New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Repoprompt Tool Guidance Refresh

by w-winter in w-winter/dot314

Refresh RepoPrompt tool guidance when the CLI/MCP surface changes.

MITAuto-check passedAI & LLM Engineering

Install Repoprompt Tool Guidance Refresh

skills CLI
$ npx skills add w-winter/dot314 --skill repoprompt-tool-guidance-refresh -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install w-winter/dot314 repoprompt-tool-guidance-refresh --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/w-winter/dot314.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/repoprompt-tool-guidance-refresh .claude/skills/repoprompt-tool-guidance-refresh && rm -rf skills-src

Use ~/.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/

Facts

Skill name
repoprompt-tool-guidance-refresh
GitHub stars
139
Token cost
~1.7k tokens
SKILL.md length
723 words
Files
118 (incl. scripts, references)
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Refresh RepoPrompt tool guidance when the CLI/MCP surface changes.

  • Works in 3 steps: Run the version tracking script → The script writes a baseline snapshot… → Stop here. Tell the user
  • Tasks that involve Structured output and tool calling
  • SKILL.md covers Phase A — Pre-Upgrade (invoke…, Phase B — Post-Upgrade (invoke…, Phase C — Update MCP… and Phase D — Classic CLI…, plus 2 more sections

What it does

Repoprompt Tool Guidance Refresh is an agent skill from w-winter/dot314. Refresh RepoPrompt tool guidance when the CLI/MCP surface changes. Tracks RepoPrompt CE (rpce-cli, the maintained target) across versions, and can diff the frozen Classic CLI (rp-cli) against CE. Uses ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh to capture/diff --help and -l (tool definitions) under ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/rp-tool-defs/.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 120 other files, including scripts and reference files (for example `references/changelog-latest.md`, `rp-cli-prompts/rp-address-review-cli.md` and `rp-cli-prompts/rp-review-chat-cli.md`).

It sits in AI & LLM Engineering, covering Structured output and tool calling. It works with Model Context Protocol. The licence is MIT.

When your agent uses it

  • Tasks that involve Structured output and tool calling

Example prompts

  • “/repoprompt-tool-guidance-refresh”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Run the version tracking script
  2. The script writes a baseline snapshot under rp-tool-defs/
  3. Stop here. Tell the user

What it can do on your machine

Read from SKILL.md and the folder at commit 0c6bbc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Repoprompt Tool Guidance Refresh loads about 1.7k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 723 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

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.

Safety

Auto-check passed

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); the scripts in this folder are not scanned.

SKILL.md

The full file from w-winter/dot314 at commit 0c6bbc7, republished under its MIT licence (© w-winter). 723 words, ~1,688 tokens.

Download SKILL.mdSave it as .claude/skills/repoprompt-tool-guidance-refresh/SKILL.md (or your agent's skills folder). This skill also uses 117 other files; get the full folder from GitHub.
name
repoprompt-tool-guidance-refresh
description
Refresh RepoPrompt tool guidance when the CLI/MCP surface changes. Tracks RepoPrompt CE (`rpce-cli`, the maintained target) across versions, and can diff the frozen Classic CLI (`rp-cli`) against CE. Uses `~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh` to capture/diff `--help` and `-l` (tool definitions) under `~/.pi/agent/skills/repoprompt-tool-guidance-refresh/rp-tool-defs/`.
disable-model-invocation
true

Workflow

RepoPrompt CE (rpce-cli) is the maintained target and the default for this skill. RepoPrompt Classic (rp-cli) is frozen — it no longer changes, so you only touch it for a one-shot cross-app comparison.

Two comparison modes:

  • Same CLI across versions (the normal loop): older rpce-cli → newer rpce-cli, run as a pre/post pair around a CE upgrade.
  • Across apps (one-shot): Classic rp-cli vs CE rpce-cli, to understand where CE's tools/flags diverge from frozen Classic.

Canonical locations (use these even if your working directory differs):

  • Skill directory: ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/ (may be a symlink target)
  • Script: ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh
  • Output directory: ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/rp-tool-defs/

Snapshots are namespaced per CLI so Classic and CE never collide: CE writes rpcecli-help__{VERSION}.txt / rpcecli-l__{VERSION}.txt with baseline .baseline_version__rpcecli; Classic writes rpcli-* (frozen, last captured at v2.1.29).

