search
Skill3 starsChanged 54 days agoMITView on GitHub
Use this skill when the candidate wants to find new roles or run their job search — e.g. "run my job search", "find new roles", "any new openings at my target companies?", "plan my search", "set up a daily search". Composes a search plan over the source catalog, probes employers' hiring systems headlessly, adds new on-thesis roles to the pipeline, and reports honestly on what it found.
54 other projects use a version of this.
Adopted by
Most recently taken up by
- beCyborg/jadlis-searchtheir own version, first seen Nov 8, 2026
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- Mahashwetha/Job-search-email-system-claudetheir own version, first seen Nov 5, 2026
- denolfe/dotfilestheir own version, first seen Nov 2, 2026
- Arcadia-1/virtuoso-bridge-litetheir own version, first seen Nov 1, 2026
- jav-ed/skill_Managtheir own version, first seen Nov 1, 2026
Used with
Projects with it also use fetch, integrate 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.
jtfasulo7Skillfetch
Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status codes or headers, follow redirects, or get page source for simple scraping. Prefer it over a browser when JavaScript rendering and page interaction are not needed. Supports proxies and redirect control.
Also in 3 projects that use this
modeled-information-formatSkillintegrate
This skill should be used when the user asks to "integrate mnemonic", "wire plugin", "add memory to plugin", "enable memory capture in plugin", "integrate memory operations", "add mnemonic protocol", "remove mnemonic integration", "rollback plugin integration", or "migrate legacy memory sections". It wires mnemonic memory capture and recall workflows into other Claude Code plugins using sentinel markers.
Also in 3 projects that use this
soilmassSkillexport
Animation export configurations including format selection, resolution, framerate, quality, and optimization settings. Use when rendering animations for web, mobile, video, or social media. Provides tokens for all export parameters across Lottie, GIF, video, and sprite sheet formats.
Also in 4 projects that use this
rogue-dev-studioSkillmonitoring
Claude monitoring and usage tracking tools (UV, claude-monitor, claude-usage-cli). Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `monitoring` work when listed in TEAM.yaml or explicitly requested.
Also in 3 projects that use this
DockerSkillwrite
Write or edit reader-facing technical prose for immediate comprehension. Use for documentation, PR titles and descriptions, release notes, design documents, user-facing explanations, and substantive comments. Also use when asked to make writing clearer, more natural, less AI-generated, or easier to read. For documentation fixes, handles edits, formatting, self-review, and commits after research identifies what to change. Do not use for code-only tasks with no prose deliverable.
Also in 3 projects that use this
JaimeGBASkillingest
Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base
Also in 4 projects that use this
Other versions54 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 54
- anthropics/knowledge-work-plugins★ 35ksame name
- exa-labs/exa-mcp-server★ 5.2ksame name
- browserbase/agent-browse★ 3.7ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
- Muuuun/luxas★ 1.2ksame name
- Arcadia-1/virtuoso-bridge-lite★ 1ksame name
- ZimoLiao/scholaraio★ 585same name
- BlockRunAI/blockrun-mcp★ 389same name
- project-numina/numina-lean-agent★ 279same name
- brightdata/skills★ 270same name
44 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.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 47 edited versions we read keep these.
3
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
- Very specific: line 33
Read criteria.md in full.
- Distinctive: line 37
Exits: when the confirmed plan is written to disk.
- Distinctive: line 57
Add on-thesis hits at To Review.
- Very specific: line 66
Session close: Run ../profile/scripts/check_files.mjs --workspace ..
- Distinctive: line 70
Never fabricate a listing, company, or metric.
“Common” is measured: kept by at least 6 in 10 of the 47 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
Search — a plan over instruments
Goal
Identify new on-thesis roles, save JDs to jd-inbox/, and add them to jobs.md at "To Review". Search discovers; evaluate assesses.
| Must be true | Where |
| Confirmed search plan before running sweeps | criteria.md § Search plan |
| New on-thesis roles at To Review with saved JDs and direct employer URLs | jobs.md + jd-inbox/ |
| Honest reporting (yield per source, counts, settings) | reply |
| Market insights recorded and dated | jobs.md § Search notes |
| Prune report proposes; engaged rows never touched | reply $\rightarrow$ jobs.md on confirmation |
Prerequisites
- Required: Workspace
CLAUDE.md(none → profile's Setup);criteria.md(targets, titles, geo, watchlist). - Optional:
companies.md,criteria.md § Search settings.
Loops and sequences
Instrument catalog and discovery tactics in references/patterns.md.
Plan composition (a sequence)
Runs when criteria.md lacks a ## Search plan or candidate requests a plan change.
- Read
criteria.mdin full. - Compose tailored queries and instrument choices (
references/patterns.md § The catalog). - Propose the plan in chat and stop. Candidate approval writes
## Search planintocriteria.mdbefore execution.
Exits when the confirmed plan is written to disk.
The sweep (the loop)
Runs when candidate asks to search or runs a manual sweep.
- Standard: The confirmed plan in
criteria.md. - Budget: At most 2 revision passes for thin results.
- Each pass: Execute plan instruments $\rightarrow$ parse results $\rightarrow$ diagnose thin yield (
references/patterns.md § Reading a thin result) $\rightarrow$ propose prune batch (To Review rows only; never propose engaged rows). - Obligations:
- Single revision: One evidence-backed revision pass at a time.
- To-Review ranking only: Active pipeline rows (Interested, Applied, Interviewing) are strictly excluded from prune proposals.
- Batch confirm: Proposed dismissals require explicit single batch approval.
- Exits: Sweep reported and prune actions confirmed; or the ceiling: two passes with the same yield → stop and present parameter adjustment as a decision for them to make. Standard does not bend to thin weeks.
Scheduled run (a sequence, unattended)
Runs when a recurring search schedule triggers (scripts/autopilot_sweep.py).
- Execute standing
criteria.md § Search planverbatim without logged-in scraping or unauthorized widening. - Add on-thesis hits at To Review; summarize results and list prune candidates without auto-dismissing.
Exits with summary delivered and prune candidates held for next attended session.
State
Owned: jobs.md, companies.md, leads.md, criteria.json, jd-inbox/, autopilot-log.md (shapes in references/schema.md).
- Hands back: New To-Review rows →
evaluate; radar hits →outreach. - Session close: Run
../profile/scripts/check_files.mjs --workspace .. No checker-subagent is spawned (search writes no candidate-voiced text). Report outcomes, never narration (clean is 1 line; fix FAILs before reply ends).
Guardrails
- Never fabricate a listing, company, or metric. Every entry requires a verifiable citation.
- Direct employer URLs only; no third-party spam aggregators.
Every reply ends with ONE contextual next step — a sentence with its why, not a menu.
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.