Detective
QinghongLin/data2story-skill
Research external context for a dataset — domain background, history, related studies, and why this data matters.
根据模糊的时间、地点、同行人、画面和文字线索找回可能的照片事件，并在用户确认后生成可追溯的回忆故事. An agent skill from LC044/TrailSnap.
AGPL-3.0Auto-check passed
Install Memory Detective
$ npx skills add LC044/TrailSnap --skill memory-detective -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LC044/TrailSnap memory-detective --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LC044/TrailSnap.git skills-src && mkdir -p .claude/skills && cp -r skills-src/package/server/app/service/agent/skills/memory-detective .claude/skills/memory-detective && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "memory-detective" agent skill from https://github.com/LC044/TrailSnap/tree/master/package/server/app/service/agent/skills/memory-detective into .claude/skills/memory-detective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-detective", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LC044/TrailSnap/tree/master/package/server/app/service/agent/skills/memory-detectiveType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LC044/TrailSnap --skill memory-detective -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LC044/TrailSnap memory-detective --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LC044/TrailSnap.git skills-src && mkdir -p .agents/skills && cp -r skills-src/package/server/app/service/agent/skills/memory-detective .agents/skills/memory-detective && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "memory-detective" agent skill from https://github.com/LC044/TrailSnap/tree/master/package/server/app/service/agent/skills/memory-detective into .agents/skills/memory-detective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-detective", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LC044/TrailSnap --skill memory-detective -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LC044/TrailSnap memory-detective --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LC044/TrailSnap.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/package/server/app/service/agent/skills/memory-detective .cursor/skills/memory-detective && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "memory-detective" agent skill from https://github.com/LC044/TrailSnap/tree/master/package/server/app/service/agent/skills/memory-detective into .cursor/skills/memory-detective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-detective", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LC044/TrailSnap.git --path package/server/app/service/agent/skills/memory-detective--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LC044/TrailSnap --skill memory-detective -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LC044/TrailSnap memory-detective --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LC044/TrailSnap.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/package/server/app/service/agent/skills/memory-detective .gemini/skills/memory-detective && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "memory-detective" agent skill from https://github.com/LC044/TrailSnap/tree/master/package/server/app/service/agent/skills/memory-detective into .gemini/skills/memory-detective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-detective", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LC044/TrailSnap memory-detectiveInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LC044/TrailSnap --skill memory-detective -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LC044/TrailSnap.git skills-src && mkdir -p .github/skills && cp -r skills-src/package/server/app/service/agent/skills/memory-detective .github/skills/memory-detective && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "memory-detective" agent skill from https://github.com/LC044/TrailSnap/tree/master/package/server/app/service/agent/skills/memory-detective into .github/skills/memory-detective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-detective", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LC044/TrailSnap --skill memory-detective -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LC044/TrailSnap memory-detective --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LC044/TrailSnap.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/package/server/app/service/agent/skills/memory-detective .opencode/skills/memory-detective && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "memory-detective" agent skill from https://github.com/LC044/TrailSnap/tree/master/package/server/app/service/agent/skills/memory-detective into .opencode/skills/memory-detective/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-detective", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
memory-detective- GitHub stars
- 767
- Token cost
- ~233 tokens
- SKILL.md length
- 48 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
根据模糊的时间、地点、同行人、画面和文字线索找回可能的照片事件，并在用户确认后生成可追溯的回忆故事. An agent skill from LC044/TrailSnap.
- Works in 8 steps: 先把用户叙述拆成可验证线索：大概时间、地点、同行人、物体或场景、照片中文字、交通票… → 先调用 search_photos_v2(description=...)… → 调用… → …
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Memory Detective is an agent skill from LC044/TrailSnap. 根据模糊的时间、地点、同行人、画面和文字线索找回可能的照片事件，并在用户确认后生成可追溯的回忆故事。
Its SKILL.md is about 230 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: TrailSnap (行影集) | AI-Powered open-source photo album for travel & life memories.（AI赋能的开源相册工具，珍藏旅行与生活点滴）. The licence is AGPL-3.0.
