Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 45121–45150 of 47988 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| sally-auditesscott1/job-search-assistantRead-only status and drift report for every skill/agent in GitHub repo esscott1/ClaudeCowork: compares the repo's main branch, the registry, the plugin marketplace, open PRs and Sally's queue against the skills actually installed in Alex's Claude account, and says which side is newer when they differ. Use when Alex asks what's installed, whether a skill is up to date, what has drifted, or for a skills status report, or when Sally needs the facts before a change. On demand from any surface. Never writes, commits, installs, or changes anything — fixes go to Sally. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-lead-intake-scanesscott1/job-search-assistantScan Alex's Gmail for new job leads (NorthStar Staffing/Jordan, LinkedIn job alerts, MyJobHelper), screen them for fit, and log new candidates to the Job Search Tracker. Cloud-only — runs on the daily schedule, no computer/browser needed. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-lead-tier2-scoringesscott1/job-search-assistantOn-demand deep-dive: fetch the real job description for one or more tracker rows (especially LinkedIn/MyJobHelper leads) using Alex's own signed-in browser, and upgrade the row's fit score and gaps from Tier 1 to a full read. Run only when Alex asks, or when he's at his computer. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| sallyesscott1/job-search-assistantSally is the front door for the agent development lifecycle (ADLC) of every skill in this skills repository. She lands changes herself (create, change, rename, retire, check in, drain the queue, package installs) as a branch + PR that the maintainer merges, and hands status and drift questions to the read-only sally-audit skill. Use whenever the maintainer asks to create, change, rename, retire, check in, or install any agent or skill, or says 'Sally'. Works from any surface (desktop app, phone, claude.ai web, cloud/scheduled); when the current session can't write to GitHub she queues the change in a claude.ai Project instead of improvising. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| sally-auditesscott1/job-search-assistantRead-only status and drift report for every skill in this skills repository: compares the repo's main branch, the registry, the plugin marketplace, open PRs and Sally's queue against the skills actually installed in the Claude account the session runs in, and says which side is newer when they differ. Use when the maintainer asks what's installed, whether a skill is up to date, what has drifted, or for a skills status report, or when Sally needs the facts before a change. On demand from any surface. Never writes, commits, installs, or changes anything — fixes go to Sally. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-fit-rubricesscott1/job-search-assistantShared scoring rubric for the job-search skills, not run on its own: job-lead-intake-scan, job-lead-tier2-scoring and job-lead-manual-jd-lookup load it whenever they set a Fit Score. Defines the evidence table the model fills in and runs score.py to turn it into a deterministic 1-10 score with a readable breakdown. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-lead-intake-scanesscott1/job-search-assistantScan the user's job sources from their job-search profile for new job leads: job-alert email in Gmail (job alerts, recruiters, job boards) and the company career sites they watch. Screen leads against their target roles and location, and log new candidates to their job tracker with a canonical link and a Tier 1 score. Cloud-only: runs on a daily schedule, no computer or browser needed. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-lead-manual-jd-lookupesscott1/job-search-assistantOn-demand, requires the user's computer: for tracker rows marked T2-pending-manual (job-lead-tier2-scoring couldn't reach the JD by web search: LinkedIn postings with no JD body, sites that block fetch), read the real JD using the user's own browser session and update the row. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-lead-tier2-scoringesscott1/job-search-assistantCloud-only, cron-friendly (every 2-4 hours): for tracker rows the user has ticked in the Run Tier 2 column, or rows they name, search the open web and fetch the real JD from company/ATS pages (never LinkedIn directly), save it to Drive, then score and update the row. Re-ticking a row rescores its saved JD against the user's current resume without searching again. Does nothing when no row is ticked. Rows it can't resolve are marked T2-pending-manual for job-lead-manual-jd-lookup. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-search-profileesscott1/job-search-assistantOn demand: sets up or updates the user's job-search profile, job-search-profile.md in their Google Drive. It holds their name, full-resume file, tracker sheet and folder, target roles, location and relocation rules, job sources (job-alert email senders and company career sites), housekeeping settings, and the look of their tailored resumes (resume-style.md, converted once from a Word template or style file they attach). Use it the first time someone sets up the job-search plugin ('set up my job search'), and whenever they change something in chat ('add a job alert sender', 'search for openings at Acme', 'watch https://careers.example.com/jobs', 'I'd relocate to Austin now', 'my tracker moved', 'set up my resume style', 'make my resume headings navy'). Interviews the user in short, menu-driven steps, pre-filled from their full resume; can save a full resume they attach or paste; checks the Gmail connector; finds and tests career sites. The other job-search skills read the profile; they never write it. