discover
Skill2 starsChanged 8 months agoMITView on GitHub
This skill should be used when the user asks to "find me roles", "what should I apply to", "search for jobs", "discover roles", or "what's out there". Searches across job boards, company careers pages, and the web for roles matching the candidate's profile. Surfaces hidden gems and triages by fit. Supercharged with ~~jobs for multi-platform search and ~~search for semantic discovery.
60 other projects use a version of this.
Adopted by
Most recently taken up by
- rafaym1/scholarship-desktheir own version, first seen Nov 16, 2026
- ychampion/ystacktheir own version, first seen Nov 15, 2026
- relai-ai/agent-eval-looptheir own version, first seen Nov 15, 2026
- ZaxbyHub/opencode-swarmtheir own version, first seen Nov 15, 2026
- qbeka/jev-job-searchtheir own version, first seen Nov 12, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 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
LambenthanSkillexp-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
skyllwtSkillexp-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 versions60 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 60
- skyllwt/OmegaWiki★ 1.7ksame name
- DAIR-AutoResearch/AutoSci★ 1.7ksame name
- PKU-DAIR/AutoSci★ 1.7ksame name
- skyllwt/AutoSci★ 1.7ksame name
- suboss87/FDEOps★ 940same name
- anombyte93/prd-taskmaster★ 608same name
- zaxbysauce/opencode-swarm★ 532same name
- ZaxbyHub/opencode-swarm★ 531same name
- qbeka/jev-job-search★ 368same name
- hsantanna88/clo-author★ 262same name
50 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 repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- coffee-chatSkill
- company-researchSkill
- fit-analysisSkill
- follow-upSkill
- interview-debriefSkill
- interview-prepSkill
- mock-interviewSkill
- negotiateSkill
- offer-analysisSkill
- personalizeSkill
- pipeline-statusSkill
- write-applicationSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 53 edited versions we read keep these.
10
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 62
If pipeline-data.md exists: check for existing contacts that could be referral paths
- Distinctive: line 90
If any discovered roles are at companies where the candidate has existing contacts (from pipeline-data.md or coffee-chat history), flag: …
- Distinctive: line 125
If ~~jobs is connected (JobSpy or similar):
- Distinctive: line 126
Use it as the PRIMARY search engine — it aggregates Indeed, LinkedIn, Glassdoor, and ZipRecruiter in a single structured query
- Distinctive: line 131
If ~~search is connected (Tavily or similar):
- Distinctive: line 132
Use for semantic discovery: finding company careers pages, niche industry boards, MBA program recruiting pages, and startup job listings …
- Distinctive: line 137
If neither is connected:
- Very specific: line 139
Search multiple queries across different sources (see references/search-strategies.md)
- Very specific: line 145
No knowledge base: Stop and say: "Run /personalize first — I need your profile to search effectively."
- Distinctive: line 155
Use web search actively — search multiple sources, not just one query
- Distinctive: line 158
Only surface roles that genuinely match the candidate's profile
- Distinctive: line 159
Don't pad the list — a few strong matches beats many weak ones
“Common” is measured: kept by at least 6 in 10 of the 53 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
/discover
If you see unfamiliar
~~placeholders, see CONNECTORS.md.
Usage
/discover
/discover product manager at fintech startups
/discover senior PM roles in NYC
/discover <URL to job board or company careers page>How It Works
┌─────────────────────────────────────────────────────────┐
│ DISCOVER │
├─────────────────────────────────────────────────────────┤
│ Phase 1: Build queries from profile │
│ - Expand target titles to adjacent roles │
│ - Map seniority level to search terms │
│ │
│ Phase 2: Search across sources │
│ - Target company careers pages (if companies listed) │
│ - Web search (LinkedIn, job boards, career pages) │
│ - Industry-specific boards │
│ │
│ Phase 3: Evaluate and fetch JDs │
│ - Quick fit score (High / Medium / Low) │
│ - Fetch full JD text when possible │
│ - Flag logistics (visa, relocation, start date) │
│ │
│ Phase 4: Triage and present │
│ - Deduplicate, rank by fit, group by company │
│ - Separate: Role Matches vs Hidden Gems │
└─────────────────────────────────────────────────────────┘Detailed search strategies are in references/search-strategies.md. Load it for
platform-specific query patterns and title expansion tables.
