chore: re-sync agent skills to upstream mattpocock/skills

Local snapshots dated 2026-09-16; upstream has moved on since. Refreshes
7 SKILL.md files (code-review, diagnosing-bugs, implement, tdd, grilling,
handoff, teach): tracker-doc references generalized, CONTEXT.md renamed
GLOSSARY.md, implement gains ticket-fetch step + Skill-tool invocation,
grilling question wording rule, handoff names the OS temp dir, teach
workspace-path resolution + quiz answer-position rules, tdd seam notes.
find-skills (vercel-labs) and prototype already current. Skill updates
take effect next session (discovery runs at startup).
This commit is contained in:
Frank committed 2026-10-18 14:57:20 -07:00
1 parent 7b7dbf55c2
commit 8702f3058d
7 files changed
+18 -12

No files matched your search

+2 -2
View File
@@ -9,7 +9,7 @@ The user has asked you to teach them something. This is a stateful request - the
## Teaching Workspace
Treat the current directory as a teaching workspace. The state of their learning is captured in this directory in several files:
Treat the current directory as a teaching workspace. Workspace paths (`./lessons/` and the rest) resolve from the directory `/teach` was run in; only the `*-FORMAT.md` links resolve from this skill's folder. The state of their learning is captured in this directory in several files:
- `MISSION.md`: A document capturing the _reason_ the user is interested in the topic. This should be used to ground all teaching. Use the format in [MISSION-FORMAT.md](./MISSION-FORMAT.md).
- `./reference/*.html`: A directory of reference materials. These are the compressed learnings from the lessons - cheat sheets, reference algorithms, syntax, yoga poses, glossaries. They are the raw units of learning. They should be beautiful documents which print out well, and are designed for quick reference.
@@ -107,7 +107,7 @@ For skill acquisition, difficulty is the tool. Effortful retrieval is what build
Each of these should be based on a **feedback loop**, where the user receives feedback on their performance. This feedback loop should be as tight as possible, giving feedback immediately - and ideally automatically.
For quizzes, each answer should be exactly the same number of words (and characters, if possible). Don't give the user any clues about the answer through formatting.
For quizzes, each answer should be exactly the same number of words (and characters, if possible). Vary which position holds the correct answer across questions. Don't give the user any clues about the answer through formatting or order.
## Acquiring Wisdom