aicodeking/deepseek-stack

ds-lessons

Find mistakes agents keep repeating in this repo and turn each into structure that blocks it, preferring types over lint over tests over docs, plus an end-of-session reflection.

Quelltext ansehen

Verwendung

  1. Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
  2. Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
  3. Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/aicodeking/deepseek-stack --skill ds-lessons

Vor dem Start

  • Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
  • Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

ds-lessons

An instruction an agent can skip is a wish. Make repeated mistakes fail loudly instead.

Steps

  1. Gather mistakes. Read the current session, recent commits, reverts, review comments, agent instruction files and workaround comments. Group them into classes. A class counts once it happened twice.
  2. For each class, pick the highest level that works:
  3. Structure: one owner per piece of state, one supported way per task, hidden internals, delete old patterns an agent would copy.
  4. Types: make the bad state impossible to write.
  5. Lint or CI check: the error message names the right file, type or function to use. If the bad pattern is already common, fail only on new additions.
  6. Test: checks behavior, not internals.
  7. Docs or agent rules: only for judgment calls that cannot be checked. Add a short example of the failure.
  8. Fix the most frequent classes now, one commit each.
  9. Prove each new check. Re-introduce a real past mistake, run the check, and show it fails. Then remove it and show it passes.
  10. Keep a table in the agent instruction file: rule, and what enforces it. If a rule already existed but nothing enforced it, treat it as a repeat and enforce it now.
  11. End-of-session reflection: list what went wrong, what took extra loops and what the user corrected. Route each item to a check, a skill edit or a rule. Drop one-off issues.

Stop when

  • Each chosen class has an enforcement that you showed failing on a real mistake.
  • Or you have handled the top three classes this session. Note the rest.

Rules

  • If the fix is structural, do not also add prose. The prose was the symptom.
  • Report each class with evidence, the level chosen, and why a higher level did not work.
aus demselben Repository

Weitere Skills

Alle Skills
aicodeking
Community

ds-adopt

Takes over an existing PR, branch or agent thread and finishes its original goal while keeping credit for the first contributors. Use when the user says take over, adopt, pick up or finish this PR, or /ds-adopt.

Installationen / 1h
2
GitHub Stars
75
Aktualisiert
28. Okt.
aicodeking
Community

ds-best-of-n

Run N independent attempts at the same task in parallel, pick the strongest as the base, and graft the best parts of the others into it. Use when one attempt at a non-trivial artifact could land on the wrong shape, or for /ds-best-of-n, 'try a few versions', 'best of 3'.

Installationen / 1h
2
GitHub Stars
75
Aktualisiert
28. Okt.
aicodeking
Community

ds-blast-radius

Find what a change could break outside its own diff, then prove the key safety fact by running real code. Use before shipping a risky or untrusted change, for 'what could this break', 'blast radius of X', or /ds-blast-radius.

Installationen / 1h
2
GitHub Stars
75
Aktualisiert
28. Okt.
aicodeking
Community

ds-blueprint

Design the types, function signatures and module layout first, agree on that shape, then implement against it. Use when work is non-trivial and coding straight away would lock in the wrong structure, or for /ds-blueprint, 'design this first', 'architect this'.

Installationen / 1h
2
GitHub Stars
75
Aktualisiert
28. Okt.