Claudeception is a skill whose whole job is to write skill files for you. You finish a piece of work, ask it to save what you learned, and it hands you back a clean, reusable file: the problem, when to use it, and the steps you actually took. It is open source, and the download is a little further down.
To turn a Claude session into a reusable skill, download blader's open-source Claudeception skill, upload it into Claude, then at the end of a session say "save this as a skill". It reviews what you did and, if the work was worth keeping, writes a SKILL.md you save and reuse. The core works with no terminal; you do the final save by hand.
What it does, and what it does not
It is worth being clear, because the name sounds grander than the job. Claudeception is not an autopilot. It does not keep working after you stop, it does not act on its own, and it does not make Claude generally smarter. What it does is narrow and genuinely useful: at the end of a session, it looks back over what you and Claude worked out, decides whether any of it is worth keeping, and if so writes it up as a structured skill file. Then it stops. The only way Claude is smarter next time is that you load the skill it wrote. Think of it as Claude taking notes on the thing you just solved, not as Claude running loose.
Get the skill
This is blader's real file, not a copy I have written. Download it, and you have the whole thing.
The skill that reviews a finished session and writes the method up as a reusable SKILL.md. Download it, then follow the steps below to use it.
Claudeception is by blader and released under the MIT licence. Copyright (c) 2024 Claude Code. Source, full licence and the terminal install: github.com/blader/Claudeception. Full credit to blader, whose work this guide is built on.
How to use it, no terminal needed
The whole thing works by uploading the file into Claude and then just talking to it. Here is the path a beginner can follow start to finish.
- Upload the skill into Claude. In Cowork, go to Customize, Skills and upload the
claudeception.mdfile you downloaded. If you are in a normal chat instead, attach the file at the start. That is the only setup. - Do a real job with Claude. This only pays off after you have actually worked something out together: a bug that took a few tries, a format you kept correcting, a way of doing a task that finally clicked. A skill is a record of a win, so you need the win first.
- At the end, ask it to save what you learned. Say "save this as a skill", or "what did we learn?". It reviews the session against its own bar and, if the work is worth keeping, writes you a full SKILL.md: a name, when to use it, the steps, and the traps. If nothing is worth keeping, it says so and saves nothing, which is the point.
- Save the file it gives you, and reuse it. Copy the skill file it wrote into wherever you keep your skills, then upload it the next time the same kind of job comes up, or trigger it by name. From then on Claude starts from your method, not from a blank page.
The honest bits
- The upload version does the thinking, not the housekeeping. Uploaded into Claude, the skill will happily review a session and draft you a clean skill file. What it will not do on that path is the automatic tidying: scanning your existing skills so you do not save a duplicate, filing the new skill into the right folder itself, and nudging you every session. Those parts need Claude Code in a terminal, and blader's repo has that one-command install if you want the full automatic version. Without it, you just save the file by hand, which takes seconds.
- Most sessions should not become a skill. The bar, which is the skill's own, is four words: reusable, non-trivial, specific, verified. If the thing you did was a one-off, or was obvious from the start, saving it grows a list you stop trusting. A short list of skills you actually run beats a long one you scroll past. The skill is built to refuse, and that refusal is a feature.
- Read the skill before you rely on it. It writes the file from what happened in the session, so a wrong turn can end up in there. Skim the steps once. It is a note to your future self, and it is worth the thirty seconds to make sure it is a good one.
If a saved skill does not fire next time
The most common snag is not a broken skill, it is one that sits there. You start a similar job and Claude solves it from scratch instead of reaching for the file. Almost always that is the description line: Claude matches your words against it, so if you phrased the request differently this time, nothing matches. Open the skill file, add the words you actually just typed to the description, and it will catch next time. You can always trigger it by name meanwhile, which never depends on the wording.
One step further, when you are ready
Saving a method is the first habit. The next, for later, is having Claude update a skill each time you correct it, so the same note never gets made twice. An independent take worth knowing about is claude-reflect-system, built around "correct once, never again": it watches for the moments you fix Claude's work and folds that fix back into the skill. You do not need it to start. It is the direction this goes once a skill or two is earning its keep.
claude-reflect-system is an open-source (MIT) project: github.com/haddock-development/claude-reflect-system.
Do it on your very next win
It comes down to one habit. Download blader's skill above, upload it once, and the next time you and Claude finally crack something, do not just close the tab. Say "save this as a skill", let it write the file, and save it. Then try triggering it on the next similar job and watch it pick up where you left off. A tool you keep sharpening beats one you keep re-explaining.
A couple of quick questions
Does it make Claude work on its own or get smarter?
No. It is not an autopilot and does not keep running. At the end of a session it writes up what you worked out as a reusable skill file, then stops. Claude only reuses it if you load that skill again later.
Do I need a terminal?
No, not for the main job. Upload the file and it reviews a session and writes you a skill when you ask. Only the automatic housekeeping (duplicate checks, saving for you, a reminder every session) needs Claude Code in a terminal.
Should every session become a skill?
No. Only when the work was reusable, non-trivial, specific, and verified. Most sessions do not clear that bar, and the skill will save nothing rather than clutter your list.