modify
Skill2 starsChanged 3 months agoMITView on GitHub
Copy a catalog bundle to modify/ and adapt one script per session.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- CraftOS-dev/Agent-Apptheir 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
- CraftOS-dev/Agent-App★ 9same 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 repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- acceptSkill
- ask-mattSkill
- buildSkill
- claude-handoffSkill
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- explainSkill
- git-guardrails-claude-codeSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- loop-meSkill
- matlab-performance-optimizerSkill
- matlabSkill
- matstudylab-bootstrapSkill
- migrate-to-shoehornSkill
- newSkill
- prototypeSkill
- researchSkill
- resolving-merge-conflictsSkill
- scaffold-exercisesSkill
- setup-matt-pocock-skillsSkill
- setup-pre-commitSkill
- setup-ts-deep-modulesSkill
- tddSkill
- teachSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wait-whatSkill
- wayfinderSkill
- wizardSkill
- writing-beatsSkill
- writing-for-agentsSkill
- writing-fragmentsSkill
- writing-great-skillsSkill
- writing-shapeSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 4 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Read LORE.md, AGENTS.md, docs/spec.md, docs/matlab-guidelines.md, and CONTEXT.md before acting.
- Very specific: line 13
Read and execute .agents/skills/matstudylab-bootstrap/SKILL.md before any other step.
- Distinctive: line 14
Do not proceed until bootstrap completes (skip, setup/update, or warn-and-continue).
- Distinctive: line 22
If subscripts are involved → ask whether to edit together or one file per session.
- Very specific: line 40
Run .agents/skills/grill-me/SKILL.md on what changes — behavior, plots, outputs, units — not the whole script from scratch.
- Very specific: line 42
If base companion .md is missing or incomplete, run the full /new checklist first.
- Very specific: line 48
Read and apply docs/agents/matlab-skills-gate.md before editing any .m file.
- Very specific: line 53
Update .md history / relevant sections with each meaningful change.
- Distinctive: line 59
Ask whether to promote now or keep iterating:
- Very specific: line 69
Never: write to codes/ except via /accept or confirmed /build.
- Very specific: line 70
Write only under modify/ after the mandatory copy step.
- Distinctive: line 71
Never change units without warning.
≈ “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
Adapt a catalog bundle by copying codes/<type>/<bundle>/ to modify/<type>/<bundle>/ before any edit. Never edit codes/ in situ.
Read LORE.md, AGENTS.md, docs/spec.md, docs/matlab-guidelines.md, and CONTEXT.md before acting.
Step 0 — Bootstrap (mandatory)
Read and execute .agents/skills/matstudylab-bootstrap/SKILL.md before any other step.
Do not proceed until bootstrap completes (skip, setup/update, or warn-and-continue).
Completion criterion: bootstrap outcome identified (skip, setup/update OK, or warn-and-continue).
Step 1 — Select bundle and script
/modifywithout hint → ask which catalog bundle to adapt.- One main script per session by default.
- If subscripts are involved → ask whether to edit together or one file per session.
Completion criterion: target codes/<type>/<bundle>/ and main .m are identified.
Step 2 — Copy catalog → modify (mandatory)
./scripts/modify-copy.sh <type> <bundle>Copies the entire bundle folder (N:1 sets included). Reuses existing modify/ copy unless MODIFY_OVERWRITE=1.
Do not edit any file until this copy succeeds.
Completion criterion: modify/<type>/<bundle>/ exists and codes/ is unchanged.
Step 3 — Grill-me on changes
Run .agents/skills/grill-me/SKILL.md on what changes — behavior, plots, outputs, units — not the whole script from scratch.
If base companion .md is missing or incomplete, run the full /new checklist first.
Completion criterion: user confirmed intended changes.
Step 4 — Edit in modify/ only (with MATLAB skills)
Read and apply docs/agents/matlab-skills-gate.md before editing any .m file.
Then:
- Rename
.m+.mdtogether if purpose changes (user confirmation). - Update
.mdhistory / relevant sections with each meaningful change.
Completion criterion: edits exist only under modify/; companion reflects the new behavior.
Step 5 — Recommend /accept modify
Ask whether to promote now or keep iterating:
/accept modifyCompletion criterion: user knows how to promote or continue editing.
Safety (non-negotiable)
- Never write to
codes/except via/acceptor confirmed/build. - Write only under
modify/after the mandatory copy step. - Never change units without warning; never delete measurement data.
Reference
- Wayfinder spec:
.scratch/matstudylab/issues/07-grilling-comando-modify.md - Companion template:
docs/templates/script-companion.md - MATLAB skills gate:
docs/agents/matlab-skills-gate.md
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.