survey
Skill2 starsChanged 27 days agoMITView on GitHub
Refreshes the self-clone source map — the local source list (inventory.py), the access paths to external work systems (sources/access.md), and how far the owner is involved in each external system (sources/external.md). Use for "/survey", "refresh sources", "check connections", and for @survey in the frontier.
21 other projects use a version of this.
Adopted by
Most recently taken up by
- genkovich/sddtheir own version, first seen Oct 25, 2026
- PKU-DAIR/AutoScitheir own version, first seen Oct 25, 2026
- wheslleyrimar/BuildCLI-Agentstheir own version, first seen Oct 22, 2026
- steven112163/dotharnesstheir own version, first seen Oct 15, 2026
- DAIR-AutoResearch/AutoScitheir own version, first seen Oct 15, 2026
- h-wata/claude-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新
Also in 5 projects that use this
- LambenthanSkill
exp-eval
实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
- skyllwtSkill
exp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
phanghonghaoSkillposter
HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.
Also in 4 projects that use this
- +6 more from Lambenthan
- +1 more from skyllwt
Other versions21 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 21
- skyllwt/OmegaWiki★ 1.7ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- genkovich/sdd★ 187same name
- SNL-UCSB/literature-survey-skill★ 93same name
- Lambenthan/empiricalwiki★ 85same name
- spacedock-dev/spacedock★ 85same name
- V-Songbird/foreman★ 35same name
- jmylchreest/aide★ 19same name
11 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- clone-initSkill
- examSkill
- growSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run from the clone home.
- Very specific: line 18
Look at what this session actually has: connected MCP servers (their tool list), authenticated CLIs (gh auth status, glab auth status, aws …
- Very specific: line 48
If a newly seen area is not in the tree, add one line to the ## Candidates of the closest existing branch (do not create branches — that is …
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
survey — what is where and how to reach it (a map, not content)
Run from the clone home.
1. Local
python3 -I tools/inventory.py > sources/local.md2. Access paths — sources/access.md
For every work system, find a read tool that carries its own credentials and confirm it once with a harmless read. Never look at or write down credential values.
Look at what this session actually has: connected MCP servers (their tool list), authenticated CLIs (gh auth status, glab auth status, aws sts get-caller-identity…), and plugins. Typical rows:
| system | tool | check call |
| issue tracker (Jira, Linear, GitHub Issues…) | MCP or authenticated CLI | who-am-I |
| wiki (Confluence, Notion…) | MCP or CLI | who-am-I · list spaces |
| chat (Slack, Teams…) | MCP | read own profile |
| code host (GitHub, GitLab…) | gh / glab | current user |
| error tracker (Sentry…) | MCP | list organisations — if unauthenticated: "human hand: authenticate in /mcp" |
| dashboards (Metabase, Grafana…) | MCP | list databases/dashboards |
| notes (Obsidian…) | MCP or the folder itself | list files |
| other | server names and kinds only from .mcp.json / ~/.claude.json (never values) | — |
Shape of sources/access.md: system | tool | status (✓/✗/human hand) | why blocked | checked at.
- A system whose credentials exist on this machine but has no such tool (e.g. a key only in some config file) is written only as "credential location:
<path>— not connected, human hand". Never pull that key out. - For every working MCP server, note which of its tools write (send, create, update, delete, run query). Remind the owner to deny them in
tools/settings.py.
3. Scope — sources/external.md (read only; scope, volume, period only)
| system | what to count |
| issue tracker | project keys of issues the owner was assignee/reporter/commenter on, period, status mix, epic/component/label names |
| wiki | space keys and names, pages the owner wrote — count and topics |
| chat | channels the owner is in with a one-line purpose, the channels they talk most in, the people they talk with most (by role) |
| code host | projects the owner committed to or opened MRs in, group structure, MR count and period |
| error tracker | organisation and project names, issue volume |
| dashboards | collection/dashboard names (what is watched as a metric) |
Shape: one section per system, a table (scope · volume · period · candidate tree link), and a final "not reachable" list.
4. Feed the tree
If a newly seen area is not in the tree, add one line to the ## Candidates of the closest existing branch (do not create branches — that is /grow's job).
python3 -I tools/tree.py lint && git add -A sources tree && git commit -q -m "survey: <summary>"Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.