Most popular Claude skills · page 429

Agent skills for Claude Code, Claude.ai and other agents, ranked by popularity: GitHub stars, forks, and how many curated lists and repos include them.

22,429 skills · showing 20545–20592

  1. 20545Bio Proteomics Data Importhackernoon/cuttlefish-agent-skillsLoads mass-spectrometry data into Python/R and strips the search engine's bookkeeping before any number is trusted -- removes decoys (REV__/Reverse), contaminants (CON__/Potential contaminant), Only-identified-by-site groups, and resolves semicolon razor/leading protein-ID ambiguity in MaxQuant proteinGroups.txt, DIA-NN report.parquet, and mzML/mzXML. Distinguishes Intensity (raw) vs LFQ intensity (MaxLFQ) vs iBAQ, treats a MaxQuant zero as missing (NaN, not log2(-inf)), and inherits the acquisition mode's missingness contract (DDA MNAR vs DIA MCAR). Use when starting an analysis from raw spec9
  2. 20546Bio Proteomics Dia Analysishackernoon/cuttlefish-agent-skillsAnalyzes data-independent acquisition (DIA) proteomics by scoring reconstructed fragment-chromatogram peak groups against a decoy null with DIA-NN (library-free directDIA, library-based, or deep-learning predicted-library routes), Spectronaut, OpenSWATH, and EncyclopeDIA. Frames the deliverable around q-value LEVEL (precursor/peptide/protein-group) and CONTEXT (run vs experiment-wide/global) rather than a bare "1% FDR", and around the duty-cycle-vs-selectivity acquisition tradeoff (window design, staggered demultiplexing, diaPASEF, narrow-window Astral). Use when identifying and quantifying pr9
  3. 20547Bio Proteomics Differential Abundancehackernoon/cuttlefish-agent-skillsTests for differentially abundant proteins between conditions with limma/DEqMS empirical-Bayes moderation, proDA/msqrob2/MSstats missingness modeling, and Python Welch+BH alternatives. Frames missing values as left-censored MNAR (model, do not impute), makes variance moderation the load-bearing step at n=3-5, and prefers feature/peptide-level testing. Use when identifying proteins with significant abundance changes between experimental groups. Summarization and normalization mechanics are proteomics/quantification; volcano and MA plots are data-visualization/volcano-and-ma-plots; pathway enric9
  4. 20548Bio Proteomics Peptide Identificationhackernoon/cuttlefish-agent-skillsPeptide-spectrum matching from MS/MS with target-decoy FDR control, framing identification confidence as a property of a ranked list (q-value/PEP) rather than a raw engine score (XCorr, hyperscore, Andromeda, SpecEValue). Covers sequence-database search engines (Comet, MS-GF+, MSFragger, Sage, MaxQuant, MetaMorpheus), concatenated vs separate target-decoy competition, PEP vs q-value, the multi-level FDR cascade, open/mass-tolerant search, rescoring (Percolator, mokapot, MS2Rescore), and pyOpenMS SimpleSearchEngineAlgorithm + FalseDiscoveryRate. Use when identifying peptides from tandem mass sp9
  5. 20549Bio Proteomics Protein Inferencehackernoon/cuttlefish-agent-skillsGroups proteins from peptide identifications and controls protein-level FDR, framing inference as a chosen explanation (parsimony or a probability model) of underdetermined peptide evidence rather than a measurement. Reports protein GROUPS (proteins indistinguishable by observed peptides) with a leading protein, not flat lists. Covers shared-vs-unique peptides, indistinguishable/subsumable proteins, parsimony vs probabilistic (ProteinProphet, EPIFANY) vs razor inference, picked-protein and picked-group FDR, and why the two-peptide rule is wrong. Use when resolving which proteins are present fr9
  6. 20550Bio Proteomics Proteomics Qchackernoon/cuttlefish-agent-skillsQuality control for bottom-up proteomics across three levels -- instrument/raw-signal (mass accuracy, RT/iRT fit, FWHM, TIC vs injection time, % MS2 identified), identification/run (missed cleavages, charge states, PTM handling artifacts, contaminants), and experiment/quantitative (replicate correlation on log2, CV on the linear scale, completeness, MNAR-vs-MCAR missingness, PCA/batch, TMT channel balance, DIA q-values). Frames QC as a control chart against a per-instrument rolling baseline, not fixed cutoffs, and mandates inspecting raw boxplots, per-sample ID counts, total signal, and contam9
  7. 20551Bio Proteomics Ptm Analysishackernoon/cuttlefish-agent-skillsFrames PTM/phosphoproteomics analysis as three stacked inference layers on a biased enrichment - chemistry selection, site localization (FLR), and protein-level-adjusted quantification with MSstatsPTM - plus kinase-activity and functional triage. Covers MaxQuant Phospho (STY)Sites multiplicity expansion, localization-probability filtering (class I, Ascore, ptmRS, DIA EG.PTMLocalizationProbabilities, DIA-NN PTM.Site.Confidence), false localization rate (LuciPHOr/DeepFLR), motif analysis with experiment-matched backgrounds, diGly/K-GG ubiquitin specificity, acetyl/glyco traps, and KSEA/PTM-SEA. 9