Example prompts
- “/memory-detective”
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- 先把用户叙述拆成可验证线索：大概时间、地点、同行人、物体或场景、照片中文字、交通票据。信息不足时一次只问一个最有区分度的问题，不要求用户填写表单。
- 先调用 search_photos_v2(description=...) 做语义召回，取最多 12 个具体 photo_id。如果用户记得招牌、菜单、车站或其他文字，再调用 search_ocr；不要把语义相似当作事实。
- 调用 investigate_memory：日期用于限制范围；地点、人物、文字关键词和语义 photo_id 会做并集召回与证据加权。关键词应拆成 1～4 个短词，不要把整段自然语言当作单个关键词。
- 最多展示 3 个候选事件。说明每个候选的日期、地点、人物、命中线索、置信度和代表照片，并使用 view_photos 或 create_contact_sheet 让用户视觉确认。展示照片时必须原样使用工具返回的 thumbnail_url，不要自行拼接媒体地址或加入用户 ID。
- 对最可能事件调用 get_photo_context 检查最多 30 张证据照片。只能陈述工具确认的信息；“可能”“推测”“用户已确认”必须明确区分。
- 用户否认候选时，保留原线索并只调整一个条件继续查找，例如放宽年份或移除地点，避免无解释地重复同一搜索。
- 用户确认事件后，可用 select_representative_photos 选图，并调用 create_artifact_draft(artifact_type="memory_story") 生成带来源照片的回忆故事草稿；需要个性页面时再用…
- 整个侦查过程只读，不得修改、移动、删除照片或自动创建相册。结尾列出已确认事实、仍属推测的内容和证据照片 ID。
What it can do on your machine
Read from SKILL.md and the folder at commit c7503d1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Memory Detective loads about 233 tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 48 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from LC044/TrailSnap at commit c7503d1, republished under its AGPL-3.0 licence (© LC044). 48 words, ~233 tokens.
Download SKILL.mdSave it as
.claude/skills/memory-detective/SKILL.md (or your agent's skills folder).- name
- memory-detective
- description
- 根据模糊的时间、地点、同行人、画面和文字线索找回可能的照片事件，并在用户确认后生成可追溯的回忆故事。
回忆侦探
- 先把用户叙述拆成可验证线索：大概时间、地点、同行人、物体或场景、照片中文字、交通票据。信息不足时一次只问一个最有区分度的问题，不要求用户填写表单。
- 先调用
search_photos_v2(description=...)做语义召回，取最多 12 个具体photo_id。如果用户记得招牌、菜单、车站或其他文字，再调用search_ocr；不要把语义相似当作事实。 - 调用
investigate_memory：日期用于限制范围；地点、人物、文字关键词和语义photo_id会做并集召回与证据加权。关键词应拆成 1～4 个短词，不要把整段自然语言当作单个关键词。 - 最多展示 3 个候选事件。说明每个候选的日期、地点、人物、命中线索、置信度和代表照片，并使用
view_photos或create_contact_sheet让用户视觉确认。展示照片时必须原样使用工具返回的thumbnail_url，不要自行拼接媒体地址或加入用户 ID。 - 对最可能事件调用
get_photo_context检查最多 30 张证据照片。只能陈述工具确认的信息；“可能”“推测”“用户已确认”必须明确区分。 - 用户否认候选时，保留原线索并只调整一个条件继续查找，例如放宽年份或移除地点，避免无解释地重复同一搜索。
- 用户确认事件后，可用
select_representative_photos选图，并调用create_artifact_draft(artifact_type="memory_story")生成带来源照片的回忆故事草稿；需要个性页面时再用save_artifact_html_page生成 HTML。没有确认前不要创建作品。 - 整个侦查过程只读，不得修改、移动、删除照片或自动创建相册。结尾列出已确认事实、仍属推测的内容和证据照片 ID。
© LC044, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in package/server/app/service/agent/skills/memory-detective of LC044/TrailSnap.
Open the folder on GitHubat commit c7503d1
Compare with similar skills
Memory Detective next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Memory Detective this skillLC044/TrailSnap | 767 | — | ~233 | Automated safety check: Pass | AGPL-3.0 | |
| DetectiveQinghongLin/data2story-skill | 156 | — | ~2.4k | Automated safety check: Notes | MIT | |
| Threat Detectionalirezarezvani/claude-skills | 28k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Resemble Detectgithub/awesome-copilot | 40k | 3 repos | ~4.1k | Automated safety check: Pass | Apache-2.0 | |
| Pii Detectruvnet/ruflo | 74k | 1 repos | ~350 | Automated safety check: Notes | MIT | |
| Detecting Dnp3 Protocol Anomaliesmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~3.6k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Threat Detection
alirezarezvani/claude-skills
A skill your agent uses when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry.
