MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Create a Classic change, clarify its requirements, and obtain user confirmation.
$ npx skills add rpamis/comet --skill comet-open -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rpamis/comet comet-open --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/assets/skills/comet-open .claude/skills/comet-open && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "comet-open" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills/comet-open into .claude/skills/comet-open/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-open", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/rpamis/comet/tree/master/assets/skills/comet-openType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add rpamis/comet --skill comet-open -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rpamis/comet comet-open --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .agents/skills && cp -r skills-src/assets/skills/comet-open .agents/skills/comet-open && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "comet-open" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills/comet-open into .agents/skills/comet-open/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-open", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rpamis/comet --skill comet-open -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rpamis/comet comet-open --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/assets/skills/comet-open .cursor/skills/comet-open && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "comet-open" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills/comet-open into .cursor/skills/comet-open/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-open", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/rpamis/comet.git --path assets/skills/comet-open--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add rpamis/comet --skill comet-open -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rpamis/comet comet-open --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/assets/skills/comet-open .gemini/skills/comet-open && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "comet-open" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills/comet-open into .gemini/skills/comet-open/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-open", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install rpamis/comet comet-openInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add rpamis/comet --skill comet-open -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .github/skills && cp -r skills-src/assets/skills/comet-open .github/skills/comet-open && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "comet-open" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills/comet-open into .github/skills/comet-open/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-open", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add rpamis/comet --skill comet-open -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install rpamis/comet comet-open --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rpamis/comet.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/assets/skills/comet-open .opencode/skills/comet-open && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "comet-open" agent skill from https://github.com/rpamis/comet/tree/master/assets/skills/comet-open into .opencode/skills/comet-open/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "comet-open", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
comet-openCreate a Classic change, clarify its requirements, and obtain user confirmation.
Comet Open is an agent skill from rpamis/comet. Create a Classic change, clarify its requirements, and obtain user confirmation. Use when the user invokes /comet-open or Classic enters Open or resumes initialization.
Its SKILL.md is about 5.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Agent Workflows. The repository describes itself as: Comet: agent skill harness for turning ideas into evaluated workflows. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 0fd42a0. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Comet Open loads about 5.9k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 3,138 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from rpamis/comet at commit 0fd42a0, republished under its MIT licence (© rpamis). 3,138 words, ~5,920 tokens.
.claude/skills/comet-open/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Before starting or resuming, read and follow comet-classic/reference/classic-layout.md. All OpenSpec CLI calls in this file must use the adapter, and all paths must use the <classic-*> logical roots bound by that protocol.
Every question and artifact-generation request passed to OpenSpec must specify the resolved Comet artifact language using a normalized ID such as en or zh-CN. Before .comet.yaml exists, read classic.language from project .comet/config.yaml, then global ~/.comet/config.yaml. After initialization, use comet state get <name> language. Fall back to the current request's language only when no language is configured. proposal.md, design.md, and tasks.md must primarily use that language.
When resuming an existing change, first inspect <classic-change-dir>/.comet.yaml:
comet classic workspace resolve <change-name> --json, enter the returned projectRoot, and select the change there.projectRoot, run comet state init <change-name> full --isolation <selected-isolation>, and then select the change.state set.comet classic workspace resolve <change-name> --json
# Enter the returned projectRoot
comet state select <change-name>For a new change, initialize .comet.yaml first and immediately run the select command above. Do not manually write a selection before state exists.
Read comet-classic/reference/workspace.md when creating a Classic change. Choose the workspace before creating OpenSpec artifacts or .comet.yaml; do not defer this to Build.
worktree directly. Prepare the independent workspace before creating OpenSpec artifacts or state.current, branch, and worktree options; a recommendation does not replace the user's choice.current and branch still require serial work. Do not describe them as suitable for concurrent sessions.Prepare the workspace before running OpenSpec new:
comet classic workspace prepare <name> --isolation <current|branch|worktree> --json
# Enter projectRoot; run subsequent OpenSpec/state commands and artifact writes thereThe prepare command reuses a registered worktree with the matching branch. If the branch remains but the registered worktree was removed, it recreates the worktree. Request an explicit rebind only if the branch was renamed, taken over for other work, or its ownership cannot be established.
