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

Mmd Insight Curation

by togechiyo in togechiyo/MMD_modoki

Curate reusable MMDmodoki knowledge from completed work, explicit owner decisions, verification results, docs, and diffs into insights cards and indexes.

MITAuto-check passed

Install Mmd Insight Curation

skills CLI
$ npx skills add togechiyo/MMD_modoki --skill mmd-insight-curation -a claude-code

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

GitHub CLI
$ gh skill install togechiyo/MMD_modoki mmd-insight-curation --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/togechiyo/MMD_modoki.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mmd-insight-curation .claude/skills/mmd-insight-curation && 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
mmd-insight-curation
GitHub stars
146
Token cost
~780 tokens
SKILL.md length
353 words
Files
2 (incl. scripts)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Curate reusable MMDmodoki knowledge from completed work, explicit owner decisions, verification results, docs, and diffs into insights cards and indexes.

  • Works in 6 steps: Keep detailed history, implementation,… → Add or update only the card content that… → Preserve the required front matter and… → …
  • Asked to extract
  • SKILL.md covers Load the contract, Classify evidence, Edit narrowly and Validate, plus 1 more section
  • Runs JavaScript scripts from its folder; calls node and git

What it does

Mmd Insight Curation is an agent skill from togechiyo/MMD_modoki. Curate reusable MMDmodoki knowledge from completed work, explicit owner decisions, verification results, docs, and diffs into insights cards and indexes. Use when asked to extract, record, update, or validate insights or human decisions; do not turn ordinary progress or unadopted external feedback into project policy.

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts.

The licence is MIT.

When your agent uses it

  • Asked to extract
  • Validate insights
  • Human decisions
  • Do not turn ordinary progress

Example prompts

  • “/mmd-insight-curation”

Requirements

  • Node.js

Workflow steps

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

  1. Keep detailed history, implementation, and comparisons in a canonical docs/ file.
  2. Add or update only the card content that changes a future decision.
  3. Preserve the required front matter and headings from the operation guide.
  4. Add the card to exactly one appropriate index
  5. When replacing guidance, retain the old record as retired or link the replacement instead of deleting the decision history.
  6. Never include local absolute paths, private asset details, secrets, or unsupported claims.

What it can do on your machine

Read from SKILL.md and the folder at commit 1e32b53. 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/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Mmd Insight Curation loads about 780 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~780

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 togechiyo/MMD_modoki at commit 1e32b53, republished under its MIT licence (© togechiyo). 353 words, ~780 tokens.

Download SKILL.mdSave it as .claude/skills/mmd-insight-curation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
mmd-insight-curation
description
Curate reusable MMD_modoki knowledge from completed work, explicit owner decisions, verification results, docs, and diffs into insights cards and indexes. Use when asked to extract, record, update, or validate insights or human decisions; do not turn ordinary progress or unadopted external feedback into project policy.

MMD_modoki Insight Curation

Keep insights/ useful as a compact decision layer without duplicating the human-facing detail in docs/.

Load the contract

Read these before editing cards:

Then search existing cards and canonical docs for the current topic. Do not create a new card until an existing card cannot represent the knowledge cleanly.

Classify evidence

  • Use observation for a reproducible lead or hypothesis that still needs confirmation.
  • Use verified only when tests, logs, current primary documentation, or explicit user-device confirmation support the result.
  • Use policy only for a decision rule that has held across conditions or is an established repository default.
  • Use decision only for an explicit project-owner adoption, rejection, deferral, confirmation, or constraint.
  • Use retired when assumptions changed or another card supersedes the guidance.

Treat statements such as “fixed” or “still broken” as technical evidence. Treat statements such as “proceed this way,” “do not add this,” or “defer this” as owner decisions. Keep technical truth and owner choice in separate cards when both are present.

External requests, issue reports, X posts, implemented code, and ambiguous conversation do not establish a project-owner decision by themselves.

Show full SKILL.md (158 more words)Show less

Edit narrowly

  1. Keep detailed history, implementation, and comparisons in a canonical docs/ file.
  2. Add or update only the card content that changes a future decision.
  3. Preserve the required front matter and headings from the operation guide.
  4. Add the card to exactly one appropriate index:
    • human decisions in decision-index.md;
    • priority: low cards in low-priority-index.md;
    • other active cards in index.md.
  5. When replacing guidance, retain the old record as retired or link the replacement instead of deleting the decision history.
  6. Never include local absolute paths, private asset details, secrets, or unsupported claims.

Validate

Run the bundled deterministic validator from the repository root:

powershell
node .agents/skills/mmd-insight-curation/scripts/validate-insights.mjs

Also run git diff --check. Fix validation errors before reporting completion. The validator checks structure and references; it does not prove that the classification or judgment is correct.

Report

State which cards were added, updated, or retired; identify the evidence class; and mention index/validation results. Do not commit or push unless explicitly requested.

© togechiyo, 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 1 other file (scripts) in .agents/skills/mmd-insight-curation of togechiyo/MMD_modoki.

  • SKILL.md
  • scripts/validate-insights.mjs

Open the folder on GitHubat commit 1e32b53

Compare with similar skills

Mmd Insight Curation 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.

