accept
Skill2 starsChanged 3 months agoMITView on GitHub
Promote staging bundles into the catalog, or attach explain docs from explain/.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- leinardi/adversarial-review-looptheir own version, first seen Nov 8, 2026
- menot-you/n-soultheir own version, first seen Nov 1, 2026
- open-agent-power/open-knowledge-studiotheir own version, first seen Nov 1, 2026
- foliveira/harmoniatheir own version, first seen Sep 27, 2026
- cristian-robert/claude-code-harnesstheir own version, first seen Sep 15, 2026
- Nagiliant/Genesis-Legacy-V2their own version, first seen Jun 18, 2026
Used with
Projects with it also use status.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- open-agent-power/open-knowledge-studio★ 9same name
- cristian-robert/claude-code-harness★ 2same name
- foliveira/harmonia★ 2same name
- leinardi/adversarial-review-loop★ 2same name
- Nagiliant/Genesis-Legacy-V2★ 2same name
- larsch/skills★ 0same name
- menot-you/n-soul★ 0same name
- synaptiai/bdsk★ 0same 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
- 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
- modifySkill
- 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
11 rules. 0 are common, 3 are distinctive, and 8 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
3
Distinctive
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 (if present), docs/spec.md (/accept requirements), and CONTEXT.md before acting.
- Very specific: line 13
Read and execute .agents/skills/matstudylab-bootstrap/SKILL.md before any other step.
- Very specific: line 14
Do not proceed until bootstrap completes (skip, setup/update, or warn-and-continue).
- Very specific: line 31
If variant is all (or default) and both new/ and modify/ have pending bundles, ask: accept everything, only new/, or only modify/?
- Very specific: line 35
Read LORE.md for git workflow (local-only or own-repo) and folder map context.
- Very specific: line 37
If LORE.md is missing, assume local-only and note it to the user.
- Very specific: line 67
Block: if catalog bundle or matching .m is missing
- Distinctive: line 70
Completion criterion: every item in scope passes validation or the command stops with a clear block reason.
- Distinctive: line 84
After a successful run, clear staging for everything accepted:
- Very specific: line 110
Never write to codes/ except through this confirmed flow.
- Distinctive: line 111
Never delete measurement data files.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
The only allowed write path into codes/. Two modes: promote (new/ / modify/) or attach (explain/ → catalog).
Read LORE.md (if present), docs/spec.md (/accept requirements), 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).
On NODE_MISSING or SYNC_FAILED_CONTINUE: warn + continue with vendored skills only — no three-option HITL menu (that menu is /build only).
Completion criterion: bootstrap outcome identified (skip, setup/update OK, or warn-and-continue).
Step 1 — Parse variant
| User input | Scope |
/accept, /accept all | All pending bundles in new/ and modify/ |
/accept new | Only new/ |
/accept modify | Only modify/ |
/accept explain | Copy explain/explain_<stem>.md into matching codes/<type>/<bundle>/ |
/accept explain <type> <bundle> | One catalog bundle only |
Completion criterion: variant is identified.
If variant is all (or default) and both new/ and modify/ have pending bundles, ask: accept everything, only new/, or only modify/?
Step 2 — Read LORE
Read LORE.md for git workflow (local-only or own-repo) and folder map context.
If LORE.md is missing, assume local-only and note it to the user.
Completion criterion: git workflow preference is known.
Step 3 — List and validate scope
Promote (all / new / modify)
ACCEPT_DRY_RUN=1 ./scripts/accept-bundle.sh <variant>Validation rules:
- At least one
.m— otherwise block - At least one base companion
.md(notexplain_*.md) — otherwise block and offer to generate fromdocs/templates/script-companion.md - 1:1: one
.m+ one.mdwith matching stems - N:1: multiple
.m+ exactly one base.md
Promotion also attaches matching explain/explain_<stem>.md files into the catalog bundle.
Attach (explain)
ACCEPT_DRY_RUN=1 ./scripts/accept-bundle.sh explain [type bundle]For each explain/explain_<stem>.md:
- Resolve
codes/<type>/<bundle>/from path (explain/<type>/<bundle>/…) or by uniquecodes/*/*/<stem>.m - Block if catalog bundle or matching
.mis missing - Copy into catalog
Completion criterion: every item in scope passes validation or the command stops with a clear block reason.
Step 4 — Confirm destination
Confirm ambiguous codes/<type>/<bundle>/ paths with the user. New codes/<type>/ folders require user confirmation and a LORE folder-map row.
Completion criterion: user confirmed each destination path.
Step 5 — Execute
./scripts/accept-bundle.sh <variant> [type bundle]After a successful run, clear staging for everything accepted:
new//modify/— remove the promoted bundle folder (empty parent dirs too)explain/— remove each attachedexplain_<stem>.md(empty parent dirs too)
Completion criterion: each item exists under codes/; no accepted files remain in new/, modify/, or explain/ for this run.
Step 6 — Git per LORE
| Git workflow | Action |
local-only | Do not commit or push |
own-repo | Propose commit message catalog: <type>/<bundle> after user OK; then ask about push to main |
Completion criterion: git behavior matches LORE.
Step 7 — LORE updates (significant changes only)
Append to LORE.md only when this accept introduced something that changes future behaviour — for example a new codes/<type>/ folder, a reclassification, or a confirmed preference about units, equipment, or workflow.
Routine promote/attach (moving drafts or study docs into an existing bundle) does not warrant a decision-log entry. Do not ask the user about LORE unless a significant change occurred in this run.
Completion criterion: LORE updated when warranted; otherwise proceed without mentioning the decision log.
Safety (non-negotiable)
- Never write to
codes/except through this confirmed flow. - Never delete measurement data files.
- From
new/: block ifcodes/<type>/<bundle>/already exists (use/modifyinstead).
Reference
- Wayfinder spec:
.scratch/matstudylab/issues/08-grilling-comando-accept.md - Companion template:
docs/templates/script-companion.md - Step 0 contract:
docs/agents/command-skill-step-0.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.