  8. 20552Bio Proteomics Quantificationhackernoon/cuttlefish-agent-skillsQuantifies protein abundance from mass spectrometry using label-free (LFQ/MaxLFQ, DIA fragment-level), isobaric (TMT/iTRAQ reporter ions, MS2 vs SPS-MS3), and metabolic (SILAC) approaches, including peptide-to-protein summarization (Tukey median polish, MaxLFQ, msqrob), sample-loading and IRS cross-plex normalization, and isotopic impurity correction. Use when turning peptide/PSM/reporter signal into a protein-by-sample abundance matrix for downstream analysis. Statistical testing of that matrix is differential-abundance; DIA quant mechanics and DIA-NN runs are dia-analysis; reading search-eng9
  9. 20553Bio Proteomics Spectral Librarieshackernoon/cuttlefish-agent-skillsBuilds and manages DIA spectral libraries as peptide query parameters (precursor m/z, a few fragment m/z plus relative intensities, normalized RT, optional CCS), covering experimental DDA, chromatogram, and in-silico predicted libraries via Koina-served Prosit, AlphaPeptDeep, MS2PIP, and DeepLC, with iRT/CiRT RT calibration, NCE tuning, format conversion (DIA-NN tsv/speclib/parquet, OpenSWATH pqp/TraML, Spectronaut, blib/dlib/elib), and library QC/merge. Use when generating, calibrating, converting, or merging a spectral library to drive a DIA search. Running the actual DIA search is dia-analy9
  10. 20554Bio Qsar Modelinghackernoon/cuttlefish-agent-skillsBuilds QSAR / QSPR models using chemprop D-MPNN, MolFormer, Uni-Mol, ChemBERTa, random forest baselines, and Gaussian processes with explicit handling of OECD 5 principles, applicability domain (kNN, leverage, conformal prediction, Mahalanobis), scaffold-balanced splits, ensemble uncertainty, calibration (Platt, isotonic), feature importance (SHAP, atomic attribution), and prospective validation. Use when building target-specific predictive models from in-house bioassay data, ADMET endpoints, or selectivity profiles.9
  11. 20555Bio Reaction Enumerationhackernoon/cuttlefish-agent-skillsEnumerates virtual chemical libraries via reaction SMARTS transformations using RDKit and reaction templates, with explicit handling of atom mapping, RDChiral template extraction, product validation, RECAP/BRICS fragmentation, R-group decomposition, matched molecular pair analysis (MMPA), and Free-Wilson analysis. Use when generating combinatorial libraries from building blocks, enumerating analog series, deriving structure-activity rules, or extracting transformations from reaction data.9
  12. 20556Bio Read Alignment Bowtie2 Alignmenthackernoon/cuttlefish-agent-skillsAligns DNA short reads to a reference with Bowtie2, choosing end-to-end (whole read must align) vs local (soft-clip read ends) mode and a sensitivity preset; the de-facto aligner for ChIP-seq, ATAC-seq, and CUT&RUN, where fragment-geometry flags (--no-mixed, --no-discordant, --dovetail, -X) and a tool-appropriate MAPQ filter feed the peak caller. Use when aligning ChIP/ATAC/CUT&RUN reads, when read ends are adapter-contaminated and need soft-clipping, or when a tunable sensitivity/speed preset is wanted. DNA variant calling prefers bwa-alignment; RNA spliced alignment is star-alignment/hisat2-9
  13. 20557Bio Read Alignment Bwa Alignmenthackernoon/cuttlefish-agent-skillsAligns DNA short reads (paired- or single-end) to a reference genome with bwa-mem2, the maintained successor to BWA-MEM, for WGS/WES and germline/somatic variant-calling pipelines; covers index build, read-group injection, the collate/fixmate/sort/markdup ordering, soft-clipping for SV split reads, ALT/decoy-aware mapping on GRCh38, -K determinism, and streaming straight to a sorted BAM. Use when mapping DNA short reads to a reference for variant calling, coverage, ChIP/ATAC (alongside bowtie2-alignment), or SV detection. RNA-seq spliced alignment is star-alignment/hisat2-alignment; BAM sort/d9
  14. 20558Bio Read Alignment Hisat2 Alignmenthackernoon/cuttlefish-agent-skillsAligns RNA-seq reads to a genome with HISAT2, the splice-aware aligner whose hierarchical graph FM-index runs at roughly a quarter of STAR's memory (~7 GB for human), whose SNP/haplotype graph index reduces reference bias in the index itself, and whose MAPQ is GATK-friendly (60 for unique, no 255 problem). Use when RNA alignment must fit a memory-constrained machine, when feeding StringTie/Cufflinks transcript assembly via --dta, or when a SNP-aware graph index is wanted for allele-robust mapping. Feature-rich/high-RAM RNA alignment and fusion detection are star-alignment; DE on known transcri9