Run this once on first use or after the upstream installation changes, and record the version for troubleshooting:
comet classic openspec -- --versionCheck actual capabilities rather than inferring compatibility from the version. Status must provide changeRoot, applyRequires, and each artifact's requires, outputPath, and status. Instructions must provide a usable resolvedOutputPath. The adapter has been checked against the state interfaces in OpenSpec 1.11.0/1.12.0; compatibility with every historical version is not guaranteed. If a command is unavailable, exits nonzero, or lacks a required capability, stop with the error and upgrade guidance. Do not upgrade the user's environment automatically.
After creation, comet state artifacts <name> --json checks paths, all required dependencies, and actual files. It recursively expands applyRequires together with Classic's mandatory proposal/tasks into the full dependency closure. If that closure requires design, do not skip it because instructions call it optional; design outside the closure is not mandatory.
Skipping specs is valid only when the request changes no behavioral specification, .openspec.yaml explicitly sets skip_specs: true, and no conflicting spec files exist. Supported roles are proposal/specs/design/tasks. Report unsupported mandatory roles or output patterns instead of guessing how to handle them.
Required now: Load the openspec-explore skill using the Skill tool. Do not skip this step.
<!-- external-openspec-skill-override -->
Adapt external OpenSpec instructions: Use its exploration method only. Do not follow instructions that directly invoke the official CLI, change to a fixed cwd, or read/write hard-coded OpenSpec directories. Use comet classic openspec -- <args...> for every CLI call and this invocation's bound <classic-*> roots for every path.
Reuse the user's PRD, designs, and confirmed facts first. Identify gaps in the following areas and produce a clarification summary. Ask only about unknowns that would change scope, the solution, or acceptance. If information is sufficient, proceed without additional questions; there is no minimum number of clarification rounds.
The summary must include all five areas: goal, non-goals, scope, key unknowns, and draft acceptance scenarios.
Before asking the user, read comet-classic/reference/decision-point.md. State the question, recommendation and reasoning, and each option's impact; prefer an available AskUserQuestion tool. Ask only about current gaps. If missing facts or materials cannot support real options, explain what is missing and request it. Apply this protocol to questions from the external exploration skill as well; loading that skill does not permit omitting choices or deciding for the user.
Reference a full PRD by path and relevant sections rather than copying it. Do not reconfirm settled facts; clarify only actual contradictions. OpenSpec skills remain mandatory dependencies. Return to Comet when exploration ends; external skills must not independently enter design, implementation, or archive. Exploration approval does not replace Open's final artifact confirmation.
For a large PRD, roadmap, complete product proposal, or a clarification summary containing multiple independent features, modules, user journeys, or milestones, assess whether multiple changes are needed before creating OpenSpec artifacts.
Use the clarified information to present a proposed split. Each item must include:
Recommend splitting when any of these apply:
If you recommend splitting, pause under comet-classic/reference/decision-point.md and wait for the user's choice. Include all these options:
Create every accepted item through /comet-open, not directly through /opsx:new. /comet-open creates both OpenSpec artifacts and .comet.yaml, keeping each change under the Comet state machine.
Do not create proposal.md, design.md, or tasks.md before the user chooses how to split the PRD. If they choose multiple changes, this /comet-open invocation handles split confirmation and scheduling only, then invokes /comet-open for each item in the approved order.
Immediately save the confirmed batch to .comet/batches/<batch-id>.json. Use a stable kebab-case batch-id. Record at least version, the original goal summary, creation time, ordered change names, and each item's goal, scope, non-goals, acceptance scenarios, and pending|open-complete|selected status. Atomically update the file after each item is created or completed. This list tracks batch order and progress; it does not replace each change's .comet.yaml.
