skills/skillify/SKILL.md
Turn proven agent-session patterns into first-party Harness Kit skills. Use when: "skillify this conversation", "make this into a skill", "generate a skill from current transcript", "extract reusable workflow". Trigger: /skillify.
npx skillsauth add phrazzld/spellbook skillifyInstall 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.
Convert an agent conversation into a durable skill when the behavior is novel, repeatable, and portable across harnesses.
MVP supports Claude Code JSONL transcripts and --from-current style local
transcript extraction. Gemini, Codex batch ingestion, hosted transcript stores,
and automatic publication are future work.
For novelty classification, portability critique, and new skill design,
delegate on judgment per the shared Roster contract: native subagents by
default; add cross-model critics, roster providers, or sprite lanes
(/sprites) only when they answer a distinct question. See
harnesses/shared/AGENTS.md (Roster).
Local lane guidance: Use specialized lanes for transcript-pattern mining, skill-design critique, portability/security review, and generated-skill validator.
cargo run --locked -p harness-kit-checks -- skillify-parse-transcript.cargo run --locked -p harness-kit-checks -- skillify-classify.
It may dispatch roster providers through the existing
harness-kit-checks dispatch-agent boundary when their judgment is
distinct, recording delegation receipts.cargo run --locked -p harness-kit-checks -- skillify-skill-crud.cargo run --locked -p harness-kit-checks -- bootstrap so the
first-party skill catalog propagates to active harnesses.Generated skills must be filesystem-first and cross-harness. Reject content
that depends on harness-private operations such as SendUserMessage, direct
tool names like Edit, or raw bash instructions without a fallback path.
Use the frontmatter schema in references/frontmatter-schema.md.
cargo run --locked -p harness-kit-checks -- skillify-parse-transcript,
cargo run --locked -p harness-kit-checks -- skillify-classify,
cargo run --locked -p harness-kit-checks -- skillify-skill-crud,
cargo run --locked -p harness-kit-checks -- check-frontmatter --repo .,
cargo run --locked -p harness-kit-checks -- bootstrap,
dagger call check --source=.skills/skillify/.Run cargo run --locked -p harness-kit-checks -- check-frontmatter --repo .
after CRUD output and bash bootstrap.sh before shipment; the generated skill
must also pass
cargo run --locked -p harness-kit-checks -- skillify-skill-crud validate --name <name>.
tools
Enumerates the peer AI agent CLIs installed on this machine (codex, claude, pi, opencode, cursor-agent, grok, agy, hermes, thinktank) and how to invoke each headlessly. A capability map, not a quota: useful for fresh-context adversarial review on a different model family, second opinions, competing attempts, and wide benches. Use when: "ask codex", "ask another model", "second opinion", "cross-model review", "what AI tools do I have", "other agents", "different model family", "adversarial critique from another provider". Trigger: /roster.
development
Run lane cards on Fly Sprites: remote, isolated, scale-to-zero sandboxes for heavy or parallel agent work. Golden-checkpoint provisioning so lanes start on a ready sprite with zero setup tokens. Use when: "run this on a sprite", "remote lane", "offload to a sandbox", "dispatch to sprites", "bake a sprite", "sprite fleet", heavy/long-running/parallel sub-agent work that should not run on this machine. Trigger: /sprites, /sprite-lane.
testing
Compose and launch roster-backed specialist lanes with prompt-native lane cards and receipts. Use when: "dispatch agents", "use subagents", "compose a team", "run provider lanes", "make lane cards". Trigger: /dispatch, /subagents, /lanes.
tools
Fast session-start repository orientation from live local evidence. Use when: "orient yourself", "start of session", "new session", "where are we", "catch me up before acting", "what should I do next", after compaction, after switching worktrees, or before choosing a Harness Kit workflow. Trigger: /orient, /ground, /session-start.