  15. 20559Bio Read Alignment Star Alignmenthackernoon/cuttlefish-agent-skillsAligns RNA-seq reads to a genome with STAR, the fast splice-aware aligner whose splice-junction database (built from a GTF at sjdbOverhang = readlength-1) and two-pass mode set junction sensitivity, whose 255-for-unique MAPQ breaks GATK, and whose GeneCounts output reveals library strandedness. Use when RNA reads must be placed on the genome for novel-isoform discovery, fusion detection, RNA variant calling, coverage tracks, splicing QC, or single-cell (STARsolo). Memory-constrained RNA alignment is hisat2-alignment; DE on known transcripts only should skip alignment for rna-quantification/ali9
  16. 20560Bio Read Qc Adapter Trimminghackernoon/cuttlefish-agent-skillsRemoves sequencing adapters from FASTQ reads with Cutadapt and Trimmomatic, including paired-end read-through, small-RNA 3' adapters, amplicon primers, and anchored/linked adapters. Use when FastQC shows adapter content climbing toward the 3' end, when inserts are shorter than the read length (small-RNA, cfDNA, FFPE), or before assembly/k-mer analysis. For all-in-one trimming use fastp-workflow; for quality/length filtering use quality-filtering.9
  17. 20561Bio Read Qc Contamination Screeninghackernoon/cuttlefish-agent-skillsDetects contamination in sequencing reads - cross-species (FastQ Screen, Kraken2), vector/PhiX/adapter, rRNA, and same-species cross-sample/index-hopping and sample swaps (SNP fingerprints via verifyBamID2/NGSCheckMate/somalier). Use when suspecting cross-contamination, PDX host reads, microbial carry-over, or sample swaps, and to decide whether to report, filter, or align to a combined reference. For deep taxonomic profiling use metagenomics/kraken-classification.9
  18. 20562Bio Read Qc Fastp Workflowhackernoon/cuttlefish-agent-skillsRuns all-in-one FASTQ preprocessing with fastp in a single pass - adapter trimming via paired-end overlap analysis, quality/length filtering, 2-color poly-G removal, base correction, optional dedup/UMI/merge, and HTML/JSON reports. Use when preprocessing bulk Illumina data and wanting one fast tool instead of separate Cutadapt, Trimmomatic, and FastQC steps. For precise small-RNA/amplicon adapters use adapter-trimming; for molecule-accurate UMI dedup use umi-processing.9
  19. 20563Bio Read Qc Quality Filteringhackernoon/cuttlefish-agent-skillsFilters reads by quality, length, N content, and complexity with Trimmomatic, fastp, and Cutadapt, including sliding-window trimming, per-read unqualified-base filtering, and 2-color poly-G removal. Use when reads have poor-quality tails, when an assembly or k-mer workflow needs clean input, or when a junk read subpopulation must be dropped. For adapter removal use adapter-trimming; for all-in-one preprocessing use fastp-workflow.9
  20. 20564Bio Read Qc Quality Reportshackernoon/cuttlefish-agent-skillsGenerates and interprets per-file and cross-sample QC reports from FASTQ data with FastQC, falco, and MultiQC, covering Phred quality, per-base composition, GC, duplication, overrepresented sequences, and adapter content. Use when performing initial QC on raw sequencing reads, validating preprocessing, or judging a multi-sample cohort for outliers and batch effects. For long reads use NanoPlot; for adapter/quality remediation route to adapter-trimming, quality-filtering, or fastp-workflow.9
  21. 20565Bio Read Qc Rnaseq Qchackernoon/cuttlefish-agent-skillsRuns RNA-seq-specific post-alignment QC - strandedness inference, gene-body 5'-3' coverage, read distribution (exonic/intronic/intergenic), rRNA/globin/mitochondrial rate, transcript integrity (TIN), and saturation - with RSeQC, Qualimap, RNA-SeQC, and Picard. Use when validating RNA-seq libraries before quantification or differential expression, diagnosing degradation or gDNA contamination, or determining library strandedness. For raw-FASTQ QC use quality-reports; for UMI dedup use umi-processing.9
  22. 20566Bio Read Qc Umi Processinghackernoon/cuttlefish-agent-skillsExtracts UMIs and collapses reads to original molecules with umi_tools (directional dedup) or builds error-corrected single-strand/duplex consensus reads with fgbio. Use when the library has UMIs and accurate molecule counting or below-sequencer-floor error correction is needed - single-cell, low-input RNA-seq, targeted panels, and ctDNA/liquid-biopsy rare-variant detection. For UMI extraction during QC use fastp-workflow; do not dedup non-UMI bulk RNA-seq.9
