skills/installer/SKILL.md
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.
npx skillsauth add avifenesh/cairn installerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Adapt a newly installed skill to this Cairn environment. Called automatically by the loop after cairn.installSkill or cairn.installPluginSkill succeeds.
Read the skill: cairn.readFile the installed SKILL.md from ~/.cairn/skills/<name>/SKILL.md.
Audit for environment references: Check for hard-coded paths, usernames, account IDs, tool names, or URLs that differ from this instance. Common issues:
cairn.getStatus)Fix issues in place: cairn.editFile to patch any mismatches. Preserve the skill's intent — only change environment-specific values.
Assign to agent types: Determine which agent types benefit from this skill (researcher, worker, planner, coder, skill-curator). Use cairn.loadSkill to verify the skill loads cleanly.
Propose AGENTS.md update: Draft a short bullet describing the new capability and what it enables. Use cairn.publishToFeed to surface the suggestion; the reflection engine will apply it.
Report: Summarize what was changed and which agent types now have access.
data-ai
Detect agent-cairn PRs that have stalled (no activity >=90 min) and classify the failure mode to route to appropriate recovery agent.
data-ai
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
testing
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
development
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