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

Speckit Wiki Ingest

by haru in haru/redmine_ai_helper

Ingest a source (feature artifacts, file, or URL) and update the related wiki pages with citations

MITAuto-check passedKnowledge Management

Install Speckit Wiki Ingest

skills CLI
$ npx skills add haru/redmine_ai_helper --skill speckit-wiki-ingest -a claude-code

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

GitHub CLI
$ gh skill install haru/redmine_ai_helper speckit-wiki-ingest --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/haru/redmine_ai_helper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/speckit-wiki-ingest .claude/skills/speckit-wiki-ingest && 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
speckit-wiki-ingest
GitHub stars
106
Token cost
~1.2k tokens
SKILL.md length
670 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Ingest a source (feature artifacts, file, or URL) and update the related wiki pages with citations

  • Works in 7 steps: Resolve configuration and the wiki → Register the source → Read the source and extract wiki-worthy… → …
  • Tasks that involve LLM wikis
  • SKILL.md covers User Input, Steps and Guardrails
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Speckit Wiki Ingest is an agent skill from haru/redmine_ai_helper. Ingest a source (feature artifacts, file, or URL) and update the related wiki pages with citations

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires spec-kit project structure with .specify/ directory

It sits in Knowledge Management, covering LLM wikis, Spec-driven development and Citation management. The repository describes itself as: A Redmine plugin that adds AI agents, MCP Server, smart completion, and vector search. The licence is MIT.

When your agent uses it

  • Tasks that involve LLM wikis
  • Tasks that involve Spec-driven development
  • Tasks that involve Citation management

Example prompts

  • “/speckit-wiki-ingest”

Requirements

  • Compatibility (from SKILL.md): Requires spec-kit project structure with .specify/ directory

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Resolve configuration and the wiki
  2. Register the source
  3. Read the source and extract wiki-worthy knowledge
  4. Choose the affected pages
  5. Update the pages
  6. Update the registry and index
  7. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 3cd87d6. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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.

  • Compatibility

    Requires spec-kit project structure with .specify/ directory

    From compatibility in the SKILL.md frontmatter.

Context cost

Speckit Wiki Ingest loads about 1.2k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 670 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from haru/redmine_ai_helper at commit 3cd87d6, republished under its MIT licence (© haru). 670 words, ~1,218 tokens.

Download SKILL.mdSave it as .claude/skills/speckit-wiki-ingest/SKILL.md (or your agent's skills folder).
name
speckit-wiki-ingest
description
Ingest a source (feature artifacts, file, or URL) and update the related wiki pages with citations
compatibility
Requires spec-kit project structure with .specify/ directory
metadata.author
formin
metadata.source
extension:wiki
user-invocable
true
disable-model-invocation
false

Wiki Ingest Skill

Ingest a Source into the Wiki

The only operation that writes knowledge into the wiki. Reads one source, extracts what is worth keeping, and folds it into the related pages — with a citation on every claim, cross-links between pages, and a hard cap on how many pages one ingest may touch.

This is the ingest operation of Karpathy's LLM Wiki pattern: the human curates sources; the LLM does the bookkeeping — summarizing, cross-referencing, and keeping related pages consistent — so knowledge compounds instead of being rediscovered from scratch on every question.

User Input

text
$ARGUMENTS

$ARGUMENTS names the source: a file path, a directory, or a URL. If empty, default to the active feature's artifacts — research.md plus the decision sections of plan.md (resolve the feature directory from the current git branch, else the most recently modified directory under specs/). key=value tokens (e.g. max_pages_per_ingest=6) are configuration overrides.

Steps

1. Resolve configuration and the wiki

Load configuration exactly as /speckit.wiki.init does (config file → SPECKIT_WIKI_* env vars → key=value arguments). If WIKI_DIR/SCHEMA.md does not exist, create the skeleton first per the init command's step 3, and say so in the report. Read SCHEMA.md — its rules override this prompt's defaults where they conflict.