When invoking /comet-open for a batch item, label it “confirmed split item” and pass its goal, scope, non-goals, and acceptance scenarios. Skip the PRD split assessment for a confirmed item unless that item still clearly contains multiple independent features.
Do not automatically move an individual batch item from Open to /comet-design. When the batch is complete, pause and ask which change to start. Advance only the selected change to /comet-design; leave the others unarchived for later recovery through /comet-classic.
Check every completed batch item; do not skip this: After all items finish Open, run the following for every <name> on the confirmed list:
comet state check <name> design --jsonThis entry validates the full required closure, actual OpenSpec outputs, and Comet state. Do not repeat a separate status scan. isComplete is diagnostic; optional artifacts do not block progress. Query status only after a failed check to locate missing dependencies or diagnose reported path/capability errors.
If any split item fails these checks, do not announce batch completion or ask which change to start. Stop further advancement and resume /comet-open at that change's first ready or blocked artifact. If OpenSpec checks pass but Comet state checks fail, repair .comet.yaml initialization or phase first, then rerun the batch checks.
Only after every item passes entry checks may you ask which change to start. Mark the user's chosen item selected in the batch list and advance that change alone to /comet-design. Leave the others unarchived for later recovery through /comet-classic.
On recovery, read .comet/batches/<batch-id>.json, then run the checks above for its created, unarchived changes. Do not recreate items that already pass. Resume failed items from the first ready artifact returned by OpenSpec. Create the remaining items from the saved list. If the list is missing or damaged, stop and ask the user to rebuild or confirm it; do not infer the original batch from directory names.
Before creating artifacts, turn Step 1's findings into a resolved brief containing goal, non-goals, scope, key unknowns, and draft acceptance scenarios. Derive an English kebab-case change name that accurately describes that scope.
comet-classic/reference/decision-point.md only when mutually exclusive scope or target-change choices remain. Naming preference alone is not a reason to pause.OpenSpec change names must use English kebab-case: lowercase letters, digits, and single hyphens. If a name conflicts but the goal is clear, choose a nonconflicting name with the same meaning and continue. Ask the user only when you cannot determine whether to reuse an existing change or create a new one.
While the resolved brief or change identity is still unclear, do not run comet classic openspec -- new change or create proposal/design/tasks. Resolve the missing information or genuine user decision before Step 2.
Required now: Load the openspec-new-change skill using the Skill tool. Do not skip this step.
<!-- external-openspec-skill-override -->
Adapt external OpenSpec instructions: Use its change-creation method only. Do not directly invoke the official CLI, adopt a fixed cwd, or write to a fixed OpenSpec root. Route creation, status, and instructions through comet classic openspec -- <args...>. Use this invocation's logical roots, including <classic-change-dir>, for all paths.
Do not load openspec-propose by default in the full /comet-classic flow. Load it only if the user explicitly requests a proposal and artifacts generated together.
<!-- external-openspec-skill-override -->
Adapt external OpenSpec instructions: The same restrictions apply to openspec-propose: no direct official CLI, fixed cwd, or fixed physical OpenSpec path. Commands must use the adapter and artifacts must use resolver-provided <classic-*> roots.
Create the change's initial structure following the loaded skill. If Step 1b already produced a clear resolved brief, override its “STOP and wait for user direction” behavior and proceed without repeating the question.
Use that resolved brief to populate the artifacts. Return to the skill's questions only if the brief still has ambiguity that would change scope.
Initialize recoverable state immediately after creating the initial structure; do not wait for every artifact to be generated (the entry check runs once in Step 3, not here):
comet state init <name> full --isolation <selected-isolation>
comet state select <name>Stop if any command fails. Then run comet classic openspec --agent-json -- status --change "<name>" --json once and check compatibility:
changeRoot must equal the bound <classic-change-dir>. planningHome, when present, must also be inside the repository. External artifact paths are unsupported.artifacts must include Classic's required IDs proposal and tasks; recursively follow their requires.applyRequires must be a resolvable list of artifact IDs. All direct and transitive dependencies must exist and be acyclic.Once the checks pass, generate the required artifacts from the schema and dependency graph returned by OpenSpec.