  23. 20567Bio Read Sequenceshackernoon/cuttlefish-agent-skillsRead biological sequence files (FASTA, FASTQ, GenBank, EMBL, ABI, SFF) with Biopython Bio.SeqIO, choosing between streaming, in-memory, and on-disk-indexed access. Use when parsing sequence files, iterating multi-record files, randomly accessing records by ID in large files, or maximizing parse throughput.9
  24. 20568Bio Reference Operationshackernoon/cuttlefish-agent-skillsGenerate consensus sequences and manage reference files using samtools. Use when creating consensus from alignments, indexing references, or creating sequence dictionaries.9
  25. 20569Bio Remote Homologyhackernoon/cuttlefish-agent-skillsDetect distant homologs using profile and structure-aware methods that go beyond standard BLAST. Use when sequence identity falls into the twilight zone (<35% pairwise), when BLAST fails to find homologs that should exist, when working at metagenomic scale (DIAMOND, MMseqs2), or when structure beats sequence (Foldseek). Covers PSI-BLAST (iterative PSSM), jackhmmer (iterative HMM), HHblits/HHsearch (profile-profile), DIAMOND, MMseqs2, and Foldseek (3Di structural alphabet, van Kempen 2024).9
  26. 20570Bio Reporting Automated Qc Reportshackernoon/cuttlefish-agent-skillsAggregates per-tool QC metrics (FastQC, fastp, alignment, quantification, variant calling, single-cell) into one interactive MultiQC report, and guides module scoping, sample-name resolution, large-cohort behavior, and turning the report into an actual QC gate. Use when summarizing QC across many samples, building a shareable quality report, or wiring automated QC into a pipeline.9
  27. 20571Call Scorergetclera/claude-skillsScore candidate interview and screening calls against a hiring rubric, using meeting transcripts and notes. Use this skill whenever the user wants to "score the interview", "give feedback on a candidate call", "how did that candidate do", "rate the candidates from this week's interviews", "pull my interview notes and score them", or wants structured feedback on a recorded conversation with a candidate. Connects to Granola via MCP to read transcripts and notes, then scores against the rubric-builder framework. Always score against an explicit rubric — build one first if none exists.5
  28. 20572Career Pivot Translatorgetclera/claude-skillsHelp someone changing careers translate their existing experience into the language of a new field. Use this skill whenever someone says "I'm switching careers", "how do I move from X to Y", "I want to pivot into [field]", "my experience is in A but I want to do B", "how do I make my background relevant for [role]", or is applying to roles outside their current domain. Finds the genuine transferable value in what they've done and reframes it in the target field's language — honestly, without overclaiming. Gather their full background and the target role before translating.5
  29. 20573Chatgpt Agentic Todogetclera/claude-skillsBuild and maintain a private, persistent agentic task inbox in ChatGPT. Capture actionable suggestions from connected email, Slack, meeting notes, calendar, and recent conversation context; deduplicate and triage tasks; provide a clear actionable UI and a "do it" prompt for each task. Use when the user requests an AI todo inbox, to extract follow-ups from their work, or to recreate Clera's agentic-todo workflow inside ChatGPT.5
  30. 20574Comp Negotiationgetclera/claude-skillsHelp a job-seeker understand their market worth and negotiate compensation. Use this skill whenever someone says "how much should I ask for", "help me negotiate my offer", "what's the market rate for [role]", "they asked my salary expectations", "should I counter this offer", or wants to know where an offer sits. Pulls live market data on the role/level/location, tells them where they stand, and generates the actual negotiation language for their situation — counters, scripts, and how to handle the awkward moments. Gather the role, level, location, and offer details first.5
  31. 20575Competitor Talent Intelgetclera/claude-skillsAnalyze competitors' hiring activity to inform sourcing and talent strategy. Use this skill whenever the user asks "who is [company] hiring", "what roles are competitors posting", "talent intelligence on [company]", "where can we poach from", "what does the market pay for X", or wants to understand hiring trends in their space. Uses the TheirStack MCP to query live job-posting data across companies, then turns it into actionable talent intel — hiring signals, tech stacks, where to source, and how the company's offer compares.5
