avifenesh
70 verified skills5,881 total stars
test-skill
Use when testing per-client skill rules
tools141
unknown-frontmatter-field
Use when validating frontmatter keys
tools141
unreachable-skill
Use when testing unreachable skills
testing141
with-context-agent
Use when testing valid context and agent configuration
testing141
with-custom-agent
Use when testing custom agent validation
testing141
with-model
Use when testing valid model configuration
testing141
test-skill
Use when testing per-client skill rules
tools141
agent-without-context-skill
Use when testing agent without context validation
testing141
agnix
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 385 rules.
tools141
hint-skill
Use when testing argument hints
testing141
code-review
Use when user asks to review code for quality and security issues.
development141
first-person-description
Use when you need pull-request review help
tools141
context-without-agent-skill
Use when testing context without agent validation
testing141
fork-with-instructions
Use when analyzing code quality
development141
directory-helper
Use when validating name-directory matching
tools141
bad-bool-skill
Use when testing boolean type validation
testing141
test-skill
Use when testing per-client skill rules
tools141
test-skill
Use when testing per-client skill rules
tools141
too-many-injections-skill
Use when testing injection limit validation
testing141
invalid-agent-skill
Use when testing invalid agent validation
testing141
test-skill
Use when testing per-client skill rules
tools141
test-skill
Use when testing per-client skill rules
tools141
agnix
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 385 rules across 10+ AI tools.
tools141
unknown-tool-skill
Use when testing unknown tool validation
tools141
deploy-prod
Use when deploying to production environment
devops141
with-argument-hint
Use when greeting users
tools141
deploy-prod
Deploys to production
devops141
reference-skill
Use when looking up documentation
documentation141
invalid-model-skill
Use when testing invalid model validation
testing141
bad-invocable-skill
Use when testing boolean type validation
testing141
helper
Use when validating vague skill names
tools141
test-skill
Use when testing per-client skill rules
tools141
test-skill
Use when testing per-client skill rules
tools141
tests/fixtures/skills/missing-frontmatter
No frontmatter here.
testing141
windows-path
Use when validating windows paths
tools141
with-hooks
Use when testing valid hooks
testing141
deep-reference
Use when validating deep references
tools141
indexed-arguments-no-hint
Use when validating indexed arguments
tools141
invalid-context-skill
Use when testing invalid context validation
testing141
hooks-skill
Use when testing hooks validation
testing141
invalid_name
Use when user wants to review code
development141
proactive-agent
Anticipation patterns and self-scheduling for proactive behavior. Use when deciding what to do next, before meetings, after deploys, during quiet periods, or when the agent loop needs a playbook. Keywords: anticipate, proactive, idle, self-schedule, meeting prep
testing4
pr-sweep
Sweep open PRs across all repos: triage, rebase stale branches, fix review comments, report what's ready for owner to merge. Use when idle loop detects open PRs, on cron schedule, or when asked to check PRs. Keywords: PR sweep, open PRs, stale PRs, review comments, rebase, triage, merge ready
testing4
growth-brief
Monthly self-improvement brief for Cairn. Queries error_patterns, action_exemplars, experiment_windows, and session_journal to synthesize what Cairn learned, where it failed, and 3 concrete proposals for Avi to approve. Run on the 1st of each month. Keywords: growth brief, monthly review, self-improvement, what did cairn learn, how is cairn doing, monthly report
data-ai4
pr-stall-detector
Detect agent-cairn PRs that have stalled (no activity >=90 min) and classify the failure mode to route to appropriate recovery agent.
data-ai4
self-improving-agent
Formalized learning loop that captures learnings, errors, and corrections to Cairn's memory system for continuous improvement. Use when: self-review, self-improve, learning loop, what did I learn, improve myself, reflect, what went wrong, error patterns, metacognition, weekly review, log this learning, should I log this. Keywords: self-review, self-improve, reflect, learn, errors, corrections, patterns, metacognition, soul, review, learning
data-ai4
self-review
Use when agent should review its own output before responding, or when asked to double-check work. Keywords: self-review, double-check, verify, validate, review output
testing4
skill-create
Use when asked to create a new skill, write a SKILL.md, add a capability, build a skill, or make a new prompt-based tool. Also use when importing or adapting an external skill. Keywords: create skill, new skill, SKILL.md, build skill, add capability, write skill, make skill, import skill, adapt skill
tools4
decision-support
Decision support with memory-backed context. Retrieves past decisions, journal history, and relevant facts before answering questions that involve a choice or tradeoff. Keywords: should I, which is better, tradeoff, compare, decide, choose, option, alternative, pros and cons, recommend
testing4
installer
Post-install skill adaptation: read a newly installed SKILL.md, fix environment-specific references (paths, accounts, tool names), assign the skill to relevant agent types, and propose an AGENTS.md update. Triggered automatically after cairn.installSkill completes.
