Skill Registry

Safe-to-fail experiment for Complex domain problems where cause-effect is only visible in retrospect. Two-phase: foreground qualify → background probe → sense result. Use when: probe, safe-to-fail, test hypothesis, experiment with hypothesis, Complex domain with hypothesis. NOT for brainstorming (use brainstorm) or known cause-effect (use investigate).

Resume session from CONTEXT-llm.md. Use when resuming work, loading saved context, continuing a previous session. Triggers include "load context", "resume session", "continue where I left off".

Recommend optimal Claude model (haiku/sonnet/opus) for a task. Use when user asks "which model", "pick model", "model for", or before starting costly/complex tasks. Covers tech and non-tech tasks.

Comprehensive toolkit for validating, optimizing, and understanding Prometheus Query Language (PromQL) queries. Use this skill when working with PromQL queries, prometheus queries, metrics queries, alerting rules, recording rules, or grafana dashboards to check syntax, detect anti-patterns, identify optimization opportunities, and interactively plan queries with users.

Use when the user asks to keep going, fix until green, converge on a verifiable target, or work within an explicit budget.

Use when plan/design is requested, whenever Codex is in Plan mode, or a non-trivial change needs evidence-backed scope, verification, or acceptance before action.

Splits a large feature branch into smaller, focused pull requests using stacked branches and cherry-pick. Groups commits by concern (infrastructure, application logic, tests, housekeeping), proposes descriptive branch names for user approval, creates stacked branches, and generates What/Why MR titles and descriptions. Use when the user says a PR is too big, asks to split a PR, wants to decompose a branch, or needs to break work into reviewable chunks.

Groups plan phases and tasks into dependency-ordered waves for parallel subagent execution via git worktrees. Builds a task dependency DAG, assigns wave numbers via topological sort, emits a living wave document that tracks status as work lands, and updates wave progress when tasks complete. Use when asked to: group tasks into waves, plan parallel execution, schedule worktrees, create a wave breakdown, wave planning, dependency grouping, update wave statuses, parallel subagents, which tasks can run in parallel.

Analyze collaboration patterns (HOW) and compute metrics from captured sessions. Use when reviewing collaboration quality, analyzing human-AI interaction, computing session metrics. Triggers include "retrospect collab", "collaboration analysis", "session patterns", "how am I collaborating".

Analyze domain insights (WHAT/WHY learned) from captured sessions. Use when reviewing learnings, extracting patterns, analyzing decisions. Triggers include "retrospect domain", "domain analysis", "what did I learn", "session insights".

Save session to CONTEXT-llm.md with conversation summary. Use when saving work, checkpointing progress, preserving session state. Triggers include "save context", "save session", "checkpoint", "save my progress".

Use when user reports an error, bug, or something not working. Search-first troubleshooting with diagnostic phase. Triggers: debug, error, broken, not working, failing, crash, exception.

Discover, install, compare, and manage Claude Code skills. Search the registry, get recommendations, validate skill quality, and manage your installed skills.

Use when the user wants a new git worktree created for a task. Picks a kebab-case branch name with a fix/feat/chore/docs/refactor prefix, runs `git worktree add` from the configured base branch, and reports the new path.

Use when the user wants a new git worktree created for a task. Picks a kebab-case branch name with a fix/feat/chore/docs/refactor prefix, runs `git worktree add` from the configured base branch, and reports the new path.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Retrieve Titan candidate memory records with source, record id, authority note, confidence, and verification path. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Create, validate, note, or close Titan session receipts as witnesses rather than final truth. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Activate Forge mutation or Delta judgment lanes only through matching explicit runtime gates on a Titan receipt. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Begin an explicit Titan service-cohort session with Atlas, Sentinel, and Mneme active and Forge or Delta locked. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Bind Titan bridge events, approvals, and replay state to explicit thread and turn ids for inspectable continuity. Use when a Titan service-cohort route needs this explicit bounded step. Do not use for hidden background agents, silent mutation, unreviewed proof sovereignty, or memory canonization without owner confirmation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Apply the aoa-session-self-diagnose workflow inside an abyss-* repository using repo-relative runtime evidence, bounded diagnostic-session artifacts, last-good comparison posture, and honest owner-aware handoff. Use when the base diagnosis workflow is correct but one abyss repo needs a thin runtime-owned diagnostic read model before any repair claim becomes honest. Do not use when the request is really for silent repair, when no concrete target path exists, or when the base skill is already sufficient without local adaptation.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Apply the aoa-safe-infra-change workflow inside an abyss-* repository using repo-relative operational surfaces, explicit local authority notes, rollback posture, and local validation commands. Use when the base infra-change workflow is correct but a thin project overlay is needed for one abyss repo. Do not use when the base skill is sufficient without local adaptation or when the task is really about producing a shareable artifact.

Explicit activation required: do not invoke or load this skill from an implicit match; wait for explicit user or operator invocation or a source-authorized parent-route selection. Apply the aoa-sanitized-share workflow inside an abyss-* repository using repo-relative sharing surfaces, explicit local thresholds, and local review posture. Use when the base sanitization workflow is correct but a thin project overlay is needed for one abyss repo. Do not use when the base skill is sufficient without local adaptation or when the real task is the underlying operational mutation.

Capture a meaningful architectural or workflow decision as an ADR or decision note, place it in the canonical decision surface, and verify the rationale stays discoverable. Use when structure, boundaries, tooling, or workflow expectations change and future contributors need to know why. Do not use for tiny self-evident edits or when the real problem is source-of-truth ambiguity rather than decision rationale.