AgentAutoFlow

Any time an external api needs to be understood or queried, including post and get. Load with read_file on .kilocode/skills/api-use-external/SKILL.md (ignore the absolute path in the location tag).

Skill for web browser automation using Playwright for both local and external URLs. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. Load with read_file on .kilocode/skills/browser-use/SKILL.md (ignore the absolute path in the location tag).

When css being written or edited. Load with read_file on .kilocode/skills/coding-css/SKILL.md (ignore the absolute path in the location tag).

Troubleshooting issues, investigating errors, diagnosing problems, systematic debugging, analyzing stack traces, and identifying root causes before applying fixes. Load with read_file on .kilocode/skills/coding-debug/SKILL.md (ignore the absolute path in the location tag).

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing code, reviewing code, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. Load with read_file on .kilocode/skills/coding-guidelines/SKILL.md (ignore the absolute path in the location tag).

When html or jinja are being written or edited. Use this skill any time you are writing, editing, refactoring, or reviewing HTML (.html files or inline HTML) or Jinja2 templates. Trigger even for small HTML additions, new template blocks, editing existing template structure, or when a user says "update the layout", "fix the template", "add a section", or "edit the page". Load with read_file on .kilocode/skills/coding-html/SKILL.md (ignore the absolute path in the location tag).

Use when a coding-capable agent is starting or finishing implementation work. At start, clarify intent, scope, context, and verification strategy. At finish, run appropriate quality checks, assess impact, capture lessons, and produce a concise completion report. Trigger for both implementation intake and implementation closeout. Load with read_file on .kilocode/skills/coding-lifecycle/SKILL.md (ignore the absolute path in the location tag).

When markdown being written or edited, including rules, skills, and documentation. Trigger any time a .md file is being created or modified, a skill's SKILL.md is being updated, rules files under .kilocode/rules*/ are being edited, or a user says "update the docs", "fix the readme", "edit this skill", "write documentation", or "format this markdown". Load with read_file on .kilocode/skills/coding-markdown/SKILL.md (ignore the absolute path in the location tag).

When python, flask, or jinja are being written or edited. Use this skill any time you are writing, editing, refactoring, or reviewing Python (.py), Django-related, Flask routes/blueprints, or Jinja2 templates (.jinja or .html with Jinja). Trigger even if the user only mentions a .py file, a Flask endpoint, a template, or asks about Python patterns, imports, error handling, or structure. Load with read_file on .kilocode/skills/coding-python/SKILL.md (ignore the absolute path in the location tag).

Use when the task is specifically about PostgreSQL or Supabase behavior such as slow queries, EXPLAIN plans, index design, JSONB querying, pg_stat analysis, VACUUM/autovacuum, replication, extensions, pgvector, pg_trgm, or PostGIS. Invoke whenever the user needs Postgres-specific diagnosis or exact SQL/config guidance rather than generic database advice, including cases framed as query tuning, replication lag, database bloat, managed Postgres limits, or production-safe performance work. Load with read_file on .kilocode/skills/db-postgres/SKILL.md (ignore the absolute path in the location tag).

Any time database-related activity is required. Load with read_file on .kilocode/skills/db-use/SKILL.md (ignore the absolute path in the location tag).

Create distinctive, production-grade frontend interfaces with exceptional design quality. Use this skill any time the user asks to build, design, style, or beautify a web UI — including components, pages, dashboards, landing pages, posters, HTML/ Load with read_file on .kilocode/skills/frontend-design/SKILL.md (ignore the absolute path in the location tag).CSS layouts, Flask/Jinja templates, React or Vue components, or any visual artifact. Trigger even for partial requests like "make this look better", "style this page", "add animations", "improve the layout", or "design a card". If the request involves any visual output for the web, use this skill.

Any time github or git activity is required, including committing and pushing changes, creating or switching branches, merging, creating issues, checking status or logs, or reverting commits. Trigger whenever the user says "update", "commit", "push", "merge", "create branch", "checkout", "create issue", "git status", "revert", or any git/GitHub-related request - even if not framed explicitly as a "GitHub task." Load with read_file on .kilocode/skills/github-use/SKILL.md (ignore the absolute path in the location tag).

Compact the current conversation into a handoff document for another agent to pick up. Use this skill whenever the user asks for a handoff, continuation note, session summary for another agent, compacted context, or a document that lets a fresh agent continue the work. Load with read_file on .kilocode/skills/handoff/SKILL.md (ignore the absolute path in the location tag).