Phase A — Pre-Upgrade (invoke BEFORE updating RepoPrompt CE)

  1. Run the version tracking script:

    bash
    ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh --pre

    (Defaults to CE. Equivalent if you cd into the skill dir: ./scripts/track-rp-version.sh --pre.)

  2. The script writes a baseline snapshot under rp-tool-defs/:

    • .baseline_version__rpcecli — the baseline rpce-cli version
    • rpcecli-help__{VERSION}.txt — output of rpce-cli --help
    • rpcecli-l__{VERSION}.txt — output of rpce-cli -l

  3. Stop here. Tell the user:

    ✓ Baseline captured at v{VERSION}. Go update RepoPrompt CE, then re-invoke this skill.

Phase B — Post-Upgrade (invoke AFTER updating RepoPrompt CE)

  1. Run the version tracking script:

    bash
    ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh --post

  2. On version change, the script captures a new snapshot and generates diffs under rp-tool-defs/:

    • rpcecli-help__{NEW_VERSION}.txt / rpcecli-l__{NEW_VERSION}.txt — new snapshots
    • rpcecli-help__{NEW_VERSION}.diff — changes in rpce-cli --help
    • rpcecli-l__{NEW_VERSION}.diff — changes in rpce-cli -l (MCP tool definitions)

  3. If no changes detected in the diffs, tell the user and stop:

    ✓ No MCP/CLI tool changes detected. Documentation is current.

  4. (Optional) Changelog context: Ask the user:

    Paste release notes for v{NEW_VERSION} (or press Enter to skip):

    If provided, write to ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/references/changelog-latest.md. If skipped, proceed using diffs as ground truth.

  5. Review diffs and identify what changed:

    • New tools
    • Removed tools
    • Changed parameters or descriptions
    • New modes/options

Phase C — Update MCP documentation (primary output)

The rp MCP tool surface is what Pi agents actually use, and it is app-neutral, so CE tool/help changes flow here.

  1. The MCP files live outside this skill folder:

    • AGENTS prefaces: agent/AGENTS-prefaces/rp-mcp-*.md
    • Prompts: agent/prompts/rp-*.md (excluding *-cli.md)

  2. Using the diffs as reference, make surgical updates to bring these files into alignment with the new tool definitions.

Phase D — Classic CLI documentation (only if a cross-app diff demands it)

Classic rp-cli is frozen, so its CLI docs do not need routine updates. The Classic-CLI artifacts are:

  • AGENTS preface: agent/AGENTS-prefaces/rp-cli-preface.md
  • Prompts: ~/.pi/agent/skills/repoprompt-tool-guidance-refresh/rp-cli-prompts/rp-*-cli.md
  • Extension: agent/extensions/repoprompt-cli/ (deprecated)

Only touch these if a cross-app comparison (Phase F) shows the guidance relies on a Classic-only behavior that CE has changed or dropped.

Show full SKILL.md (301 more words)Show less

Phase E — Git

Stage the changed files (new snapshots/diffs under rp-tool-defs/, plus any updated docs).

Phase F — Cross-app comparison (one-shot: Classic vs CE)

Use this to understand how CE's CLI/tool surface diverges from frozen Classic — useful when migrating guidance or validating the repoprompt-mcp extension's compatibility assumptions.

  1. Ensure a current CE snapshot exists (capture one if needed):

    bash
    ./scripts/track-rp-version.sh --ce --force

    The frozen Classic baseline is already captured (rpcli-*, v2.1.29). To refresh it while Classic is still installed: ./scripts/track-rp-version.sh --classic --force.

  2. Generate the cross-app diffs:

    bash
    ./scripts/track-rp-version.sh --compare-apps

    This writes, under rp-tool-defs/:

    • xapp-help__rpcli-{CLASSIC}__rpcecli-{CE}.diff — --help differences
    • xapp-l__rpcli-{CLASSIC}__rpcecli-{CE}.diff — tool-definition differences

  3. These diffs are large by design (different apps). Read them to spot CE tools, flags, or parameters that differ from Classic, then update Phase C (and only if necessary, Phase D).

