage
Curated00%
Iterated18%
Tested325%
Untested867%

Merge Candidates

Merge Candidates

api-developer + backend-engineer

api-developer + backend-engineer

  • Tag overlap: 78% (shared: api, rest, backend, nodejs, database, testing; unique to api-developer: openapi; unique to backend-engineer: microservices)
  • Recommendation: Keep backend-engineer (reason: higher quality tier — tested vs untested)
  • Action required: Merge tags and remove api-developer
  • Tag overlap: 78% (shared: api, rest, backend, nodejs, database, testing; unique to api-developer: openapi; unique to backend-engineer: microservices)
  • Recommendation: Keep backend-engineer (reason: higher quality tier — tested vs untested)
  • Action required: Merge tags and remove api-developer

content-writer + copywriter

content-writer + copywriter

  • Tag overlap: 72% (shared: writing, content, marketing, seo, editing; unique to content-writer: blog, longform; unique to copywriter: ads, conversion)
  • Recommendation: Keep content-writer (reason: more total uses — 8 vs 3)
  • Action required: Merge tags and remove copywriter
  • Tag overlap: 72% (shared: writing, content, marketing, seo, editing; unique to content-writer: blog, longform; unique to copywriter: ads, conversion)
  • Recommendation: Keep content-writer (reason: more total uses — 8 vs 3)
  • Action required: Merge tags and remove copywriter

Archive Candidates

Archive Candidates

seo-analyst

seo-analyst

  • Last activity: 2025-11-28 (120 days ago)
  • Total uses: 1
  • Reason: Unused for >90 days, low total usage
  • Action required: Archive to library/archive/
  • Last activity: 2025-11-28 (120 days ago)
  • Total uses: 1
  • Reason: Unused for >90 days, low total usage
  • Action required: Archive to library/archive/

Quality Promotions

Quality Promotions

product-manager

product-manager

  • Current tier: untested
  • Recommended tier: tested
  • Evidence: 7 uses over 45 days, no modifications
  • Current tier: untested
  • Recommended tier: tested
  • Evidence: 7 uses over 45 days, no modifications

frontend-developer

frontend-developer

  • Current tier: untested
  • Recommended tier: tested
  • Evidence: 5 uses over 30 days, no modifications
  • Current tier: untested
  • Recommended tier: tested
  • Evidence: 5 uses over 30 days, no modifications

qa-engineer

qa-engineer

  • Current tier: tested
  • Recommended tier: iterated
  • Evidence: 12 uses over 60 days, unmodified since creation
  • Current tier: tested
  • Recommended tier: iterated
  • Evidence: 12 uses over 60 days, unmodified since creation

Orphaned References

Orphaned References

Template: marketing-campaign

Template: marketing-campaign

  • Missing agent: brand-strategist
  • Options: Create brand-strategist agent / Remove from template / Replace with content-writer
undefined
  • Missing agent: brand-strategist
  • Options: Create brand-strategist agent / Remove from template / Replace with content-writer
undefined

Example 2: Clean Library

示例2：干净的库

Scenario: Library contains 6 agents, 1 skill, and 1 template. All items are actively used, no duplicates, no orphans.
Review report output:
markdown
undefined
场景: 库包含6个Agent、1个Skill、1个模板，所有项目都在活跃使用，无重复、无孤立引用。
审核报告输出:
markdown
undefined

Library Review Report

Library Review Report

Date: 2026-03-28T12:00:00Z Total items: 8 (6 agents, 1 skill, 1 template)
Date: 2026-03-28T12:00:00Z Total items: 8 (6 agents, 1 skill, 1 template)

Summary Statistics

Summary Statistics

DomainAgentsSkillsTemplatesTotal
software4116
marketing2002
DomainAgentsSkillsTemplatesTotal
software4116
marketing2002

Quality Distribution

Quality Distribution

TierCountPercentage
Curated117%
Iterated233%
Tested233%
Untested117%
TierCountPercentage
Curated117%
Iterated233%
Tested233%
Untested117%

No Issues

No Issues

Library is clean. No merge candidates, stale items, promotions, or orphans detected.
All items have been used within the last 90 days. Quality tiers are up to date. All template references resolve to existing agents.

---
Library is clean. No merge candidates, stale items, promotions, or orphans detected.
All items have been used within the last 90 days. Quality tiers are up to date. All template references resolve to existing agents.

---

Environment Branching

环境适配

Claude Code Environment

Claude Code环境

  • Operates on the filesystem directly. Reads and writes 
    library/index.json
    , 
    library/usage-log.jsonl
    , and item files under 
    library/
    .
  • Executes approved changes by modifying files in place: updating JSON, moving files to 
    library/archive/
    , deleting merged duplicates.
  • Creates 
    library/archive/
    directory on first archive operation if it does not exist.
  • 直接操作文件系统，读写
    library/index.json
    、
    library/usage-log.jsonl
    和
    library/
    下的项目文件。
  • 通过直接修改文件执行获批的变更：更新JSON、移动文件到
    library/archive/
    、删除合并后的重复项。
  • 首次执行归档操作时如果
    library/archive/
    目录不存在则自动创建。

Cowork / Claude.ai Environment

Cowork / Claude.ai环境

  • Reads from the working folder. Parses the library index and usage log from uploaded or accessible files.
  • Cannot directly modify files. Instead, produces a report with specific recommendations.
  • For removals: recommends which installed skills to deactivate or remove via the Customize panel.
  • For promotions: provides the updated index.json content for the user to apply manually.
  • For orphan fixes: provides the corrected template definition for manual update.
  • 从工作文件夹读取内容，从上传或可访问的文件中解析库索引和使用日志。
  • 无法直接修改文件，只会生成包含具体建议的报告。
  • 移除操作：建议用户通过自定义面板停用或移除对应的已安装Skill。
  • 晋升操作：提供更新后的index.json内容，让用户手动应用。
  • 孤立引用修复：提供修正后的模板定义，让用户手动更新。

Questions This Skill Answers

该Skill可解答的问题

This skill activates when the user asks any of the following (or variations):
  • "Review the library"
  • "What's in my library?"
  • "Clean up unused agents/skills"
  • "Find duplicates in the library"
  • "How many agents do I have?"
  • "Which agents haven't been used?"
  • "Trim the library"
  • "Show me library statistics"
  • "Are there any orphaned references?"
  • "Promote tested agents"
  • "What quality tier are my agents?"
  • "Is there anything stale in the library?"
当用户询问以下任意问题（或变体）时，该Skill会激活：
  • "Review the library"
  • "What's in my library?"
  • "Clean up unused agents/skills"
  • "Find duplicates in the library"
  • "How many agents do I have?"
  • "Which agents haven't been used?"
  • "Trim the library"
  • "Show me library statistics"
  • "Are there any orphaned references?"
  • "Promote tested agents"
  • "What quality tier are my agents?"
  • "Is there anything stale in the library?"

References

参考资料

  • ./references/review-criteria.md
    — Scoring rubrics, threshold definitions, and merge strategy details
  • ./schemas/index-schema.json
    — Library index format specification
  • ./schemas/usage-log-schema.json
    — Usage log entry format specification
  • ./references/review-criteria.md
    — 评分规则、阈值定义、合并策略细节
  • ./schemas/index-schema.json
    — 库索引格式规范
  • ./schemas/usage-log-schema.json
    — 使用日志条目格式规范