levels-status
Skill3 starsChanged 32 days agoMITView on GitHub
Show one dashboard of every layer's current and target level, open gaps and pending actions, read from the project's LEVELS.md. Read-only and cheap. Use when the user runs /levels-status or asks where the project stands across the level skills.
In this repository16 other files it gives its agents.
- backend-levelSkill
- code-levelSkill
- data-levelSkill
- design-levelSkill
- docs-levelSkill
- idea-levelSkill
- levels-helpSkill
- levels-nextSkill
- levelsSkill
- perf-levelSkill
- pitch-levelSkill
- restyle-levelSkill
- security-levelSkill
- ship-levelSkill
- test-levelSkill
- ux-levelSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Read-only. This skill changes no file, spawns no agent and starts no other skill.
- Very specific: line 15
Read LEVELS.md in the project root.
- Distinctive: line 16
If the arguments name a layer, show that layer's section in full and stop.
- Distinctive: line 19
Waiting on you: every pending live step, manual action or unanswered question recorded in any section, with the layer it belongs to.
- Very specific: line 23
Flow: if the block has a flow: row, show it on its own line (current phase, skills left) and keep it out of the table.
- Very specific: line 26
If the levels block and a section disagree, show both values and say they disagree.
≈ “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
Levels status
Arguments: $ARGUMENTS
Read-only. This skill changes no file, spawns no agent and starts no other skill.
- Read
LEVELS.mdin the project root. If it does not exist, say so and list the level skills that can create it, one line each, then stop. - If the arguments name a layer, show that layer's section in full and stop.
- Otherwise print, in this order:
- A table from the levels block: layer, current level, target level, distance to target, open gaps, date last updated (the
Date:line of the layer's section). Sort by distance to target, largest first. - Waiting on you: every pending live step, manual action or unanswered question recorded in any section, with the layer it belongs to.
- Accepted risks: each one with its reason.
- Stale: any layer not updated in over 30 days, or older than the last commit in the project.
- Not yet run: level skills with no row in the block.
- Flow: if the block has a
flow:row, show it on its own line (current phase, skills left) and keep it out of the table. It is written bylevelsand is not a layer.
- A table from the levels block: layer, current level, target level, distance to target, open gaps, date last updated (the
- End with one line: the layer furthest from its target. Do not recommend an action.
levels-nextdoes that.
If the levels block and a section disagree, show both values and say they disagree. Do not guess which is right.
Report only what the file says. Never estimate a level that has not been recorded.
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.