Scope of Relevant Changes

Only update documentation for changes that affect levers you directly use:

  • New/changed/removed MCP tools
  • New/changed/removed CLI commands or flags
  • Changed parameters, modes, or behaviors

Ignore changes that only affect:

  • RepoPrompt desktop app UI (without MCP/CLI changes)
  • Integrations with other apps/harnesses (without MCP/CLI changes)
  • Internal implementation details not exposed via tools

The diffs are the source of truth. If a changelog item has no corresponding signature in the diffs, it's not relevant to this refresh.

Token Economy

The preface files are included in every session's system prompt. Keep them tight:

  • Do not document OS-level implementation details (e.g., how delete works under the hood) unless agents need to reason about it
  • When two ops overlap significantly (e.g., extract_handoff and get_log both read session transcripts), pick one canonical op for the preface and omit the other. Skills and prompts can expand on the omitted op when a specific workflow needs it
  • Behavioral notes about agent roles (e.g., what design produces) should be ≤10 tokens — just enough to route correctly

© w-winter, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 117 other files (scripts, references) in skills/repoprompt-tool-guidance-refresh of w-winter/dot314.

  • SKILL.md
  • references/changelog-latest.md
  • rp-cli-prompts/rp-address-review-cli.md
  • rp-cli-prompts/rp-review-chat-cli.md
  • rp-tool-defs/rpcecli-help__1.0.21.txt
  • rp-tool-defs/rpcecli-help__1.0.22.diff
  • rp-tool-defs/rpcecli-help__1.0.22.txt
  • rp-tool-defs/rpcecli-l__1.0.21.txt
  • rp-tool-defs/rpcecli-l__1.0.22.diff
  • rp-tool-defs/rpcecli-l__1.0.22.txt
  • rp-tool-defs/rpcli-help__1.5.68.txt
  • rp-tool-defs/rpcli-help__1.6.0.diff
  • rp-tool-defs/rpcli-help__1.6.0.txt
  • rp-tool-defs/rpcli-help__1.6.1.diff
  • rp-tool-defs/rpcli-help__1.6.1.txt
  • rp-tool-defs/rpcli-help__1.6.10.diff
  • rp-tool-defs/rpcli-help__1.6.10.txt
  • rp-tool-defs/rpcli-help__1.6.11.diff
  • … and 100 more

Open the folder on GitHubat commit 0c6bbc7

Compare with similar skills

Repoprompt Tool Guidance Refresh 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.

Repoprompt Tool Guidance Refresh compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Repoprompt Tool Guidance Refresh this skillw-winter/dot314139—~1.7kAutomated safety check: PassMIT
Tool Use Data Synthesissunny-glow/Auto-BenchMax1.3k—~3.3kAutomated safety check: PassNone
Agent Interface DesignNeeeophytee/finding-unknowns-skills343—~650Automated safety check: PassMIT
Ax Gendosco/aithy107—~5.4kAutomated safety check: PassApache-2.0
Perfupraullenchai/Rapid-MLX3.9k—~1.6kAutomated safety check: NotesCustom licence
Anthropic Product Knowledgesyahiidkamil/Software-Engineer-AI-Agent-Atlas4014 repos~651Automated safety check: PassNone

Similar skills

  • Tool Use Data Synthesis

    sunny-glow/Auto-BenchMax

    Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo.

    1.3k GitHub stars~3.3k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

  • Agent Interface Design

    Neeeophytee/finding-unknowns-skills

    Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.

    343 GitHub stars~650 tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed

  • Ax Gen

    dosco/aithy

    This skill helps an LLM generate correct AxGen code using @ax-llm/ax.

    107 GitHub stars~5.4k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Perfup

    raullenchai/Rapid-MLX

    Autonomous performance optimization: research, PoC, benchmark, implement, review, PR

    3.9k GitHub stars~1.6k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Anthropic Product Knowledge

    syahiidkamil/Software-Engineer-AI-Agent-Atlas

    Stop and consult this skill whenever your response would include specific facts about Anthropic's products.

