Executioner1939

This skill should be used when the user explicitly invokes `/oracle:bugfix <bug report>` to diagnose and fix a reported bug end-to-end, or when a message reads as an unambiguous bug report paired with a request to fix and ship it -- a pasted error or Slack/issue-tracker message, a described regression, "X is broken", "why does Y do Z", "is this intentional". Grounds in git history and project context before touching code, distinguishes an accidental regression from a deliberate design decision that is now wrong for a changed requirement, fixes the root cause with Boy Scout cleanup of directly-adjacent gaps, adds regression/unit test coverage, and lands the change as a hotfix -- branch, PR, merge -- by default, unless the user specifies a different flow.

Initialise the per-project oracle harness. Creates `.oracle/values.yaml` (committable per-project overrides), seeds it with sensible defaults inferred from the surrounding project (Cargo.toml -> rust, package.json -> typescript, pyproject.toml -> python, go.mod -> go, otherwise multi), then renders the harness in-place over the plugin tree using those values. Safe to re-run; idempotent. Use when first onboarding a project to oracle, or after a major upstream template change to refresh defaults.

Configure the model that narrates oracle session summaries. Selects which Claude model is invoked via `claude --model <m> -p` when the session-summary threshold is crossed (every 30 min of active agent time or every 50 turns, whichever lands first). Default is Sonnet 4.6. Set to `off` to disable the LLM narrative tier and keep only the deterministic counts. Modelled on `/model` in the Claude Code CLI.

Carbon decoder reference for Address Lookup Table program on Solana — program `AddressLookupTab1e1111111111111111111111111`, crate `carbon-address-lookup-table-decoder` (5 instructions, 1 account types). Use when decoding, indexing, or analyzing this program with Carbon: looking up instruction args/discriminators/accounts, account struct fields, or CPI event schemas. Run the bundled `scripts/carbon.py` to extract details from the local cargo cache. Triggers on "Address Lookup Table", "address-lookup-table", "carbon-address-lookup-table-decoder", "AddressLookupTab1e1111111111111111111111111", "AddressLookupTableDecoder", "Address Lookup Table program", "CloseLookupTable", "CreateLookupTable", "DeactivateLookupTable", "ExtendLookupTable", "FreezeLookupTable", "AddressLookupTable".

Carbon decoder reference for Associated Token Account program on Solana — program `ATokenGPvbdGVxr1b2hvZbsiqW5xWH25efTNsLJA8knL`, crate `carbon-associated-token-account-decoder` (3 instructions). Use when decoding, indexing, or analyzing this program with Carbon: looking up instruction args/discriminators/accounts, account struct fields, or CPI event schemas. Run the bundled `scripts/carbon.py` to extract details from the local cargo cache. Triggers on "SPL Associated Token Account", "associated-token-account", "carbon-associated-token-account-decoder", "ATokenGPvbdGVxr1b2hvZbsiqW5xWH25efTNsLJA8knL", "SplAssociatedTokenAccountDecoder", "Associated Token Account program", "Create", "CreateIdempotent", "RecoverNested".

Carbon decoder reference for Bonkswap on Solana — program `BSwp6bEBihVLdqJRKGgzjcGLHkcTuzmSo1TQkHepzH8p`, crate `carbon-bonkswap-decoder` (19 instructions, 5 account types). Use when decoding, indexing, or analyzing this program with Carbon: looking up instruction args/discriminators/accounts, account struct fields, or CPI event schemas. Run the bundled `scripts/carbon.py` to extract details from the local cargo cache. Triggers on "Bonkswap", "bonkswap", "carbon-bonkswap-decoder", "BSwp6bEBihVLdqJRKGgzjcGLHkcTuzmSo1TQkHepzH8p", "BonkswapDecoder", "AddSupply", "AddTokens", "ClosePool", "CreateDualFarm", "CreateFarm", "CreatePool", "Farm", "Pool", "PoolV2", "Provider".

Carbon decoder reference for Boop launchpad on Solana — program `boop8hVGQGqehUK2iVEMEnMrL5RbjywRzHKBmBE7ry4`, crate `carbon-boop-decoder` (26 instructions, 4 account types, 23 CPI events). Use when decoding, indexing, or analyzing this program with Carbon: looking up instruction args/discriminators/accounts, account struct fields, or CPI event schemas. Run the bundled `scripts/carbon.py` to extract details from the local cargo cache. Triggers on "Boop", "boop", "carbon-boop-decoder", "boop8hVGQGqehUK2iVEMEnMrL5RbjywRzHKBmBE7ry4", "BoopDecoder", "Boop launchpad", "AddOperators", "BuyToken", "CancelAuthorityTransfer", "CloseBondingCurveVault", "CollectMeteoraTradingFees", "CollectTradingFees", "AuthorityTransferCancelledEvent", "AuthorityTransferCompletedEvent", "AuthorityTransferInitiatedEvent", "BondingCurveDeployedEvent", "AmmConfig", "BondingCurve", "Config", "LockedCpLiquidityState".

Carbon decoder reference for Metaplex Bubblegum (compressed NFTs) on Solana — program `BGUMAp9Gq7iTEuizy4pqaxsTyUCBK68MDfK752saRPUY`, crate `carbon-bubblegum-decoder` (35 instructions, 2 account types). Use when decoding, indexing, or analyzing this program with Carbon: looking up instruction args/discriminators/accounts, account struct fields, or CPI event schemas. Run the bundled `scripts/carbon.py` to extract details from the local cargo cache. Triggers on "Bubblegum", "bubblegum", "carbon-bubblegum-decoder", "BGUMAp9Gq7iTEuizy4pqaxsTyUCBK68MDfK752saRPUY", "BubblegumDecoder", "Metaplex Bubblegum (compressed NFTs)", "Burn", "BurnV2", "CancelRedeem", "CollectV2", "Compress", "CreateTree", "TreeConfig", "Voucher".

Canonical spec for how research entries, sources, tools, topics, and pipelines are structured in this repo. Use whenever adding to INDEX/, when writing under topics/, when authoring or modifying a pipeline skill, or when validating a contribution against the standard. Defines frontmatter schema, identifier rules, linking conventions, status and confidence lifecycles, and provenance requirements.

Re-classify rows in INDEX/sources.md and INDEX/tools.md that landed in the `unsorted` bucket — either with `category=unsorted` or `kind=unsorted`. Re-applies the categories.md vocabulary and the kind heuristic with a fresh attempt, using GitHub topics, description, README excerpts. Use on demand or on a slow weekly schedule to drain the unsorted backlog.

Diff your current GitHub stars against INDEX/tools.md, emit a PR adding newly-starred repos and flagging unstarred ones. Also re-checks staleness (last_pushed > 3 years or archived) and moves stale repos to _archived/tools.md. Use daily via the star-sweep GitHub Action.

Add a new article, video, talk, paper, book, podcast, or repo to the corresponding INDEX/ table with correctly-shaped frontmatter, derived labels, validated URL, and provenance. Use whenever the user wants to add reading material or a new tool to the awesome list. Wraps the row shapes defined in `.claude/templates/{source,repo}.md`.

Sweep INDEX/sources.md (and optionally INDEX/tools.md) for dead links, moving entries with confirmed-dead URLs to _archived/ with tombstones (last_seen, reason, optional wayback link). Use weekly via the link-check GitHub Action, or on demand when the user wants a manual sweep. Never hard-deletes.

Parse a captured docs corpus into structured concept, API, tool, and entity extracts with frontmatter, plus relation edges, and emit the knowledge graph in Mermaid and JSON forms. Use after scrape-firecrawl when a topic needs structured semantic extraction beyond the URL link graph.

Scan configured release feeds for new libraries, frameworks, and tools in the user's interest areas (Rust, distributed systems, observability, build tooling, FP, DevOps, knowledge-graph / RAG). Append candidates to TRIAGE.md for manual review. Never auto-adds to INDEX/. Use daily via the new-releases-triage GitHub Action, or on demand.

Capture every page of a target docs site via Firecrawl into a topic's 20-sources/ directory as cleaned markdown plus link metadata. Use when starting a new topic that needs a docs corpus as its source-of-truth.