2. Register the source

In sources.md, dedup by normalized path/URL:

  • New source → append the next S-id with type (feature-artifact, file, url), today's date in both date columns, and an empty pages list.
  • Known source → update Last ingested only. Re-ingesting is the normal way to refresh the wiki after a source changed.
3. Read the source and extract wiki-worthy knowledge

Read the source once. Extract discrete items worth keeping — knowledge that outlives the source's moment:

  • decisions and their rejected alternatives
  • constraints, limits, and gotchas that will bite again
  • domain concepts and how this project uses them
  • how a component actually works (when the source proves it)
  • verified external facts

Skip transient status ("tests currently failing"), speculation, and anything already on a page unchanged. Summarize — never paste bulk source content.

4. Choose the affected pages

Load INDEX.md (never all pages). Map each extracted item to an existing page by topic, or to a new page typed per the schema's page-type table. Hard cap: at most ingest.max_pages_per_ingest pages created or updated in one run. If items would exceed the cap, ingest the most valuable ones and list the remainder in the report as a suggested follow-up ingest.

Show full SKILL.md (279 more words)Show less
5. Update the pages

Create pages/ if missing. For each affected page (read only those):

  • Merge the new items where they belong; update statements the source has made stale.
  • Cite the source on every new or changed claim: … (S007). When ingest.require_citations is true, no uncited claim may be written.
  • If the new source contradicts an existing cited claim, keep both under a marker — > ⚠ conflict: S002 says X; S007 says Y — and flag it in the report. Never silently overwrite a cited claim.
  • Cross-link: link new pages from the related existing pages you touched, and back. A new page unreachable from any other page is an orphan — avoid creating one.
  • Update frontmatter: updated to today, sources to include the S-id.
  • If a page exceeds ingest.page_max_words, split it per the schema and link both halves.
6. Update the registry and index
  • sources.md: fill the source's Pages touched with the page filenames.
  • INDEX.md: add/adjust one line per created or renamed page, grouped by type, and remove the "No pages yet" placeholder if present.
7. Report
  • The source and its S-id (new or re-ingested).
  • Pages created and updated — one line each on what changed.
  • Conflicts flagged (if any) and items deferred by the page cap (if any).
  • Next step: /speckit.wiki.lint if conflicts were flagged, otherwise /speckit.wiki.query <question> to test what the wiki now knows.

Guardrails

  • Sources are immutable — never edit the ingested file, and never edit spec.md, plan.md, or tasks.md from this command.
  • Respect the page cap and word cap; splitting and deferring beat sprawling.
  • Every claim written carries a source citation; conflicts are kept visible, not resolved by deletion.
  • Do not load every page "for context" — INDEX plus the affected pages only.

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

Files

Just SKILL.md in .claude/skills/speckit-wiki-ingest of haru/redmine_ai_helper.

Open the folder on GitHubat commit 3cd87d6

Compare with similar skills

Speckit Wiki Ingest 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.

Speckit Wiki Ingest compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Speckit Wiki Ingest this skillharu/redmine_ai_helper106—~1.2kAutomated safety check: PassMIT
Wiki Queryrohitg00/pro-workflow2.9k—~554Automated safety check: PassNone
Wiki Context PackAr9av/obsidian-wiki3.5k—~752Automated safety check: NotesMIT
Llmwikiatomicstrata/llm-wiki-compiler2.2k—~814Automated safety check: PassMIT
Karpathy LLM WikiAstro-Han/karpathy-llm-wiki2.5k—~3.6kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone

Similar skills

  • Wiki Query

    rohitg00/pro-workflow

    Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub stars~554 tokensUpdated 12 days ago
    Knowledge ManagementAuto-check passed

  • Wiki Context Pack

    Ar9av/obsidian-wiki

    Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task.

    3.5k GitHub stars~752 tokensUpdated today
    Knowledge ManagementAuto-check: notes

  • Llmwiki

    atomicstrata/llm-wiki-compiler

    Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation.