In Agent JSON mode, read upstream fields from data.upstream.data. Execute only the complete argv and cwd returned by data.nextAction; upstream raw nextSteps are diagnostic only.
Generate artifacts from OpenSpec state:
Reuse the status from Step 2's compatibility check for the first iteration, and the refreshed status from the preceding write for later iterations. Rerun comet classic openspec --agent-json -- status --change "<name>" --json only on recovery or external artifact changes, reading the full upstream JSON from data.upstream.data.
Expand the full dependency closure of applyRequires plus proposal/tasks. Once every item is done or legitimately skipped, run comet state artifacts <name> --json and exit the loop only if it passes. A completed top-level tasks artifact cannot hide incomplete dependencies. isComplete is diagnostic.
From unfinished artifacts with status: "ready", prioritize those that advance the applyRequires dependency closure, following CLI order. Do not hard-code generation order or assume the schema contains only proposal/design/tasks.
Get current instructions for each ready <artifact-id>:
comet classic openspec --agent-json -- instructions <artifact-id> --change "<name>" --jsonFollow the returned JSON instructions:
dependencies.template for the artifact's structure.instruction.context and rules as constraints; do not copy them into the artifact.resolvedOutputPath. For wildcard outputs, create every actual file required by the instruction.After each artifact is created, validate the closure locally with comet state artifacts <name> --json (no OpenSpec subprocess); refresh status once only when it reports a missing dependency or ordering error, or when new live instructions are needed, then recheck paths and the full dependency closure. Do not regenerate done items. Process only newly ready items in the closure, not unrelated optional artifacts.
Handle failures and blocked dependencies: If applyRequires is incomplete but no required dependency is ready, report the relevant blocked artifacts and their missingDeps, then stop. Do not guess order or skip dependencies. Also stop and report the OpenSpec error if adapter status / instructions fails, returns invalid JSON, escapes the repository, or lacks a usable resolvedOutputPath. Do not substitute a hard-coded document structure.
Check the name and scope: Use the English kebab-case name resolved in Step 1b; non-kebab-case names, including Chinese names, are not allowed. Keep scope consistent with the resolved brief and the user's request. Do not expand or narrow it on your own.
Confirm these artifacts exist:
<classic-change-dir>/
├── .openspec.yaml
├── .comet.yaml
├── proposal.md # Why + What: problem, goal, scope
├── design.md # When required or useful; keep technical decisions here without duplicating them
└── tasks.md # Task checklistCheck that state was initialized correctly:
comet state check <name> openContinue to Step 4 when it passes. On failure, the script reports the specific cause.
Resume unfinished creation steps: Open operations can be safely retried. On recovery, process the status in this order, retaining completed work:
projectRoot, and run comet state init <name> full --isolation <selected-isolation>. Stop and repair malformed state instead of overwriting it. Then select the change and run comet state check <name> open.comet classic openspec --agent-json -- status --change "<name>" --json and recheck changeRoot, core IDs, applyRequires, artifacts, and missingDeps.done: keep the artifact unchanged and do not regenerate it.ready: fetch its instructions with comet classic openspec --agent-json -- instructions <artifact-id> --change "<name>" --json, write the artifact accordingly, then validate the closure locally with comet state artifacts <name> --json instead of refreshing status.blocked: follow missingDeps and complete dependencies in the applyRequires closure first. Validate with comet state artifacts <name> --json after each dependency and refresh status only when it reports a new problem; do not generate a blocked artifact directly.comet state artifacts <name> --json passes.If required dependencies cannot progress, list the relevant blocked artifacts and missingDeps, then stop and report. Existing directories or three fixed files do not replace the CLI's checks. Conversely, an optional artifact outside applyRequires must not block implementation merely because isComplete: false.