Mmd Insight Curation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mmd Insight Curation this skilltogechiyo/MMD_modoki146—~780Automated safety check: PassMIT
Formatting Insight AxesPostHog/posthog40k—~2.1kAutomated safety check: PassCustom licence
Insight Error Pagevercel/next.js143k—~5.5kAutomated safety check: PassMIT
Verification Before Completionforyourhealth111-pixel/Vibe-Skills3.6k—~1.1kAutomated safety check: PassApache-2.0
Verification Before Completionfarm-fe/farm5.6k47 repos~1kAutomated safety check: PassMIT
Library Curatornexu-io/open-design100k—~574Automated safety check: PassApache-2.0

Similar skills

  • Formatting Insight Axes

    PostHog/posthog

    Official

    Pick the right y-axis unit when creating or updating an insight via posthog:insight-create or posthog:insight-update — both TrendsQuery (trendsFilter.aggregationAxisFormat) and SQL insights…

    40k GitHub stars~2.1k tokensUpdated yesterday
    DatabasesAuto-check passed

  • Insight Error Page

    vercel/next.js

    Official

    Write or audit an insight-kind error page for the Next.js dev overlay.

    143k GitHub stars~5.5k tokensUpdated today
    Writing & ContentAuto-check passed

  • Verification Before Completion

    foryourhealth111-pixel/Vibe-Skills

    Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready.

    3.6k GitHub stars~1.1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Verification Before Completion

    farm-fe/farm

    A skill your agent uses when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any…

    5.6k GitHub starsUsed in 47 repos~1k tokens
    Agent WorkflowsAuto-check passed

  • Library Curator

    nexu-io/open-design

    Search the OD Library (the global asset registry) and apply matching assets into the current project mid-task.

    100k GitHub stars~574 tokensUpdated yesterday
    Auto-check passed

  • Verification Before Completion

    jnMetaCode/superpowers-zh

    Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output.

    8.3k GitHub stars~443 tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from togechiyo/MMD_modoki

  • Mmd Release

    togechiyo/MMD_modoki

    Prepare or execute an MMDmodoki version release by reconciling version files, feedback ledger, release notes, verification, CI packages, tags, and GitHub Release assets.

    146 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Mmd Rendering Triage

    togechiyo/MMD_modoki

    Diagnose MMDmodoki viewport or exported-image rendering artifacts by separating shadow, transparency, geometry, depth precision, and pipeline causes.

    146 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Mmd Test

    togechiyo/MMD_modoki

    Select and run the smallest sufficient MMDmodoki verification set after code or configuration changes, then separate new failures from known baselines.

    146 GitHub stars~936 tokensUpdated today
    Auto-check passed

Questions about Mmd Insight Curation

What does Mmd Insight Curation do?

Curate reusable MMDmodoki knowledge from completed work, explicit owner decisions, verification results, docs, and diffs into insights cards and indexes. Mmd Insight Curation is an agent skill from togechiyo/MMD_modoki. Curate reusable MMDmodoki knowledge from completed work, explicit owner decisions, verification results, docs, and diffs into insights cards and indexes.

When should I use Mmd Insight Curation?

Mmd Insight Curation fits situations like: asked to extract; validate insights; human decisions; do not turn ordinary progress.

How do I install Mmd Insight Curation in Claude Code?

Run `npx skills add togechiyo/MMD_modoki --skill mmd-insight-curation -a claude-code`. Or copy the skill folder (.agents/skills/mmd-insight-curation in togechiyo/MMD_modoki) into .claude/skills/mmd-insight-curation in your project. Claude Code loads it when a task matches its description.

How do I install Mmd Insight Curation in Codex?

Run `npx skills add togechiyo/MMD_modoki --skill mmd-insight-curation -a codex`. Or copy the skill folder (.agents/skills/mmd-insight-curation in togechiyo/MMD_modoki) into .agents/skills/mmd-insight-curation in your project. Codex loads it when a task matches its description.

Can I use Mmd Insight Curation 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 togechiyo/MMD_modoki --skill mmd-insight-curation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mmd-insight-curation, .gemini/skills/mmd-insight-curation, .github/skills/mmd-insight-curation and .opencode/skills/mmd-insight-curation in your project.

What does Mmd Insight Curation need to run?

Going by SKILL.md and its folder, Mmd Insight Curation needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and git). Our summary lists: Node.js.

Does Mmd Insight Curation access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Mmd Insight Curation 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 Mmd Insight Curation use?

Mmd Insight Curation 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 Mmd Insight Curation use?

About 780 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mmd Insight Curation?

Skills that share tags, products or a category with Mmd Insight Curation: Formatting Insight Axes (PostHog/posthog, 40k stars), Insight Error Page (vercel/next.js, 143k stars), Verification Before Completion (foryourhealth111-pixel/Vibe-Skills, 3.6k stars) and Verification Before Completion (farm-fe/farm, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mmd Insight Curation?

togechiyo (a GitHub user) maintains it in togechiyo/MMD_modoki, which has 146 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 11, 2026.

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