Inputs
- Candidate profile from knowledge/profile.md (target roles, companies, location, situation)
- Optional: specific company, role type, job board URL, or search criteria from user
- If pipeline-data.md exists: check for existing contacts that could be referral paths
Produce
1. Role Matches
For each discovered role:
| Company | Title | Location | Quick Fit | Posted |
| [name] | [role] | [remote/city] | High/Med/Low | [date or ~age] |
One sentence on why it matches. Link to posting. If JD was fetched, include top 3 requirements so user can evaluate without clicking through.
2. Hidden Gems
Roles the candidate might not think to look for:
- Adjacent titles (e.g., "Chief of Staff" when targeting "Strategy")
- Emerging categories in their domain
- Companies they haven't considered
- MBA leadership programs or rotational programs at target companies
3. Triage Recommendations
- Apply now — strong fit, don't wait
- Worth a look — run
/fit-analysisfor deeper analysis - Reach but interesting — apply if time permits, note what's missing
- Skip — poor fit, explain why briefly
4. Referral Opportunities
If any discovered roles are at companies where the candidate has existing contacts (from pipeline-data.md or coffee-chat history), flag: "You have a contact at [company] — referral path possible."
Output Format
## Role Discovery: [N] roles found
### Apply Now
**Stripe — Senior PM, Payments** (SF / Remote) 🟢 High fit
> Top requirements: payments experience, cross-functional leadership, data-driven
> Why it fits: [one sentence mapping to profile]
> [Link] | Posted ~3 days ago
**Plaid — Product Lead, Developer Platform** (SF) 🟢 High fit
> ...
### Worth a Look
**[Company] — [Role]** ([Location]) 🟡 Medium fit
> Why to look: [reason]. Run `/fit-analysis` for full scoring.
### Hidden Gems
- **[Company] — Chief of Staff** — You wouldn't have searched for this,
but your ops + strategy background maps well. [Link]
### Referral Paths
- 🤝 **Stripe** — You had coffee with Sarah Chen (PM). Consider reaching out.
### Skip
- **[Company]** — [brief reason: seniority mismatch / location / etc.]If Connectors Available
If ~~jobs is connected (JobSpy or similar):
- Use it as the PRIMARY search engine — it aggregates Indeed, LinkedIn, Glassdoor, and ZipRecruiter in a single structured query
- Filter by: job type, location, remote status, salary range, posting recency
- This replaces manual web searching for job boards
If ~~search is connected (Tavily or similar):
- Use for semantic discovery: finding company careers pages, niche industry boards, MBA program recruiting pages, and startup job listings that don't appear on major boards
- Also useful for finding "hidden gems" — companies hiring for adjacent roles
If neither is connected:
- Fall back to built-in WebSearch + WebFetch
- Search multiple queries across different sources (see references/search-strategies.md)
If Something Goes Wrong
- No good matches found: Say so honestly. Suggest broadening: "Your search is very specific — want me to expand to adjacent titles or new industries?"
- Candidate's targets seem too narrow: Flag it with data: "Only 3 results for 'AI PM at Series A climate startups in NYC' — broader search would surface more options."
- Candidate's targets seem too broad: Suggest focusing: "50+ results. Want to filter by [industry / location / company size]?"
- No knowledge base: Stop and say: "Run
/personalizefirst — I need your profile to search effectively." - Job board URL provided but can't fetch: Note the limitation, search the web for the same company instead.
After Output
- "Interested in one? Paste the JD and I'll score it with
/fit-analysis" - "Want deeper intel on a company?
/company-research [company]" - "Ready to apply?
/write-applicationfor cover letter and outreach" - "Track these?
/pipeline-status add [company] [role]"
Rules
- Use web search actively — search multiple sources, not just one query
- Load references/search-strategies.md for platform-specific patterns
- Expand target titles to adjacent roles (see title expansion table in references)
- Only surface roles that genuinely match the candidate's profile
- Don't pad the list — a few strong matches beats many weak ones
- Fetch JD text when possible so user can evaluate without clicking
- Note posting age — stale postings (60+ days) should be flagged
- Note logistics: visa sponsorship, relocation, start date constraints
- Cross-reference with pipeline-data.md for referral opportunities
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.