Use the most recent successful comet state artifacts <name> --json result to check required artifacts. Rerun it after file or schema changes. Do not enter Step 5 or run the phase guard while any issue remains.
Then inspect content: proposal must cover the problem, goals, scope, and non-goals; design must cover high-level decisions and data flow; tasks must be explicit. If the schema returns specs or other artifacts, check their content against their instructions too. The presence of proposal, design, and tasks does not make other required content optional.
After all OpenSpec artifacts and content checks are complete, pause under comet-classic/reference/decision-point.md and wait for explicit user confirmation. Do not run the phase guard or advance automatically before confirmation.
This final review confirms the change name, scope, and artifact content together. Step 1b does not replace it; do not add a separate routine summary/name approval before it either.
Present a single-choice question with this summary and both options:
Summary:
Options:
After confirmation, complete the exit conditions. If adjustments are requested, update the relevant files and obtain confirmation again.
comet state artifacts <name> --json passes: the full required closure is complete or legitimately skipped, and required outputs are nonempty.comet guard <change-name> open --apply. The guard advances only after every check passes; it updates phase independently of auto_transition.Use --apply before exiting. Without it, .comet.yaml remains at phase: open and the next entry check fails.
comet guard <change-name> open --applyThe full workflow moves to phase: design; hotfix/tweak presets move to phase: build.
Follow comet-classic/reference/auto-transition.md and agent.continuation from the successful result. Do not repeat next, select, or check when valid state information is already available. Run the following only after context loss, external state changes, or when an older result lacks that information:
comet state next <change-name>NEXT: auto: invoke the skill named by SKILL to continue.NEXT: manual: do not invoke the next skill. Follow HINT, return control, and end this invocation without another confirmation question.NEXT: done: the workflow is complete.Hotfix/tweak skills control their own continuation after phase moves directly to build. Their next result names the corresponding preset skill.
© rpamis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in assets/skills/comet-open of rpamis/comet.
Open the folder on GitHubat commit 0fd42a0
Comet Open next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Comet Open this skillrpamis/comet | 3.2k | — | ~5.9k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
rpamis/comet
A skill your agent uses when 用户要启动或恢复 Comet 工作流,需要根据 active change、.comet.yaml、hotfix/tweak 意图路由到对应阶段 Skill。
rpamis/comet
Comet workflow entry. An agent skill from rpamis/comet.
rpamis/comet
Comet — OpenSpec + Superpowers dual-star development workflow.
rpamis/comet
Archive and deliver a Classic change. An agent skill from rpamis/comet.
rpamis/comet
Comet Classic workflow entry. An agent skill from rpamis/comet.
rpamis/comet
Complete the Classic technical design and obtain user confirmation.
Categories
Create a Classic change, clarify its requirements, and obtain user confirmation. Comet Open is an agent skill from rpamis/comet. Create a Classic change, clarify its requirements, and obtain user confirmation.
Comet Open fits situations like: the user invokes /comet-open; classic enters Open; resumes initialization.
Run `npx skills add rpamis/comet --skill comet-open -a claude-code`. Or copy the skill folder (assets/skills/comet-open in rpamis/comet) into .claude/skills/comet-open in your project. Claude Code loads it when a task matches its description.
Run `npx skills add rpamis/comet --skill comet-open -a codex`. Or copy the skill folder (assets/skills/comet-open in rpamis/comet) into .agents/skills/comet-open in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rpamis/comet --skill comet-open -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/comet-open, .gemini/skills/comet-open, .github/skills/comet-open and .opencode/skills/comet-open in your project.
SKILL.md names no scripts, command-line tools or credentials: Comet Open is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Comet Open is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.9k tokens (SKILL.md is roughly 24k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Comet Open: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
rpamis (a GitHub organization) maintains it in rpamis/comet, which has 3,166 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 9, 2026.
Source: rpamis/comet on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.