    2.2k GitHub stars~814 tokensUpdated yesterday
    Knowledge ManagementAuto-check passed

  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

    A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.

    2.5k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed

  • Wiki Builder

    rohitg00/pro-workflow

    Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.

    2.9k GitHub stars~1k tokensUpdated 12 days ago
    Knowledge ManagementAuto-check passed

More from haru/redmine_ai_helper

All 23 skills in this repo

  • Commit

    haru/redmine_ai_helper

    Stage the current changes and create a git commit with a properly formatted English message.

    106 GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

  • Create Pull Request

    haru/redmine_ai_helper

    Create a pull request from the current branch. An agent skill from haru/redmine_ai_helper.

    106 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Create Release Branch

    haru/redmine_ai_helper

    Create a release branch for a given version. An agent skill from haru/redmine_ai_helper.

    106 GitHub stars~599 tokensUpdated today
    Auto-check passed

  • Record Code Review Feedback

    haru/redmine_ai_helper

    Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis.

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

  • Record Spec Feedback

    haru/redmine_ai_helper

    Record a user's correction of an AI-written specification in docs/spec-feedback/ as an append-only entry with root-cause analysis.

    106 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Qlty Check

    haru/redmine_ai_helper

    Code quality checks, formatting, and metrics via qlty CLI. An agent skill from haru/redmine_ai_helper.

    106 GitHub starsUsed in 2 repos~628 tokens
    Auto-check passed

Categories

Questions about Speckit Wiki Ingest

What does Speckit Wiki Ingest do?

Ingest a source (feature artifacts, file, or URL) and update the related wiki pages with citations. Speckit Wiki Ingest is an agent skill from haru/redmine_ai_helper.

When should I use Speckit Wiki Ingest?

Speckit Wiki Ingest fits situations like: tasks that involve LLM wikis; tasks that involve Spec-driven development; tasks that involve Citation management.

How do I install Speckit Wiki Ingest in Claude Code?

Run `npx skills add haru/redmine_ai_helper --skill speckit-wiki-ingest -a claude-code`. Or copy the skill folder (.claude/skills/speckit-wiki-ingest in haru/redmine_ai_helper) into .claude/skills/speckit-wiki-ingest in your project. Claude Code loads it when a task matches its description.

How do I install Speckit Wiki Ingest in Codex?

Run `npx skills add haru/redmine_ai_helper --skill speckit-wiki-ingest -a codex`. Or copy the skill folder (.claude/skills/speckit-wiki-ingest in haru/redmine_ai_helper) into .agents/skills/speckit-wiki-ingest in your project. Codex loads it when a task matches its description.

Can I use Speckit Wiki Ingest 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 haru/redmine_ai_helper --skill speckit-wiki-ingest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/speckit-wiki-ingest, .gemini/skills/speckit-wiki-ingest, .github/skills/speckit-wiki-ingest and .opencode/skills/speckit-wiki-ingest in your project.

What does Speckit Wiki Ingest need to run?

SKILL.md names no scripts, command-line tools or credentials: Speckit Wiki Ingest is instructions for the agent only. Compatibility (from SKILL.md): Requires spec-kit project structure with .specify/ directory.

Does Speckit Wiki Ingest 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 Speckit Wiki Ingest 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. Review the folder before installing.

What licence does Speckit Wiki Ingest use?

Speckit Wiki Ingest 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 Speckit Wiki Ingest use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Speckit Wiki Ingest?

Skills that share tags, products or a category with Speckit Wiki Ingest: Wiki Query (rohitg00/pro-workflow, 2.9k stars), Wiki Context Pack (Ar9av/obsidian-wiki, 3.5k stars), Llmwiki (atomicstrata/llm-wiki-compiler, 2.2k stars) and Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Speckit Wiki Ingest?

haru (a GitHub user) maintains it in haru/redmine_ai_helper, which has 106 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 10, 2026.

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