Call a Hermes agent from Kilo Code via the local chat completions API. Use for web scraping, browser automation, and research tasks that Hermes handles better (saved credentials, browser tools, web search). Load with read_file on .kilocode/skills/hermes-api-client/SKILL.md (ignore the absolute path in the location tag).

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable. Load with read_file on .kilocode/skills/improve-codebase-architecture/SKILL.md (ignore the absolute path in the location tag).

Self-improvement system for managing (finding/using, saving/adding, and pruning) solutions, patterns, lessons learned, and workarounds. Use this skill whenever a mode says "check learnings", "check memories", "prior solutions", "remember this", "save this pattern", or when you discover a non-obvious fix after 2+ failed attempts. Also trigger when encountering unexpected behavior that others might hit. Load with read_file on .kilocode/skills/learning/SKILL.md (ignore the absolute path in the location tag).

When a mode needs to read, create, or write (log progress) to a log file. Load with read_file on .kilocode/skills/log-file-use/SKILL.md (ignore the absolute path in the location tag).

For debugging, testing, or any purpose a mode may have for browsing the app's web site. Load with read_file on .kilocode/skills/login-using-querystring/SKILL.md (ignore the absolute path in the location tag).

For understanding what each mode does, which mode is best (most appropriate mode) for a given situation, and establishing a pattern for choosing when and how a mode delegates or passes operation to another mode. This skill provides `mode selection strategy`. Load with read_file on .kilocode/skills/mode-selection/SKILL.md (ignore the absolute path in the location tag).

When a planning mode (architect, planner-a, planner-b, planner-c) starts its work. This skill is *not* to be loaded for use with any other modes unless specifically called. Load with read_file on .kilocode/skills/planning-init/SKILL.md (ignore the absolute path in the location tag).

When a query was called directly from the research mode. Load with read_file on .kilocode/skills/research/SKILL.md (ignore the absolute path in the location tag).

Systematic ambiguity resolution through information gathering. Use when facing unclear requirements, unknown context, uncertain implementation choices, or any situation where guessing would be risky. Also use when another skill or rule directs you here via an ambiguity gate. Trigger this skill even for partial ambiguity — if you're weighing two approaches, unsure which files are in scope, or filling in gaps with "probably" or "I assume", that's ambiguity. Don't skip this skill just because you *could* guess; the cost of guessing wrong is wasted work. Load with read_file on .kilocode/skills/resolve-ambiguity/SKILL.md (ignore the absolute path in the location tag).

Security engineering toolkit for threat modeling, vulnerability analysis, secure architecture, and penetration testing. Includes STRIDE analysis, OWASP guidance, cryptography patterns, and security scanning tools. Use when the user asks about security reviews, threat analysis, vulnerability assessments, secure coding practices, security audits, attack surface analysis, CVE remediation, or security best practices. Load with read_file on .kilocode/skills/senior-security/SKILL.md (ignore the absolute path in the location tag).

Finds insights that eliminate multiple components at once — "if this is true, we don't need X, Y, or Z." Use this skill whenever you notice the same concept implemented multiple ways, a growing list of special cases, complexity that keeps spiraling, or when you hear "we just need to add one more case." Also trigger when refactoring feels like whack-a-mole, config files are growing, or someone says "don't touch that, it's complicated." Trigger immediately when asked to add yet another special case to an already long list. Otherwise known as "Simplification Cascades" — one insight that collapses 10 things at once. Load with read_file on .kilocode/skills/simplification/SKILL.md (ignore the absolute path in the location tag).

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch; evaluate, update or optimize an existing skill; run evals to test a skill; benchmark skill performance with variance analysis; or optimize a skill's description for better triggering accuracy. Load with read_file on .kilocode/skills/skill-creator/SKILL.md (ignore the absolute path in the location tag).

When creating tests and using tests for testing of application operation. Use this skill any time you are writing, running, or verifying tests — including pytest unit tests, integration tests, terminal verification scripts, or browser-based E2E flows. Trigger even for partial requests like "run the tests", "write a test for X", "verify this works", "check that the sync works", or "does this pass?". If any form of testing or verification is involved, use this skill. Load with read_file on .kilocode/skills/testing/SKILL.md (ignore the absolute path in the location tag).