markdown agents

vincentmumme/personalos-boilerplate

Agent

Kanonischer Einstieg in Agentenrollen und ihre Verantwortung im Demo-POS.

zircote/human-voice

Agent

Reviews content files for AI writing patterns, character restriction violations, and voice profile compliance. Use this agent when editing or reviewing markdown content, blog posts, documentation, or any prose that should match the author's established writing voice.

zircote/human-voice

Agent

Conducts adaptive voice elicitation interviews. Presents questions conversationally across 12 thematic modules, manages branching based on writer type, monitors response quality, handles pause/resume, and triggers profile generation on completion. Use when the user wants to start or continue a voice elicitation…

zircote/human-voice

Agent

Synthesizes voice profiles from self-report scores and computational writing analysis. Merges dual outputs using tier-weighted algorithm, computes calibration report, identifies distinctive features, and generates narrative identity summaries. Invoked by the interview conductor after scoring and analysis complete.

zotoio/CRUX-Compress

Agent Cursor

Memory lifecycle manager for CRUX. Handles dream extraction, REM sleep rebalancing, conflict detection, compression, and Recall decompression.

zotoio/CRUX-Compress

Agent Cursor

Semantic compressor for Cursor rule files in .cursor/rules/. Converts markdown rules to CRUX notation achieving 5-10x token reduction while preserving all actionable information.

zotoio/CRUX-Compress

Agent Cursor

Engineering expert focused on codebase integrity. Audits code quality, test coverage, security, shell script best practices, CI/CD workflows, and CRUX notation consistency.

archugunov/pm-job-search

Agent

Use this agent for the gut-check moments of a job search: got an offer to weigh, stuck and don't know why, torn between two roles, a string of rejections you can't explain, wondering if you're aiming too high or too low. Also for proactive sharpening: positioning, outreach tactics, search strategy resets, negotiation…

archugunov/pm-job-search

Agent

Use this agent when reviewing a draft (case study, take-home assignment, interview-prep doc, outreach message, research brief, or any artefact where a PM's strategic POV is being tested) and you want a Chief Product Officer's lens — strategy clarity, scale-readiness, business-model fit, judgement under uncertainty.…

archugunov/pm-job-search

Agent

Use this agent for live interview practice — not draft review. The agent PLAYS the interviewer asking real hard questions, pushing back on hand-wavy answers, asking the unflattering follow-up. Three modes: full mock-round simulation (default), single-question deep-dive, or pressure-test on one specific story's weak…

arimxyer/doc-manager-mcp

Agent

Documentation lifecycle expert and orchestrator. Analyzes documentation state, assesses quality, coordinates sync workflows, and delegates content work to doc-writer. Use for any task requiring documentation analysis, validation, quality assessment, workflow orchestration, or state management. Do NOT use for…

arimxyer/doc-manager-mcp

Agent

Documentation content specialist. Creates and updates documentation files with platform-specific formatting, validates own work, and reports results. Use for straightforward content tasks with clear scope - writing API docs, updating guides, creating examples. Do NOT use for workflow orchestration, quality assessment…

muckybuzzwoo/claude-code-youtube-extract

Agent

Internal leaf worker for the yt-extract skill. Runs the yt-extract.py backend for a single YouTube URL and returns its output (summarized or raw). Dispatched only by the yt-extract skill's Step 1 — not for general use.

gideondk/strata

Agent

Process one parent-directory GROUP of bootstrap candidate files (e.g. .planning/auth-rewrite/PLAN.md + .../CONTEXT.md + .../SPEC.md) as a unit — read all files in the group, decide what concepts deserve their own notes across the set, write each note once, mark every source file processed, return one line per write.…

gideondk/strata

Agent

Isolated-context memory retrieval. Takes a natural-language query, searches the vault + code graph in this subagent's own context, returns a single curated brief (≤ 600 tokens) to the parent. Use this for heavy synthesis across many notes so the parent's context stays clean; it calls the ranked, supersession-aware…

zircote-plugins/documentation-review

Agent

Reviews documentation quality, accuracy, and completeness. Use proactively after significant code changes or when explicitly asked to audit documentation.

zircote-plugins/documentation-review

Agent

Writes, updates, and restructures documentation including API docs, READMEs, and technical guides from codebase analysis.

jozobeer/mojiemoji-plugin

Agent

A helper agent that chooses the font, color, animation, and speed for Mojiemoji image stamps in GitHub Markdown.

Blakeem/AI-Prompt-Guide-MCP

Agent

Implementation, debugging, and documentation specialist.

Blakeem/AI-Prompt-Guide-MCP

Agent

Code quality, security, and architectural analysis specialist.

retospect/precis-mcp

Agent Claude Code

Haiku mechanical filer — files a decided finding (gripe/backlog) after dedup; won't pick the target.

retospect/precis-mcp

Agent Claude Code

Sonnet backlog-readiness judge — vets a spec against prose/code; never writes code or flips status.

retospect/precis-mcp

Agent Claude Code

Cheap agent — mints a new migration/backlog/skill file from convention; never invents content.

jamestexas/agents

Agent

Use this agent to trace a reported symptom BACKWARD through the dataflow to the site that originates it, verify the load-bearing facts against primary sources, and terminate in an attributed disposition — root cause, fix-owner, and ticket action — not just an investigation write-up. Combines the SRE reflex (start from…