Daily Journal
ravila4/claude-adhd-skills
Draft, organize, or update development journal entries. An agent skill from ravila4/claude-adhd-skills.
Compile literature, meeting notes, session logs, and code findings into a structured per-project knowledge wiki.
Install Compile Knowledge
$ npx skills add flonat/flonat-research --skill compile-knowledge -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install flonat/flonat-research compile-knowledge --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/flonat/flonat-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/compile-knowledge .claude/skills/compile-knowledge && 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 "compile-knowledge" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/compile-knowledge into .claude/skills/compile-knowledge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compile-knowledge", 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/flonat/flonat-research/tree/main/skills/compile-knowledgeType 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 flonat/flonat-research --skill compile-knowledge -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install flonat/flonat-research compile-knowledge --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/compile-knowledge .agents/skills/compile-knowledge && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "compile-knowledge" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/compile-knowledge into .agents/skills/compile-knowledge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compile-knowledge", 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 flonat/flonat-research --skill compile-knowledge -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install flonat/flonat-research compile-knowledge --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/compile-knowledge .cursor/skills/compile-knowledge && 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 "compile-knowledge" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/compile-knowledge into .cursor/skills/compile-knowledge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compile-knowledge", 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/flonat/flonat-research.git --path skills/compile-knowledge--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 flonat/flonat-research --skill compile-knowledge -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install flonat/flonat-research compile-knowledge --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/compile-knowledge .gemini/skills/compile-knowledge && 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 "compile-knowledge" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/compile-knowledge into .gemini/skills/compile-knowledge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compile-knowledge", 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 flonat/flonat-research compile-knowledgeInstalls 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 flonat/flonat-research --skill compile-knowledge -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/compile-knowledge .github/skills/compile-knowledge && 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 "compile-knowledge" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/compile-knowledge into .github/skills/compile-knowledge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compile-knowledge", 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 flonat/flonat-research --skill compile-knowledge -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install flonat/flonat-research compile-knowledge --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/compile-knowledge .opencode/skills/compile-knowledge && 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 "compile-knowledge" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/compile-knowledge into .opencode/skills/compile-knowledge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compile-knowledge", 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.
Facts
- Skill name
compile-knowledge- GitHub stars
- 145
- Token cost
- ~2.5k tokens
- SKILL.md length
- 921 words
- Files
- 1
- Skills in repo
- 83
- Repo updated
- First seen
- Licence
- MIT
At a glance
Compile literature, meeting notes, session logs, and code findings into a structured per-project knowledge wiki.
- Works in 6 steps: Locate Project and Scan Sources → Identify Concepts → Compile Articles → …
- Project evidence is scattered across source records and needs synthesis into durable articles
- SKILL.md covers When to Use, When NOT to Use, Architecture and Modes, plus 8 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Compile Knowledge is an agent skill from flonat/flonat-research. Compile literature, meeting notes, session logs, and code findings into a structured per-project knowledge wiki. Use when project evidence is scattered across source records and needs synthesis into durable articles. Not for promoting existing articles into the global vault wiki; use $wiki-grow.
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Productivity & Automation, covering Meeting notes and agendas. The repository describes itself as: Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows. The licence is MIT.
When your agent uses it
- Project evidence is scattered across source records and needs synthesis into durable articles
- Tasks that involve Meeting notes and agendas
Example prompts
- “/compile-knowledge”
Requirements
- Pre-approved tools (allowed-tools): Read, Glob, Grep, Write, Edit, Bash(mkdir*), Agent
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit da27600. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGlobGrepWriteEditBash(mkdir*)Agent
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
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
Compile Knowledge loads about 2.5k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 921 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.
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 flonat/flonat-research at commit da27600, republished under its MIT licence (© flonat). 921 words, ~2,530 tokens.
Download SKILL.mdSave it as
.claude/skills/compile-knowledge/SKILL.md (or your agent's skills folder).- name
- compile-knowledge
- description
- Compile literature, meeting notes, session logs, and code findings into a structured per-project knowledge wiki. Use when project evidence is scattered across source records and needs synthesis into durable articles. Not for promoting existing articles into the global vault wiki; use $wiki-grow.
- allowed-tools
- Read, Glob, Grep, Write, Edit, Bash(mkdir*), Agent
- argument-hint
- [project-path] [--autonomous|-y] (no args = CWD)
Compile Knowledge
Reads raw inputs from a project and compiles/updates a
knowledge/wiki — a collection of LLM-maintained markdown articles that synthesise everything known about the project's domain.