- Official
Resemble Detect
github/awesome-copilot
Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using…
Pii Detect
ruvnet/ruflo
Detect and flag personally identifiable information (PII) in text, code, and configurations.
Detecting Dnp3 Protocol Anomalies
mukul975/Anthropic-Cybersecurity-Skills
Detect anomalies in DNP3 communications used in SCADA/ICS systems by monitoring unauthorized control commands, firmware update attempts, protocol violations, and deviations from baseline traffic…
Detecting Attacks On Scada Systems
mukul975/Anthropic-Cybersecurity-Skills
This skill covers detecting cyber attacks targeting Supervisory Control and Data Acquisition (SCADA) systems including man-in-the-middle attacks on industrial protocols, unauthorized command…
More from LC044/TrailSnap
All 10 skills in this repoTrailsnap CLI
LC044/TrailSnap
Query photos, albums, locations, tags, and people from a TrailSnap instance through its command-line client.
Release Publisher
LC044/TrailSnap
发布并验收 TrailSnap 新版本：汇总提交、同步全项目版本号、更新官网日志与客户端更新清单、执行发布前测试、创建 GitHub Release、监控标签 CI、核验 Release 附件，并生成小红书和公众号文案。Use when the user asks to 发布新版本、发版、创建或检查 GitHub Release、总结版本变更、监控发布 CI、检查发布产物，或撰写版本更新帖子。
Trailsnap Commit
LC044/TrailSnap
TrailSnap 仓库提交、推送、需求平台与 PR 工作流规则。Use when preparing commits, pushing branches, managing the corresponding platform requirement, creating or merging pull requests, or monitoring PR CI in this…
Trailsnap Agent
LC044/TrailSnap
Query a user's TrailSnap photo library through scoped MCP tools to find photos, reconstruct memories, build person timelines, create evidence-backed narratives, or propose an album plan for explicit…
Album Doctor
LC044/TrailSnap
对照片库或指定相册进行体检，并把结构、时间、地点、AI 元数据与安全清理问题转成可选择、可确认、尽量可撤销的计划. An agent skill from LC044/TrailSnap.
Person Timeline
LC044/TrailSnap
按年份和事件整理指定人物出现过的照片，展示共同经历、成长变化、地点与同行人，并可生成可追溯的人物故事. An agent skill from LC044/TrailSnap.
Questions about Memory Detective
What does Memory Detective do?
根据模糊的时间、地点、同行人、画面和文字线索找回可能的照片事件，并在用户确认后生成可追溯的回忆故事. An agent skill from LC044/TrailSnap. Memory Detective is an agent skill from LC044/TrailSnap.
How do I install Memory Detective in Claude Code?
Run `npx skills add LC044/TrailSnap --skill memory-detective -a claude-code`. Or copy the skill folder (package/server/app/service/agent/skills/memory-detective in LC044/TrailSnap) into .claude/skills/memory-detective in your project. Claude Code loads it when a task matches its description.
How do I install Memory Detective in Codex?
Run `npx skills add LC044/TrailSnap --skill memory-detective -a codex`. Or copy the skill folder (package/server/app/service/agent/skills/memory-detective in LC044/TrailSnap) into .agents/skills/memory-detective in your project. Codex loads it when a task matches its description.
Can I use Memory Detective in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LC044/TrailSnap --skill memory-detective -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-detective, .gemini/skills/memory-detective, .github/skills/memory-detective and .opencode/skills/memory-detective in your project.
What does Memory Detective need to run?
SKILL.md names no scripts, command-line tools or credentials: Memory Detective is instructions for the agent only.
Does Memory Detective access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Memory Detective safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Memory Detective use?
Memory Detective is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Memory Detective use?
About 233 tokens (SKILL.md is roughly 932 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Memory Detective?
Skills that share tags, products or a category with Memory Detective: Detective (QinghongLin/data2story-skill, 156 stars), Threat Detection (alirezarezvani/claude-skills, 28k stars), Resemble Detect (github/awesome-copilot, 40k stars) and Pii Detect (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Memory Detective?
LC044 (a GitHub user) maintains it in LC044/TrailSnap, which has 767 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 6, 2026.
Source: LC044/TrailSnap on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.