  32. 20576CV Screenergetclera/claude-skillsScreen and rank candidate CVs/resumes against a role, producing a scored shortlist with reasons. Use this skill whenever the user uploads resumes and a job description, or says "screen these candidates", "rank these CVs", "who should we interview", "filter these applicants", "go through this batch of resumes". Also trigger for shortlisting from a candidate spreadsheet or list. Scores against the role's must-haves, nice-to-haves, and red flags, and surfaces signal beyond keywords.5
  33. 20577Hiring Briefgetclera/claude-skillsCreate a structured hiring brief / intake document before a search kicks off. Use this skill whenever the user says "build a hiring brief", "prep for a kickoff call", "intake for a new role", "align with the hiring manager", or is about to start a search and needs to define the target before sourcing. Produces the ideal-candidate profile, sourcing strategy, interview plan, and timeline — so the recruiter and hiring manager are aligned before a single CV is touched.5
  34. 20578Interview Prep Dossiergetclera/claude-skillsBuild a complete, personalized interview prep dossier for a specific role. Use this skill whenever someone has an interview coming up and says "help me prep for an interview", "I have an interview at [company]", "prepare me for this interview", "what should I know before my interview", or pastes a job description and wants to get ready. Scrapes the company website via Firecrawl, reads the pasted JD, and reads the candidate's uploaded resume, then produces tailored prep: what the company does, what they'll likely probe, how to connect the candidate's experience to the role, and smart questions 5
  35. 20579Interview Questionsgetclera/claude-skillsGenerate a structured interview question bank for a specific role, seniority, and the traits being hired for. Use this skill whenever the user says "give me interview questions", "what should I ask this candidate", "build an interview guide", "questions for a [role] interview", or is preparing a hiring panel. Produces competency, behavioral, and role-specific questions, each with what a good vs. bad answer looks like, so interviewers know what they're listening for.5
  36. 20580Interviewer Dossiergetclera/claude-skillsBuild a profile of the person who will interview you, from their exported LinkedIn profile. Use this skill whenever someone says "who is interviewing me", "tell me about my interviewer", "I'm meeting [name] for an interview", "help me understand this person before my interview", or uploads a LinkedIn profile PDF and wants to prep for a conversation with that person. Reads the interviewer's LinkedIn export and produces the "sauce": what they know deeply, what they likely care about, where their blind spots are, and how to build rapport. Ask the candidate to export the interviewer's LinkedIn pro5
  37. 20581Interviewer Researchgetclera/claude-skillsResearch an interviewer's public work — talks, podcasts, articles, interviews, posts — to prep for a conversation with them. Use this skill whenever someone wants to "look up my interviewer", "find what [name] has said publicly", "research the person interviewing me", "has my interviewer written or spoken anywhere", or wants to go deeper than a LinkedIn profile. Searches the web for the interviewer's published thinking and synthesizes what they care about, their stated views, and how to engage them. Ask for the interviewer's name and company to disambiguate.5
  38. 20582Jd Writergetclera/claude-skillsWrite compelling, structured job descriptions that attract strong candidates. Use this skill whenever the user wants to "write a JD", "create a job description", "draft a job posting", "we're hiring for X", or pastes a role brief and wants it turned into a posting. Also trigger when the user wants to improve an existing JD, make a role sound more attractive, or benchmark a role against the market. Always produce a full structured JD using the proven template below — the best JDs sell the company and the mission first, then the role, then qualifications.5
  39. 20583Offer Decision Toolgetclera/claude-skillsHelp someone decide between job offers, or whether to take an offer at all. Use this skill whenever someone says "I have two offers", "should I take this job", "help me compare these offers", "offer A vs offer B", "should I leave my current job for this", or is weighing a career decision. Gathers EVERYTHING about each option — comp, equity, growth, manager, risk, life fit — and produces a weighted decision framed around the person's actual priorities, with an honest take on equity and risk. Collect full details on every option before advising.5
