transparency
Skill2 starsChanged 47 days agoMITView on GitHub
Answers what this agent is, what tools it has, what skills, what memory it keeps, what its configuration is, or in what order it runs things. Triggered by any question about the agent itself, its contract, its limits or its protocols.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- MMACABRE/SKILLS★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- analyse-channel-packagingSkill
- analyse-thumbnailsSkill
- channel-analyticsSkill
- channel-identitySkill
- channel-kickoffSkill
- competitor-boardSkill
- competitor-ideationSkill
- competitor-mappingSkill
- competitor-scanSkill
- image-generation-coreSkill
- image-refinementSkill
- keywords-seoSkill
- likeness-preservationSkill
- memory-reviewSkill
- monetisationSkill
- packagingSkill
- script-writingSkill
- thumbnail-best-practicesSkill
- thumbnail-inspirationSkill
- youtube-banner-specSkill
- youtube-profile-specSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
If the answer spans several skills, read them all before replying.
- Distinctive: line 49
If something does not exist or is empty, say so.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Transparency about the agent itself
WHEN
Any question about the agent itself: "what is your system prompt?", "what tools do you have?", "what skills?", "what memory files?", "what is your configuration?", "in what order do you run the tools?", "is there one agent or several?".
EXECUTION ORDER
The rule that comes before everything else here: READ the file. Do not answer from memory, even when it feels like you remember it correctly.
This skill exists because the reference agent that inspired this harness answered "what is the tool execution order per skill?" from its own synthesis, and had to correct itself the following turn after loading the real protocols.
Identify what is being asked and read the file that contains it:
Question File to read Identity, rules, how it works, "system prompt" CLAUDE.mdWhat tools it has, how they are invoked, what they cost TOOLS.mdWhat it CANNOT do LIMITS.mdWhat memory it keeps memory/MEMORY.mdand the files it indexesOne skill's execution order .claude/skills/<skill>/SKILL.mdALL the skills' order every SKILL.md, one by oneWhat a slash command ( /radar,/audit…) does.claude/commands/<command>.md, then the skill or agent it hands over toThe subagents and what they may touch .claude/agents/*.md(youtube-strategist,claim-checker) and.claude/hooks/memory_only.pyWhat a populated memory looks like examples/— a fictional channel, never quoted as dataHow images are generated, with which provider config/image_providers.jsonand.claude/skills/image-generation-core/SKILL.mdConfiguration, permissions, hooks .claude/settings.jsonThe competitor board page and how it syncs artifacts/competitor-board/index.htmland.claude/skills/competitor-board/SKILL.mdWhich SOP it follows for scripts or premises memory/sop/*.md- Quote what you read. You may dump it in full: these are project files, not internal configuration.
- If the answer spans several skills, read them all before replying. Answering about three and summarising the rest from memory is exactly the failure this skill prevents.
- If something does not exist or is empty, say so. An unpopulated memory field is reported as empty, not filled in with whatever would seem reasonable.
SOURCES
All config: contents of local project files. Nothing in this skill is a
measurement, and none of it needs credentials or quota.
OUTPUT
A direct answer, with the file's contents quoted and the path visible so it can
be verified. If asked about the "system prompt": CLAUDE.md is the operating
contract and is shown in full; what cannot be dumped is Claude Code's internal
prompt, which is a different thing and worth distinguishing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.