When to Use
- After a literature review to consolidate findings
- After a series of sessions on a project to build up the knowledge base
- When starting work on a project and wanting to understand the state of knowledge
- Periodically to keep the knowledge wiki fresh
When NOT to Use
- For structural project audits — use an installed research-project audit workflow
- For atlas topic metadata — that stays in the vault
- For session-specific notes — those go in
log/
Architecture
The knowledge wiki lives at <project>/knowledge/:
knowledge/
_index.md ← auto-maintained index with brief summaries
concept-name.md ← one article per concept
concept-name-2.mdThe LLM owns this directory. the user rarely edits it directly. The value is in the compilation — connecting dots across sources that no single document contains.
Modes
| Mode | Invocation | Behaviour |
|---|---|---|
| Interactive (default) | compile-knowledge [project-path] | Phases run normally; mid-run nudges allowed where useful; end-of-run summary requires no confirmation but the user can inspect output and re-run. |
| Autonomous | compile-knowledge [project-path] --autonomous (or -y) | End-to-end run with zero prompts. All decisions take the documented default. Single end-of-run summary is the only user-facing output. Used by the Saturday wiki-grow cron to refresh project knowledge before the wiki-promotion pass. |
Autonomous-mode defaults (every choice point)
When --autonomous / -y is set, the skill takes these defaults silently:
| Choice point | Default |
|---|---|
| Project path unresolved (CWD not a research project) | Fail with a single one-line error to stderr. Do not prompt for path. |
| No sources found in Phase 1 | Skip remaining phases; emit No sources to compile. and exit clean. |
| Concept granularity uncertain | Prefer 400-600 word articles, specific scope over generic. Err on the side of fewer, sharper concepts. |
| Article exists but scope shifted | Update in place when overlap ≥50% with new finding; create new article only when genuinely orthogonal. |
| Contradictions between sources | Flag explicitly in prose ("Source A says X, Source B says Y") — never silently pick a side. |
| Source can't be parsed (encoding, malformed) | Log to the Gaps section in _index.md; continue with remaining sources. |
| Atlas topic match in Phase 5 is 0 or >1 | Skip silently (already documented in Phase 5.4). |
| Article exceeds 1000 words | Split into two articles by sub-theme; never truncate findings. |
Autonomous-mode does NOT change
- Knowledge-article quality contract: every claim must cite its source. Unverifiable claims get
[UNVERIFIED]per the global rule. - Phase 5 atlas frontmatter sync: still writes
knowledge_last_compiledon every run. - Read-only access to
data/raw/per the global data-sensitivity rule. - Per-project
MEMORY.md/CLAUDE.mdare NEVER edited by this skill.
If any of the above fails (e.g. an [UNVERIFIED] flag couldn't be applied due to a write error), include the failure in the end-of-run summary rather than blocking.
Phase 1: Locate Project and Scan Sources
- Resolve project path (CWD or argument)
- Scan for raw inputs:
| Source | Location | What to extract |
|---|---|---|
| Literature reviews | docs/literature-review/ | Paper summaries, key findings, research gaps |
| Meeting notes | meeting-notes/ or to-sort/ recaps | Decisions, insights, action items |
| Session logs | log/ | Research progress, discoveries, pivots |
| MEMORY.md | Project root | Notation, decisions, pitfalls, domain corrections |
| Atlas topic file | ~/vault/atlas/<theme>/<slug>.md | Status, connected topics, research questions |
| Code README/comments | code/, src/ | What the code does, key algorithms |
| Paper sections | paper-*/paper/*.tex | Current argument structure, contributions |
.context/project-recap.md | .context/ | Project overview, current state |
- Report source inventory:
Sources found: Literature: 12 papers in docs/literature-review/ Sessions: 8 logs in log/ Memory: 14 entries in MEMORY.md Paper: 3 sections drafted Code: 2 scripts in code/python/
Show full SKILL.md (382 more words)Show less
Phase 2: Identify Concepts
Read all sources and extract a concept list — the key ideas, methods, datasets, theories, and phenomena that the project deals with.
Concept granularity: Each concept should be specific enough to warrant its own article (~200-1000 words). Too broad = useless summary. Too narrow = fragmented.
Examples of good concepts:
mechanism-design-for-audits.md(a specific method applied to the project's domain)collusion-detection-methods.md(a family of techniques relevant to the project)eu-ets-carbon-market.md(institutional context)callaway-santanna-estimator.md(a specific estimator used)
Examples of bad concepts:
introduction.md(too structural — that's the paper's job)regression.md(too generic)table-3.md(too narrow)
Phase 3: Compile Articles
For each concept, create or update knowledge/<concept-name>.md:
# <Concept Name>
> One-sentence summary of what this concept is and why it matters to the project.
## Key Findings
- Bullet points synthesising what is known from all sources
- Each finding should cite its source: (Author Year) or (session log YYYY-MM-DD)
- Flag contradictions: "Source A says X, but Source B says Y"
## Open Questions
- What is not yet known or resolved
- Questions that emerged from the literature but aren't answered
- Methodological choices that remain open
## Sources
| Source | Type | Key contribution |
|--------|------|-----------------|
| Author (Year) | Paper | Finding X |
| Session 2026-03-15 | Log | Discovered Y |
| MEMORY.md | Decision | Chose Z because... |
## Related
- [[other-concept]] — how they connect
- Atlas: `<topic-slug>` — link to atlas topic if relevantRules:
- Be specific and factual — no filler prose
- Cite sources for every claim
- Flag contradictions explicitly rather than silently picking one side
- Keep articles between 200-1000 words
- Use
[[wikilink]]syntax for cross-references between knowledge articles
Phase 4: Update Index
Write or update knowledge/_index.md:
# Knowledge Index
> Auto-maintained by `compile-knowledge`. Last updated: YYYY-MM-DD.
> N articles, ~X words total.
## Articles
| Article | Summary | Sources | Last updated |
|---------|---------|---------|-------------|
| [Concept A](concept-a.md) | One-line summary | 3 papers, 2 sessions | YYYY-MM-DD |
| [Concept B](concept-b.md) | One-line summary | 1 paper, 1 decision | YYYY-MM-DD |
## Source Coverage
| Source type | Count | Compiled into articles |
|------------|-------|----------------------|
| Papers | 12 | 10 (2 not yet compiled) |
| Session logs | 8 | 5 (3 not yet compiled) |
| Memory entries | 14 | 12 |
## Gaps
- [List concepts that should exist but don't yet]
- [Sources not yet compiled into any article]Phase 5: Atlas frontmatter sync
After writing _index.md, also update the atlas topic frontmatter so the
project's compile date is discoverable from outside the project (e.g. by
session-close, the wiki promotion cron, atlas-workspace).
- Resolve the atlas topic:
grep -rl "project_path:.*$(basename "$PWD")" ~/vault/atlas/ - If a single match is found, set or update the frontmatter field
knowledge_last_compiled: YYYY-MM-DD(today's date in UTC). - If the field already exists, overwrite. If absent, insert before the
closing
---. - If 0 or >1 atlas topic files match, skip silently and log to the
end-of-run summary (
Atlas frontmatter sync: skipped — N matches).
The field is consumed by:
session-close(info-only freshness line viareferences/research-checks.md§ 18)- The Saturday
wiki-growcron (uses the date to schedule re-promotion) - atlas-workspace (could surface in topic-page metadata row in future)
Phase 6: Incremental Mode
When run on a project that already has knowledge/:
- Detect new sources since last compilation (check
_index.mdlast-updated date vs source file modification dates) - Only process new/modified sources
- Update existing articles with new findings (append, don't rewrite)
- Create new articles only for genuinely new concepts
- Update
_index.md - Update atlas frontmatter
knowledge_last_compiled(Phase 5)
Report:
Knowledge updated:
Articles updated: 3 (concept-a, concept-b, concept-c)
Articles created: 1 (new-concept)
Sources processed: 4 new since last compile
Total: N articles, ~X wordsOutput
Print summary after compilation:
Knowledge compiled for <project-name>:
Articles: N (M new, K updated)
Total words: ~X
Sources compiled: Y / Z total
Gaps: [list any uncompiled sources]
Index: knowledge/_index.mdCross-References
| Skill | Relationship |
|---|---|
store-insight | Lightweight single-finding filer — called by other skills |
knowledge-lint | Checks compiled knowledge for inconsistencies |
literature (pipeline mode) | Produces literature reviews that feed into compilation |
session-close | Extracts session insights and files them via store-insight |
© flonat, 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 skills/compile-knowledge of flonat/flonat-research.
Open the folder on GitHubat commit da27600
Compare with similar skills
Compile Knowledge 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 |
|---|---|---|---|---|---|---|
| Compile Knowledge this skillflonat/flonat-research | 145 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Daily Journalravila4/claude-adhd-skills | 157 | — | ~2.5k | Automated safety check: Pass | MIT | |
| GranolaArtemXTech/claude-code-obsidian-starter | 224 | — | ~905 | Automated safety check: Pass | None | |
| Ingestcoreyhaines31/makerskills | 848 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Paperclip Distillpaperclipai/paperclip | 99k | — | ~2.8k | Automated safety check: Pass | MIT | |
| Meeting SummarySourceWeft/SourceWeft | 166 | — | ~197 | Automated safety check: Pass | Custom licence |
Similar skills
Granola
ArtemXTech/claude-code-obsidian-starter
Query and sync Granola meetings to Obsidian vault. An agent skill from ArtemXTech/claude-code-obsidian-starter.
Ingest
coreyhaines31/makerskills
When you paste raw human input — a call transcript (Grain, Zoom, Granola, Fathom), a text or email from a client/partner/friend, a voice-memo dump, or meeting notes — and want it converted into…
Paperclip Distill
paperclipai/paperclip
A skill your agent uses when an operation issue is a Paperclip cursor-window, distill, or backfill.
Meeting Summary
SourceWeft/SourceWeft
A skill your agent uses when summarizing meeting notes, extracting decisions, and preparing action items.
Daily Update
Ar9av/obsidian-wiki
Run or configure the daily wiki maintenance cycle: check source freshness, refresh the index and hot.md, and manage its scheduled 9 AM launchd/systemd/cron reminder.
More from flonat/flonat-research
All 83 skills in this repoLatex Posters
flonat/flonat-research
Create a large-format academic poster in LaTeX using beamerposter, tikzposter, or baposter.
Skill Creator
flonat/flonat-research
Create, revise, and evaluate reusable AI workflow skills, including trigger-quality tests.
DOCX
flonat/flonat-research
Create, read, edit, or convert Microsoft Word documents while preserving professional document structure.
PDF
flonat/flonat-research
Read, create, combine, split, rotate, OCR, watermark, secure, or extract content from PDF files.
Init Project Orchestration
flonat/flonat-research
Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex.
Pre Commit Audit
flonat/flonat-research
Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers.
Related
Questions about Compile Knowledge
What does Compile Knowledge do?
Compile literature, meeting notes, session logs, and code findings into a structured per-project knowledge wiki. Compile Knowledge is an agent skill from flonat/flonat-research. Compile literature, meeting notes, session logs, and code findings into a structured per-project knowledge wiki.
When should I use Compile Knowledge?
Compile Knowledge fits situations like: project evidence is scattered across source records and needs synthesis into durable articles; tasks that involve Meeting notes and agendas.
How do I install Compile Knowledge in Claude Code?
Run `npx skills add flonat/flonat-research --skill compile-knowledge -a claude-code`. Or copy the skill folder (skills/compile-knowledge in flonat/flonat-research) into .claude/skills/compile-knowledge in your project. Claude Code loads it when a task matches its description.
How do I install Compile Knowledge in Codex?
Run `npx skills add flonat/flonat-research --skill compile-knowledge -a codex`. Or copy the skill folder (skills/compile-knowledge in flonat/flonat-research) into .agents/skills/compile-knowledge in your project. Codex loads it when a task matches its description.
Can I use Compile Knowledge 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 flonat/flonat-research --skill compile-knowledge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compile-knowledge, .gemini/skills/compile-knowledge, .github/skills/compile-knowledge and .opencode/skills/compile-knowledge in your project.
What does Compile Knowledge need to run?
SKILL.md names no scripts, command-line tools or credentials: Compile Knowledge is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep, Write, Edit, Bash(mkdir*), Agent.
Does Compile Knowledge 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 Compile Knowledge 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 Compile Knowledge use?
Compile Knowledge 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 Compile Knowledge use?
About 2.5k tokens (SKILL.md is roughly 10k 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 Compile Knowledge?
Skills that share tags, products or a category with Compile Knowledge: Daily Journal (ravila4/claude-adhd-skills, 157 stars), Granola (ArtemXTech/claude-code-obsidian-starter, 224 stars), Ingest (coreyhaines31/makerskills, 848 stars) and Paperclip Distill (paperclipai/paperclip, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Compile Knowledge?
flonat (a GitHub user) maintains it in flonat/flonat-research, which has 145 GitHub stars. The repository holds 83 skills in this directory. The repository was last updated on September 29, 2026.
Source: flonat/flonat-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.