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-trackeresscott1/job-search-assistantShared tracker contract for the job-search skills, not run on its own: job-lead-intake-scan, job-lead-tier2-scoring, job-lead-manual-jd-lookup, tailored-resume-builder and job-tracker-cleanup load it before reading or writing the Job_Search_Tracker Google Sheet. Defines which columns each skill owns, how rows are found, added and updated, the Score Tier values, the Run Tier 2 and Build Resume checkboxes, the per-job JD and fit-report files in Drive, the Archive tab, canonical_url.py for dedup, and read_posting.py with the rules for when a posting counts as closed. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| job-tracker-cleanupesscott1/job-search-assistantCloud-only, cron-friendly (weekly): moves stale rows from the Job Search Tracker's Job Log to its Archive tab: rows found more than the profile's archive age (30 days by default) ago that are still 'Need to review' and that the user hasn't touched. Never touches a row the user has acted on, and never deletes anything for good. Also on demand: 'clean up the tracker now', 'restore JS-123' to move an archived row back, or 'reset my job tracker' / 'start my job search over' to move every row to the Archive (after the user confirms) so the plugin starts fresh. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| tailored-resume-builderesscott1/job-search-assistantOn demand only, never scheduled: when the user says 'build ticked resumes' (tracker rows ticked in Build Resume), names tracker rows, or pastes a job description: picks the most relevant true content from the user's full resume and renders a .docx and PDF of at most 3 pages (or fewer when the user asks) in the user's own resume style (resume-style.md, or the plugin's default), plus a Google Doc of the same resume saved straight to the job's Drive folder. Never invents experience; reports gaps instead. Not for scoring (that's job-fit-rubric), not for editing the master inventory, and not for setting up the resume style (that's job-search-profile). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| finding-verifierOuros-App/ouros-skillsIndependently verify a suspected Ouros security finding. Use after another agent reports a vulnerability or suspicious behavior, before severity is finalized, an issue is opened, or a fix is proposed as security-critical. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ouros-ai-securityOuros-App/ouros-skillsAudit Ouros AI, MIDAS, MCP and tool-calling security. Use when reviewing prompt-injection resistance, tool authorization, cross-user/thread isolation, MCP boundaries, guardrails, model-controlled arguments, or whether AI behavior can exceed the authenticated user's privileges. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ouros-security-auditOuros-App/ouros-skillsCoordinate an authorized security audit of Ouros repositories and QA/local services. Use when the user asks for a broad security review, red-team-style assessment, attack-surface audit, pre-release security pass, or autonomous security campaign across multiple Ouros components. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| safe-runtime-testingOuros-App/ouros-skillsRun authorized, non-destructive security tests against Ouros local or QA services. Use for runtime verification of auth, authorization, API, business-logic or configuration hypotheses when the environment must be left clean and stable afterward. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ask-matthancrafted/markdown-harnessAsk which skill or flow fits your situation. A router over the skills in this repo. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| claude-handoffhancrafted/markdown-harnessHand the current conversation off to a fresh background agent that picks up the work immediately. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| code-reviewhancrafted/markdown-harnessReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| codebase-designhancrafted/markdown-harnessShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| commithancrafted/markdown-harnessAuthor a commit message and commit it — Conventional Commits header, Keep a Changelog body, Source trailer, enforced by a commit-time husky gate if setup (--setup-husky). Use before every `git commit`, whether a human or an agent initiates it, including a run split across commits. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-bugshancrafted/markdown-harnessDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| domain-modelinghancrafted/markdown-harnessBuild and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| git-guardrails-claude-codehancrafted/markdown-harnessSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| grill-mehancrafted/markdown-harnessA relentless interview to sharpen a plan or design. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| grill-with-docshancrafted/markdown-harnessA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| grillinghancrafted/markdown-harnessGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| handoffhancrafted/markdown-harnessCompact the current conversation into a handoff document for another agent to pick up. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| implementhancrafted/markdown-harnessImplement a piece of work based on a spec or set of tickets. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |