注释
代码注释与标注
curate-fused-memories
leodearden
"Run the memory-consolidation curation sitting: batch-rule the backlog of 'Human gate: consolidate duplicate cluster' tasks and execute the resulting consolidations against the fused-memory Mem0 corpus under the gate-3200 retain-and-tag shape. Use when the user says 'run the curation sitting', 'consolidate duplicate memories', 'batch-rule the consolidation gates', 'clean up the Mem0 corpus', 'curate memories', 'adjudicate the duplicate-cluster gates', or wants the memory-consolidation backlog (task 3524 / esc-3524-1) worked. This is NOT for: ordinary memory writes (use /memory), the reconciliation escalation queues (recon-escalation-watcher), unblocking stuck tasks (/unblock), or a single ad-hoc near-exact dedup that recon Stage 1/2 can absorb inline — per the 2026-08-02 policy, new clusters route through inline Stage 1/2 consolidation, not new gate tasks."
escalation-watcher
leodearden
"Watch for and handle level-2 escalations from the dark-factory orchestrator in a long-running loop. Under the 3-tier escalation ladder (L0→per-task steward, L1→escalation-watcher-auto, L2→human), this skill is the L2 consumer. Use this skill when the user wants to monitor escalations, says 'watch escalations', 'handle escalations', 'babysit the orchestrator', or wants a long-running session to catch and triage issues that the auto-watcher couldn't resolve. Also trigger when the user starts an orchestrator run and asks you to keep an eye on it, mentions escalations piling up, or wants automated escalation handling. This is a continuous loop skill that runs until stopped."
fuse-agent
commontoolsinc
Agent-specific interaction patterns for working with FUSE-mounted spaces. Use when deploying patterns via FUSE, working with Activity Logs, Annotations, or coordinating agent workflows that read/write pieces through the filesystem. Triggers include "deploy a pattern", "log an event", "create annotation", "agent workflow", or managing piece lifecycle via FUSE.
explain
LM-Kit
Explains any topic in plain language. Type a word or phrase and get a clear, jargon-free explanation.
cf-review
commontoolsinc
Review a changeset for the Common Fabric repo — the local branch diff vs main, or a GitHub PR. Flags correctness and regression bugs loudly, checks that runtime-semantics changes stay coherent across docs/comments/examples, catches duplicated core machinery (hashing, serialization, cloning, identity) and code fighting the transformer/reactive model, and scrutinizes whether the tests guard the right principles. Report-first; offers to post a self-signed PR review. Use when asked to review code, review a PR, review the current branch or diff, or self-review before pushing. Invoke as /cf-review or /cf-review <PR#>.
writing-code
commontoolsinc
Conventions for writing or changing code in this repository — the two documents to read before the first edit, which document governs the thing you are about to touch, and which conventions no automated gate will catch. Use before writing, changing, or refactoring TypeScript anywhere in the tree. Patterns need pattern-dev as well; this skill covers what is true of all code here.
topics
commontoolsinc
Interact with the Common Fabric team's Topics board on Estuary through
sqlex
go-sqlex
sqlex is a modern enhancement wrapper for Go database/sql based on jmoiron/sqlx,
jspecify-nullness
alexandru
JSpecify nullness annotations for Java APIs and tooling. Use when adopting or migrating JSpecify annotations, designing null-safe Java signatures and generics, or interpreting tool conformance and Kotlin interop.
kotlin-java-library
alexandru
Kotlin design for Java libraries and Java consumers. Use when building Kotlin code intended for Java callers, aligning with Java interop, JVM annotations, records, and backward/binary compatibility rules.
Skill: ticket-to-pr
strikersam
→ scope-guard: to stay focused
implementation-planner
strikersam
Plan a multi-file or multi-step implementation before writing any code. Use before any change touching more than two files, adding a new feature, or changing a module interface.
explain
Terryc21
'Deep-dive explanation of how a specific file, feature, or data flow works. Triggers: "explain", "how does X work", "walk me through", "what does this do".'
loment
Loment-Lang
Read this before writing a program in Loment - FujoOS's own systems language (Rust-flavoured surface syntax plus capability domains; six more surface grammars - C, C++, Java, C#, Go, Python - share its semantics, see docs/188). With the toolchain installed you can write, check and compile native executables with no Python runtime. Use it for: writing a Loment program or a .lomt file; writing a Loment library (a library is a directory, dependencies are the use lines in the source, exports are pub, optional pkg.lomp manifest, see section 9); managing or debugging dependencies; compiling or running with the loment command; reading the E001-E036 error codes; looking up a builtin or a piece of syntax (loment builtins / loment syntax / loment cheat); expressing a piece of logic in the project's own language; how to write struct / enum / match / capability / guard; giving a project its own source extension (source_ext in loment.conf, section 7.1); registering a custom loment subcommand (loment foo runs loment-foo from PATH, section 7.2); and what differs when migrating from another language. For anything about libraries and dependencies read the lompi guide first (~/.claude/skills/lompi/SKILL.md, or <prefix>/share/lompi/skill/SKILL.md when you only have the package) - installing a library, resolving dependencies, which libraries exist on this machine, and what a use <name> resolves to all live there. Also use this whenever the task is to author, read or debug Loment source (.lomt / .lom / .lomp) or a Loment library with the toolchain installed.
review-pr
osdlc
Review one or more pull requests and post the findings as a GitHub review. A marker in the posted review records the head commit it covered, so a later run with nothing new either stops (--mode auto) or asks whether to review again (--mode ask, the default), and a run over new commits reviews the delta since the last review first while still judging the changeset as a whole. Keeps its state on a per-PR git ref on origin (claim, findings, answers), rebuilt from the PR when missing, so several sessions can run the same sweep without posting twice. Suits a loop such as /loop /review-pr --mode auto.
comment-review
osdlc
"Review the comments in a diff or a subtree and minimize them against the expression ladder: a fact belongs first in the identifier, then in the signature and types, then in the declaration's doc annotation, and only when none of those can carry it does it earn an inline comment. Deletes comments that restate the code, moves facts down the ladder, tightens what survives to one short literal statement, strips volatile project state, and replaces duplicated prose with a reference to one canonical home. Invoke for \"review the comments\", \"too many comments\", \"comment cleanup\", or as the comment pass on a branch before review."
parley
osdlc
Check, serve and render a parley document as one review page, then read the reviewer's comments and answers back and reply to each one. A document is JSON: a list of typed blocks and the questions the agent needs answered. The peer parley.mjs is one bundled file that runs under bun, node 22+ and deno with no dependencies and no build step.
code-review
osdlc
"Review a change for correctness bugs and report concrete findings with a fix for each. The rubric other reviewing skills embed: what to read, what to look for, what to skip, and how to write a finding."
halcon-skill
bertram-eu
Generate, refactor, run, and review HALCON HDevelop (.hdev) and HDevelopEVO (.hscript) programs with accurate operator usage, parameter defaults, value ranges, and practical vision pipelines. Use when the user asks for HDevelop or HScript code, operator selection, debugging logic, converting requirements into vision scripts, or building reusable procedures.
80-retro
gamesexplained
The last step of every run. Name the skill text that changed what you did, record where the kit fell short, and change in the same branch only what the next run would not catch by itself, so the next contributor starts from a better kit. Complete game.json.
ship
ZachArticulateV
"Get finished work merged cleanly: write commits that follow the repository's conventions, open or update a pull request that says how the change was verified, watch CI and fix what fails at the root, and answer review comments. Use when the user asks to commit, push, open or update a PR, check or fix CI, address PR feedback, or whether a PR is ready to merge."
officecli-docx
lidicn
"Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments, headers/footers, or tables of contents. Trigger whenever the user mentions 'Word doc', 'document', 'report', 'letter', 'memo', or references a .docx filename."
visual-plan
thorgas
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.
officecli-pptx
lidicn
"Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck', 'slides', 'presentation', 'pitch', or references a .pptx filename."