  40. 20584Offer Lettergetclera/claude-skillsGenerate clean, professional offer letters from a few inputs. Use this skill whenever the user wants to "write an offer letter", "draft an offer", "make an offer for [candidate]", or is extending a role to a hire. Produces a complete, warm-but-professional offer letter and can flag if comp falls outside a defined band. Note: this drafts the letter — it does not send it or commit the company to terms.5
  41. 20585Outreach Personalizergetclera/claude-skillsWrite personalized candidate outreach messages that get replies — not templates. Use this skill whenever the user wants to "reach out to a candidate", "write a sourcing message", "draft outreach", "message this person on LinkedIn/email", or is running a sourcing campaign. Connects to Apollo via MCP to enrich candidate context (role, company, background) so the message references something real about the person. Produces outreach that sounds human and specific, never mass-blast.5
  42. 20586Public Face Review Buildergetclera/claude-skillsTurn a supplied people/contact list with names, profile-picture URLs, roles, LinkedIn URLs, and optional owner fields into a mobile-friendly face-memorization web app with grid, quiz, flashcard, shuffle, and filtering modes, then publish it to a shareable public URL when an approved writable hosting destination is available. Use when the user wants to memorize attendees, founders, candidates, customers, investors, or other people before an event or meeting.5
  43. 20587Rejection Writergetclera/claude-skillsWrite warm, specific candidate rejection emails that protect the employer brand. Use this skill whenever the user wants to "reject a candidate", "write a rejection email", "let a candidate down", "decline an applicant", or needs to close the loop with someone who didn't get the role. Tailors tone to how far the candidate got (applied / screened / interviewed / final round) and avoids the generic, brand-damaging rejection. Drafts only — the user reviews and sends.5
  44. 20588Rubric Buildergetclera/claude-skillsBuild structured, weighted interview scoring rubrics for any role. Use this skill whenever the user wants to "build a rubric", "create a scorecard", "set up interview scoring", "how should we evaluate candidates", "what should we score on", or is designing a hiring loop and needs a way to rate candidates consistently. Also trigger when the user wants to standardize how interviewers grade, reduce hiring bias, or align a panel on what "good" looks like. The rubric this skill produces is the backbone the call-scorer and cv-screener skills score against — build it first.5
  45. 20589Startup Career Findergetclera/claude-skillsHelp someone find the right STARTUP role based on their interests, experience, and what actually energizes them. Use this skill whenever someone says "what startup role is right for me", "help me figure out what to do", "I want to work at a startup but don't know what role", "what should my next move be", or is exploring career direction within the startup world. Asks sharp questions about their interests and past experience, then points them to real startup roles that fit — holding an elite talent bar and being honest when startups aren't the right fit. Startup-exclusive by design.5
  46. 20590Story Bank Buildergetclera/claude-skillsBuild a bank of strong behavioral interview stories by interviewing the candidate conversationally. Use this skill whenever someone says "help me prep behavioral stories", "I freeze on tell-me-about- a-time questions", "build my STAR stories", "I never know what examples to give in interviews", or wants a ready set of stories for behavioral rounds. Draws stories out of the candidate through RELAXED, casual conversation — not an interrogation — then shapes them into strong, reusable STAR stories mapped to the competencies a target role will test. Gather the candidate's background and target rol5
  47. 20591Strengths and Gapsgetclera/claude-skillsHelp a candidate identify what to highlight from their experience for a specific role, and surface gaps with a plan to address them. Use this skill whenever someone says "how do I match my resume to this job", "what should I emphasize for this role", "am I a good fit for this", "help me prepare my pitch for this job", or pastes a JD and wants to position themselves well. Reads the JD and the candidate's background, finds their genuine strengths against the requirements, and probes with SPECIFIC questions to verify whether they truly have the experience each requirement implies — then coaches t5
  48. 20592Agent DevelopmentDreydrey9000/claude-skillsThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.5