    401 GitHub starsUsed in 4 repos~651 tokens
    AI & LLM EngineeringAuto-check passed

  • Fieldflow CLI

    guillaumegay13/fieldflow

    Use FieldFlow to inspect and reduce noisy JSON CLI output before it reaches model context.

    110 GitHub stars~872 tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

More from w-winter/dot314

  • Deep X Research

    w-winter/dot314

    Deep, exhaustive research on a topic across X (Twitter) by driving Grok (x.com/i/grok) through surf.

    139 GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed

  • Text Search

    w-winter/dot314

    Search indexed text corpora with qmd. An agent skill from w-winter/dot314.

    139 GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed

  • Prose Review

    w-winter/dot314

    Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing…

    139 GitHub stars~3.6k tokensUpdated 2 days ago
    Auto-check passed

  • Rp

    w-winter/dot314

    Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace.

    139 GitHub stars~3.4k tokensUpdated 2 days ago
    Auto-check passed

  • Surf

    w-winter/dot314

    Control Chrome browser via CLI for testing, automation, and debugging.

    139 GitHub stars~7.6k tokensUpdated 2 days ago
    Auto-check: warnings

  • Xcodebuildmcp

    w-winter/dot314

    Build/test Xcode projects via the XcodeBuildMCP MCP server using a local CLI wrapper for pi (no MCP support).

    139 GitHub stars~196 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Repoprompt Tool Guidance Refresh

What does Repoprompt Tool Guidance Refresh do?

Refresh RepoPrompt tool guidance when the CLI/MCP surface changes. Repoprompt Tool Guidance Refresh is an agent skill from w-winter/dot314. Refresh RepoPrompt tool guidance when the CLI/MCP surface changes.

When should I use Repoprompt Tool Guidance Refresh?

Repoprompt Tool Guidance Refresh fits situations like: tasks that involve Structured output and tool calling.

How do I install Repoprompt Tool Guidance Refresh in Claude Code?

Run `npx skills add w-winter/dot314 --skill repoprompt-tool-guidance-refresh -a claude-code`. Or copy the skill folder (skills/repoprompt-tool-guidance-refresh in w-winter/dot314) into .claude/skills/repoprompt-tool-guidance-refresh in your project. Claude Code loads it when a task matches its description.

How do I install Repoprompt Tool Guidance Refresh in Codex?

Run `npx skills add w-winter/dot314 --skill repoprompt-tool-guidance-refresh -a codex`. Or copy the skill folder (skills/repoprompt-tool-guidance-refresh in w-winter/dot314) into .agents/skills/repoprompt-tool-guidance-refresh in your project. Codex loads it when a task matches its description.

Can I use Repoprompt Tool Guidance Refresh in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add w-winter/dot314 --skill repoprompt-tool-guidance-refresh -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/repoprompt-tool-guidance-refresh, .gemini/skills/repoprompt-tool-guidance-refresh, .github/skills/repoprompt-tool-guidance-refresh and .opencode/skills/repoprompt-tool-guidance-refresh in your project.

What does Repoprompt Tool Guidance Refresh need to run?

SKILL.md names no scripts, command-line tools or credentials: Repoprompt Tool Guidance Refresh is instructions for the agent only.

Does Repoprompt Tool Guidance Refresh access the network?

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.

Is Repoprompt Tool Guidance Refresh safe to install?

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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Repoprompt Tool Guidance Refresh use?

Repoprompt Tool Guidance Refresh is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Repoprompt Tool Guidance Refresh use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 387 tokens, read only when the agent opens those files.

What are the alternatives to Repoprompt Tool Guidance Refresh?

Skills that share tags, products or a category with Repoprompt Tool Guidance Refresh: Tool Use Data Synthesis (sunny-glow/Auto-BenchMax, 1.3k stars), Agent Interface Design (Neeeophytee/finding-unknowns-skills, 343 stars), Ax Gen (dosco/aithy, 107 stars) and Perfup (raullenchai/Rapid-MLX, 3.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Repoprompt Tool Guidance Refresh?

w-winter (a GitHub user) maintains it in w-winter/dot314, which has 139 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: w-winter/dot314 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.