tools4
telegram-digest
Manage Telegram notification batching and delivery to forum topics. Use when running digest crons, configuring notification preferences, or routing alerts to Telegram.
tools4
coding-session
Autonomous coding workflow: branch, code, test, draft PR. Use when starting a coding task from the idle loop or continuing an incomplete session. Keywords: coding, implement, fix, bug, PR, CI, test, review, worktree, autonomous
development4
skill-vetter
Assess trust and safety of external SKILL.md files before importing into Cairn. Use when asked to vet, review, import, or check an external skill. Keywords: vet, vetting, trust, safety, review skill, check skill, import skill, external skill, security review
development4
content-pipeline
Generate content drafts when a PR is merged or significant code ships. Produces a Twitter/X thread, blog post outline, and changelog entry from PR title, changed files, and commit messages. Keywords: content, tweet, blog, changelog, announce, write about, PR merged, shipped, released, draft post, social, thread
development4
pr-workflow
Use when creating PRs, monitoring CI, addressing review comments, or shipping code. Keywords: create PR, push, CI, review, merge, ship
development3
agent-hardening
Use when reviewing agent security, prompt injection defenses, input sanitization, LLM security hardening, or SSRF protection. Keywords: prompt injection, agent hardening, input sanitization, LLM security, SSRF, defense in depth
testing3
digest
Use when user asks for a digest, summary of updates, what's new, catch me up, or daily briefing. Keywords: digest, summary, updates, what's new, catch up, briefing
data-ai3
github
Use when performing GitHub operations: PRs, issues, CI, releases, or any gh CLI task. Keywords: github, gh, PR, pull request, issue, CI, actions, release, merge, review, repo
tools3
gogcli
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, Docs, Tasks, Chat, People, and Classroom via the `gog` command
tools3
secrets-scanner
Scan files or text for hardcoded secrets, API keys, tokens, PEMs, passwords, and connection strings. Use when importing external skills, vetting content, or auditing for credential leaks. Keywords: scan, secrets, credentials, api key, token, password, PEM, leak, vet, audit
development3
skill-enhance
Use when asked to validate a skill, check a SKILL.md, enhance a skill, lint skills, review skill quality, or fix skill issues. Runs structural and quality checks on Cairn skill files. Keywords: enhance skill, validate skill, check skill, lint skill, review skill, skill quality, fix skill, skill issues, SKILL.md check
development3
system-health
Use when asked about system health, server resources, infrastructure status, or 'how is the server doing'. Comprehensive host-level health report: CPU, memory, disk, database, Go process, TLS cert, SSE clients, poller health. For provider-specific checks use /provider-status instead. Keywords: system health, server, cpu, memory, disk, database, db size, wal, process memory, process, sse clients, poller, infrastructure, resources, uptime
tools3
web-search
Use when user asks to search the web, research a topic, find information online, or needs current data. Keywords: search, google, look up, find, research, news, what is, how to, latest
development3
push-notify
Send push notifications via Telegram (primary) or Gotify (fallback). Use when: notify, push notification, alert me, send notification, ping me, push alert, telegram, gotify, browser closed, user offline, task complete, approval needed, critical error, digest ready. Keywords: notify, push, alert, telegram, gotify, notification
development3
research
Structured multi-source research methodology. Enables web search, memory, file reading, and deep search for comprehensive investigation. Keywords: research, investigate, explore, analyze, gather, study
development3
code-review
Use when user asks to review code, check for bugs, review a PR, audit code quality, or find security issues. Keywords: review, audit, check, bugs, security, style, PR
development3
deploy
Use when user asks to deploy, build and ship, release, or push to production. Keywords: deploy, release, ship, build, push, production
development3
joi
Use when building joi schemas, validating input data, defining custom types, conditional validation with .when(), cross-field references, custom error messages, or writing joi extensions. Standalone package that integrates with the @hapi ecosystem.
tools3
hapi
Use when building @hapi/hapi servers, routes, plugins, auth schemes, HTTP APIs, request lifecycle, caching, stale-while-revalidate, server methods, views, startup sequences, or response marshalling.
tools3
onboarding
First-run onboarding: learns user name, use case, and communication style
tools3